[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7B95CRRAW9BMRC3Q98KTPVG":3,"skill-same:01M7B95CRRAW9BMRC3Q98KTPVG":104},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":38,"commitSha":39,"skillDirectory":40,"forksCount":41,"repositoryHtmlUrl":42,"repositoryHomepageUrl":43,"ownerHtmlUrl":44,"ownerBlogUrl":45,"ownerDescription":46,"updatedAt":47,"install":48,"resources":61},"01M7B95CRRAW9BMRC3Q98KTPVG","stickman-video",null,"Make a viral stickman video in code, with no video model: a jointed SVG stick figure (round head, two-bone arms and legs with fixed bone lengths, poses written as joint angles) acts out a survival-choice story, a POV story, a \"fake friend vs real friend\" contrast, a history explainer or a stick fight, with a DAY counter, rules that appear one at a time, word-timed captions, procedural sound and a two-choice \"FOLLOW FOR DAY 2\" ending, rendered to a 1080x1920 MP4 with HyperFrames. Ships the working rig (planted-foot walk, breathing idle, head turns, blinks, shock, crouch), script templates with word counts, the fixes for stiff head-only stickman animation, and a 24 s example whose voice cost $0.04 (4 credits). Use when someone asks for a stickman video, stick figure animation, a faceless stickman channel, a survival choice story, POV stickman, or wants to \"make videos like the viral stickman reels\". For Google Flow or Veo clip prompts use kaomei\u002Fstickman-video-director instead.","hashgraph-online\u002Fawesome-codex-plugins","hashgraph-online","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F160371962?v=4","01M6CNB6NRJVNNGN14TR01Q6D3","HOL (Hashgraph Online)","01M6JT1HSKKG9V68KQAQGBA7XP",1575,"MIT","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FvargHQ\u002Fskills\u002Fstickman-video\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: stickman-video\ndescription: >-\n  Make a viral stickman video in code, with no video model: a jointed SVG stick figure (round\n  head, two-bone arms and legs with fixed bone lengths, poses written as joint angles) acts out\n  a survival-choice story, a POV story, a \"fake friend vs real friend\" contrast, a history\n  explainer or a stick fight, with a DAY counter, rules that appear one at a time, word-timed\n  captions, procedural sound and a two-choice \"FOLLOW FOR DAY 2\" ending, rendered to a\n  1080x1920 MP4 with HyperFrames. Ships the working rig (planted-foot walk, breathing idle, head\n  turns, blinks, shock, crouch), script templates with word counts, the fixes for stiff\n  head-only stickman animation, and a 24 s example whose voice cost $0.04 (4 credits). Use when someone\n  asks for a stickman video, stick figure animation, a faceless stickman channel, a survival\n  choice story, POV stickman, or wants to \"make videos like the viral stickman reels\". For\n  Google Flow or Veo clip prompts use kaomei\u002Fstickman-video-director instead.\nlicense: MIT\ncompatibility: >-\n  HyperFrames 0.9 (bunx hyperframes or npx hyperframes; brings Chrome, needs Node 22 and\n  ffmpeg). The voice is optional: the varg MCP (https:\u002F\u002Fmcp.varg.ai\u002Fmcp) or a VARG_API_KEY, or\n  any recorded file. Word timings come from local whisper.cpp through hyperframes transcribe.\n  No key is needed for the picture, the sound effects or the render.\nmetadata:\n  author: vargHQ\n  version: \"1.0.0\"\n  varg.cost.typical: \"$0.04 (4 credits) for a 60-word ElevenLabs v3 voiceover; picture, sound and render free\"\n  varg.runtime.typical: \"17 s to render 24 s of 1080x1920 at 30 fps on an Apple M1 Pro\"\n  varg.models: \"eleven_v3 (voice, optional)\"\n  varg.outputs: \"mp4 1080x1920 30 fps, contact sheet\"\n  openclaw:\n    requires:\n      anyBins:\n        - ffmpeg\n    homepage: https:\u002F\u002Fvarg.ai\u002Fhow-to\nallowed-tools: Bash(bunx:*) Bash(npx:*) Bash(bun:*) Bash(ffmpeg:*) Bash(ffprobe:*) Bash(curl:*) Read Write Edit\n---\n\n# Stickman video: a jointed figure, a few rules, a choice\n\nStickman reels are a format wave on X, TikTok and Shorts in autumn 2026, and the pitch that travels is \"100% code, $0 video generation\" ([@finnardley](https:\u002F\u002Fx.com\u002Ffinnardley\u002Fstatus\u002F2115786060231770351), 65,440 views). The complaints are just as consistent: limbs too long, a character that only moves its head, monotone animation ([a user replying to the stickman-video-director author](https:\u002F\u002Fx.com\u002FGazunH26262\u002Fstatus\u002F2121123319143633304)). This skill fixes those with a real rig: bones of fixed length, poses as angles, legs solved by inverse kinematics, and several motion layers running at once.\n\nThe example in `assets\u002Fexample\u002F` is a 24.3 s \"Day 1: lighthouse rules\" reel built with this skill: an original premise, a 60-word voice for $0.04 (4 credits), procedural sound, word-timed captions, three rules, a two-choice ending, rendered in 17 s.\n\n## 1. Ask, then go\n\nAsk once, in one message, with a default for each. Then write the script and show it before building.\n\n| Ask | Options | Default |\n|---|---|---|\n| Format | survival choice (DAY N + rules + 1\u002F2 ending), POV, contrast (fake vs real), history explainer, stick fight | survival choice |\n| Length | 15–25 s (one episode, Shorts\u002FReels), 45–60 s, longer = a series of episodes | 20–25 s |\n| Ratio | 9:16, 16:9 (YouTube long form), 1:1 | 9:16, 1080x1920, 30 fps |\n| Voice | AI narrator on varg at about $0.04 (4 credits) per 60 words, their own recording, no voice (captions + sound only) | AI narrator, calm and tense |\n| Style | night set with a white figure; paper white with a black figure; retro TV glow; one set drawn in code | night set |\n\nIf they bring a premise, use it. If not, offer three one-line premises that are not copies of a known channel's episodes (see section 9).\n\n## 2. Five formats and why each travels\n\nView counts are the X posts' own counters on the collection date (2026-11-13). Follower and income figures inside those posts are the posters' claims, not verified.\n\n| Format | What it is | Why it travels | Evidence |\n|---|---|---|---|\n| **Survival choice** | Second person (\"you\"), a DAY counter, 3–4 rules that appear one at a time, a rule gets tested, the ending card \"1: … \u002F 2: …\" and \"FOLLOW FOR DAY 2\" | The choice asks for a comment, the DAY counter promises a series, the rules give the viewer something to check against the picture | [@finnardley](https:\u002F\u002Fx.com\u002Ffinnardley\u002Fstatus\u002F2115786060231770351) code-only prompt with exactly this structure, 65,440 views; [@brainextends](https:\u002F\u002Fx.com\u002Fbrainextends\u002Fstatus\u002F2111569272732553535) zombie-on-a-farm interactive episodes (\"22M views, 154K followers in 5 days\"), 50,885 views; [@laurgrowth](https:\u002F\u002Fx.com\u002Flaurgrowth\u002Fstatus\u002F2117973871513194869) empty subway, \"1: GET ON \u002F 2: STAY\", 6,615 views; [@CrazyKaomei](https:\u002F\u002Fx.com\u002FCrazyKaomei\u002Fstatus\u002F2119617667623776480) doomsday-survival style with an A-or-B ending, 21,050 views |\n| **POV** | \"POV: you're the last one in …\"; the viewer is the figure, the first frame is the situation | No setup needed; the hook is the situation itself; easy to make 4–5 hook variants of one story | [@FeyiLux](https:\u002F\u002Fx.com\u002FFeyiLux\u002Fstatus\u002F2103734366182441001) \"how to start the POV stickman niche\" (and: the niche is crowded, write 4–5 hooks), 26,076 views; [@nolantoken](https:\u002F\u002Fx.com\u002Fnolantoken\u002Fstatus\u002F2113601722253758649) creepy stickman stories with choice endings, an app account claiming 56.3k followers in 15 posts, 12,034 views |\n| **Contrast** | Two figures, the same situation twice: fake friend vs real friend, you vs you, white figure vs yellow figure; one line of text | Readable with the sound off in under a second; relatable; ends in \"tag your real friend\" | [@ghosstty_](https:\u002F\u002Fx.com\u002Fghosstty_\u002Fstatus\u002F2117010986812998119) on 4 \"fake friend vs real friend\" reels over 50M views each (top 97.3M), 7,620 views; [@maubaron](https:\u002F\u002Fx.com\u002Fmaubaron\u002Fstatus\u002F2119163598660665748) on 11-second stick-figure clips, black background, one line of text, \"225M views in a few days\", 13,229 views |\n| **History explainer** | A deadpan narrator; a grand event told through one small stickman's absurd problem; each claim one picture | The contrast between the serious voice and the silly picture; evergreen topics; long watch time | [@CrazyKaomei](https:\u002F\u002Fx.com\u002FCrazyKaomei\u002Fstatus\u002F2112791668332319070) \"history picture book\" style, \"deadpan absurd contrast\", 57,439 views; [@sarpstar](https:\u002F\u002Fx.com\u002Fsarpstar\u002Fstatus\u002F2119082994925211686) an 8-minute documentary made in code overnight, 540,864 views; a reply asking how to get this style with a consistent character was pointed to the stickman-video-director repo |\n| **Stick fight** | Two figures stand in for two teams, apps or models and fight in three exchanges | Rivalry, a clear winner, short; the \"made 100% in code\" claim is part of the post | [@rayanabdulcader](https:\u002F\u002Fx.com\u002Frayanabdulcader\u002Fstatus\u002F2119995155625181371) two chat-app dock icons fighting as stick figures, 100% code, 137,490 views; [@Framer_X](https:\u002F\u002Fx.com\u002FFramer_X\u002Fstatus\u002F2117995586528104755) a stickman fight used as the motion reference for other characters, 72,629 views |\n\nAlso cited for the size of the wave: [@Aygramm_](https:\u002F\u002Fx.com\u002FAygramm_\u002Fstatus\u002F2112481704724004911) \"stickman animations are the new gold rush\", 40,656 views; [@theoardley](https:\u002F\u002Fx.com\u002Ftheoardley\u002Fstatus\u002F2116684286837330374) listing \"stickman survival stories\" among free Claude video skills, 499,979 views.\n\n## 3. Script templates\n\n**Pace, measured.** ElevenLabs v3 \"Adam\" read the 60-word example in 25.1 s raw (2.4 words\u002Fs, sentence pauses of about 0.4 s). Shortening every pause to 0.2 s gave 22.2 s (2.7 words\u002Fs) without stretching speech. Plan at 2.5 words per second of voice, then tighten pauses. Leave 2 s after the last word for the ending card.\n\n### Survival choice, 20–25 s, 55–65 words\n\n| Beat | Seconds | Words | Line pattern | Picture |\n|---|---|---|---|---|\n| Hook | 0–1.2 | 2 | \"Day one.\" | DAY N title already on frame 0 over the figure mid-stride |\n| Situation | 1.2–5 | 10–12 | \"You're the new [role]. The last [role] left three rules.\" | walk in, stop, look back over the shoulder, look up, look at the camera on \"three rules\" |\n| Rule 1 | 5–7.6 | 6–8 | \"Rule one: [simple instruction].\" | rule card 1 lands on the word \"Rule\"; the figure shows it (points at the thing) |\n| Rule 2 | 7.6–12.3 | 12–14 | \"Rule two: [instruction]. If [condition], [don't do X].\" | the condition comes true on screen; the figure almost does X and stops |\n| Rule 3 | 12.3–15.2 | 7–8 | \"Rule three: never [the thing about to happen].\" | the figure walks to the danger and looks at it |\n| Break | 15.2–20.2 | 12–14 | \"It's [time]. [The rule is tested]. And [a twist that makes it personal].\" | the HUD clock flips; shock jump; crouch and tremble; the camera creeps toward the danger |\n| Choice | 20.2–22.3 | 8 | \"[Option 1], or [option 2]?\" | \"1:\" lands on option 1's first word, \"2:\" on option 2's; the figure looks between the two |\n| Hold | 22.3–24.3 | 0 | none | \"FOLLOW FOR DAY 2\" for at least 2 s |\n\nThe example's script: \"Day one. You're the new lighthouse keeper. The last keeper left three rules. Rule one: the light never stops turning. Rule two: count the ships. If there's one more than yesterday, don't wave. Rule three: never open the door after midnight. It's twelve-oh-one. Someone knocks. And the voice outside sounds like yours. Open the door, or keep the light on?\" Write numbers as words for the voice (\"twelve-oh-one\") and fix them back in the captions.\n\n### POV, 15–20 s, 35–50 words\n\n0–1 s: the text \"POV: [situation]\" on frame 0 (on screen; the voice may read it). Then three escalating beats of 3–4 s, 8–12 words each, each one a new action or a new thing in the set. End on a question or a choice (6–8 words). Write 4–5 hook variants and test them as separate posts.\n\n### Contrast, 10–15 s, 0–25 words\n\n0–1.5 s: one line of setup text (\"When you trip in public:\"). Then the same staging twice, 4–6 s each, label on top (\"FAKE FRIEND\" \u002F \"REAL FRIEND\"): the same trigger, opposite reactions, a 0.4 s hold on each reaction. 1–2 s ending: \"Tag your real friend\". Often no voice: music bed and two or three effects.\n\n### History explainer, 45–60 s, 110–150 words\n\n\"In [year], [grand event].\" in a deadpan voice, then one claim per sentence, one picture per claim, a change every 2–3 s. Every third beat cuts from the grand scale (a map, a crowd of identical figures) to one small figure's problem. End on an ironic payoff and a question. Every fact needs a source you can name; never invent dates, numbers or quotes.\n\n### Stick fight, 10–20 s, 0–10 words\n\nName tags over two figures (generic stand-ins, not real logos). Three exchanges: anticipation 0.15–0.2 s (wind up the opposite way), hit in 2–3 frames, reaction held 0.3–0.5 s, a hit sound on the contact frame. A reversal in the third exchange, then a winner pose and one line of text.\n\n## 4. The rig, and the fixes for stiff stickmen\n\nThe figure is `assets\u002Fstickman-rig.html` (a 9-second pose tour that renders as is) and the same code as `assets\u002Fexample\u002Frig.js`. API, channel table and pose values: `references\u002Frig.md`.\n\n| Complaint | Fix in the rig |\n|---|---|\n| Limbs too long, proportions drift | Fixed bones in local units: head radius 36, neck 12, torso 124, upper arm 70, forearm 66, thigh 86, shin 84. Nothing ever stretches; an unreachable foot target stops where the leg ends. |\n| Limbs detach, poses pop | One SVG path per limb, recomputed every frame from joint angles. Never swap whole images between poses. |\n| Feet slide | The walk phase comes from the distance the hips have travelled, not from time: the stance foot is planted at any speed. Legs are two-bone IK with the knee bending forward. |\n| Only the head moves; monotone | Every shot has a body action. Motion is layered: keyed pose, walk cycle, breathing (3.1 s) and weight shift (5.7 s), tremble, blinks, and a line boil (seeded jitter of 0.8 px redrawn 12 times a second). |\n| Everything moves at once, on one curve | Overlapping action: the head leads by 0.05 s, the near arm follows by 0.05–0.07 s, the far arm by 0.09–0.11 s. Eases by job: `snap` for reactions, `back` for gestures, `inOut` for looks, `walk` (short ramps, constant speed) for travel. |\n| The face says nothing | A head turn is the eyes sliding across the head (spacing narrows toward profile). Brows appear only with an emotion; an O-mouth for shock; eyes up to 1.6x. |\n| Arms vanish when they cross the body | The near arm and leg get a dark outline pass that starts partway down the bone, so the shoulder and hip joins stay clean. |\n\nActing rules:\n\n- One action per beat: anticipate (0.1–0.2 s), act fast (`snap`, 0.1–0.15 s), hold the reaction 0.4–0.8 s.\n- Shock is a sequence, not a pose: jump back 40 px with arms up and eyes 1.5x, land with the knees absorbing (`hipDrop` 34), then crouch (`hipDrop` 80, lean 26, tremble). Keep the eyes visible after the crouch: drop the near arm to the knees when the figure peeks.\n- Look-around: over the shoulder (`lookX` -1), then up, then at the camera on the line that matters.\n- Never both arms in unison, never a perfectly mirrored pose.\n- No principal picture holds still for more than 2.5 s. Breathing alone does not count, and neither does a camera move or a text entrance on its own: give the figure an action.\n- Turning around is a 0.16 s flip through edge-on; author a blink on it.\n\n## 5. Sound and captions\n\n**Voice.** On varg: `check_balance`, then `search_voices` with an intent such as \"calm, tense, low male English narrator for a dark survival short\", then `estimate_cost`, then one `generate_speech`. The example used \"Adam\" (Deep English Story Voice, varg voice id `preset_610bdb815cd5`) on `eleven_v3`: 354 characters, 60 words, **$0.04 (4 credits)**, one take. Download the file, then shorten the pauses: `bun tighten-pauses.mjs voice.mp3 assets\u002Faudio\u002Fvoice.wav` (pauses over 0.25 s become 0.2 s; speech is never time-stretched).\n\n**Word timings, free.** `bunx hyperframes transcribe assets\u002Faudio\u002Fvoice.wav --model small.en --language en` runs whisper.cpp locally (2 s for 22 s of voice) and writes `assets\u002Faudio\u002Ftranscript.json`. Read it: the example's ASR wrote \"twelve-oh-one\" as \"1201\". Do not pay for transcription.\n\n**Captions.** `bun captions.mjs assets\u002Faudio\u002Ftranscript.json \u003Cvoice start> \u003Cwords already on a title> \u003Cending card start>` writes the groups into `index.html`: at most 3 words, one line of at most 18 characters (font shrinks from 74 px for long lines), a break at punctuation or a pause of 0.15 s or more, the active word in yellow. Place them under the rules and above the figure's head, inside the 168–1330 px band of a 1080x1920 frame. Hide them while the ending card shows the same words.\n\n**Ambience and effects.** One bed plus 2–4 effects, each on a visible cause. `bun sfx.mjs assets\u002Faudio 25` synthesizes everything with ffmpeg, so nothing needs a licence: a sea, wind and lamp-motor bed normalised to -30 LUFS; a low thud for the title stamp; a door knock in three takes at different pitch; an electrical buzz gated by the same on\u002Foff table as the lamp flicker in the picture; a whoosh that peaks 0.8 s after it starts. If you use a library sound instead, keep its URL and licence (CC0 or the library's own terms) next to the file. Levels in the example: voice 1.0, bed 1.0, knocks 0.65–0.8, thud 0.45–0.55, buzz 0.3, whoosh 0.4; the mix measured -13.5 LUFS integrated, -1.0 dBTP true peak, no clipping (measured with `hyperframes audio`, not listened to).\n\n## 6. Build it in HyperFrames\n\n1. `bunx hyperframes init my-reel --resolution portrait --non-interactive --skip-transcribe` (or `npx`).\n2. Copy `assets\u002Fexample\u002F` into it (`index.html`, `rig.js`, `captions.mjs`, `sfx.mjs`, `tighten-pauses.mjs`), or start from `assets\u002Fstickman-rig.html` as `index.html` for a bare stage. The example has no media: make `assets\u002Faudio\u002F` with steps 3 and 4.\n3. Voice, pauses, transcript, captions (section 5).\n4. `bun sfx.mjs assets\u002Faudio \u003Cfilm seconds + 1>`; place each effect so its peak lands one frame after its picture.\n5. Write the film in `index.html`:\n   - One clock. A proxy object with a setter, tweened from 0 to the duration on the paused GSAP timeline, redraws the set and the rig for that exact time. Nothing reads a clock, `Math.random` or the previous frame.\n   - The set is SVG inside a camera group (`translate · scale · translate` from three keyed channels `cx`, `cy`, `cs`). Draw it in code: walls, a window, a door, a lamp. A world wider than the frame lets the camera pan between places.\n   - The figure: `Stickman.create(group, { scale, ground, blinks })`, a `Stickman.track(...)` of pose keys written as `P.move(start, duration, { channel: value }, ease)` on the voice's word times, and `Stickman.draw(fig, P, t)` inside the clock.\n   - HUD, rules, captions and the ending card are HTML clips animated on the same timeline. Rules land on the word \"Rule\"; the clock flips on its word.\n6. `bunx hyperframes lint`, then `bunx hyperframes check --json --no-cache`. Use `bunx hyperframes`, not `bunx --bun hyperframes`: under the Bun runtime `check` printed nothing on repeat runs.\n7. Look: `bunx hyperframes snapshot --at \u003C12 beat times> --no-end`, then `--range \u003Cwalk start>,\u003Cwalk end> --frames 8` for the walk, and zoomed crops of the figure at the reaction poses.\n8. `bunx hyperframes render --quality delivery --output out.mp4`, then `ffprobe` (duration equals the root `data-duration`), `bunx hyperframes audio out.mp4 --json`, and a contact sheet decoded from the MP4.\n\nTwo traps the example hit:\n\n- **Caption hard-kill.** Under a clip host, GSAP records the inherited `visibility: hidden` as the start value, so `tl.set(group, { visibility: \"hidden\" }, end)` leaves every group hidden after a backward seek. Kill caption groups with `opacity: 0` only.\n- **Two-line captions** collide with things drawn in the set (the example's ship numbers). Keep one line per group.\n\nThe example is one `index.html` on purpose (one clock drives the rig and the set), so `lint` warns that the scenes are not sub-compositions; that warning is expected.\n\n## 7. Checks before delivery\n\n- [ ] Frame 0 is the hook: the DAY title or the POV line plus the figure mid-action, never black.\n- [ ] Limbs attached in every sampled frame, bones the same length, feet on the ground except in a jump, no foot sliding during the walk (8-frame strip).\n- [ ] Walk, breathing idle, a head turn, one reaction (shock or crouch) and blinks all appear; nothing principal holds for more than 2.5 s.\n- [ ] Rules appear one at a time on their words; the clock or DAY counter changes on its word.\n- [ ] Captions one line, word-timed, inside 168–1330 px, nothing readable under the right-hand action rail.\n- [ ] The ending: \"1:\" and \"2:\" on screen with the spoken options, \"FOLLOW FOR DAY 2\" for at least 2 s.\n- [ ] Sound present, effects on their pictures, about -14 LUFS, true peak at or under -1 dBTP; say it was measured, not heard.\n- [ ] `check` has no errors; duration and size match (1080x1920, 30 fps).\n\n## 8. Costs\n\n| Item | Measured |\n|---|---|\n| Voice, 60 words, ElevenLabs v3 on varg | $0.04 (4 credits), one take |\n| Word timings (local whisper.cpp) | free, 2 s |\n| Sound effects and ambience (ffmpeg) | free |\n| Render, 24.3 s at 1080x1920, 729 frames | free, 17.3 s on an Apple M1 Pro (hardware GPU, screenshot capture) |\n| Total for the example | $0.04 (4 credits) |\n\n## 9. Other routes\n\n- **kaomei\u002Fstickman-video-director** ([GitHub](https:\u002F\u002Fgithub.com\u002Fkaomei\u002Fstickman-video-director), MIT, by [@CrazyKaomei](https:\u002F\u002Fx.com\u002FCrazyKaomei), about 5,900 stars in November 2026). Director mode writes a treatment, then one prompt per roughly 10-second clip for Google Flow (Gemini Omni Flash), Veo, Kling, Runway or Luma; you generate and edit the clips yourself. Autopilot renders a narrated, captioned MP4 locally (Node 20+, FFmpeg) after a 20-second sample is approved; the author recommends Codex. Eleven visual styles. Install by pasting the repo URL into your agent with \"Install this Skill for me\"; the installed skill is called `directing-stickman-videos`. Use it when the person wants generated clips or one of its styles.\n- **Generated 2.5D look on varg.** A character sheet and set stills with `gpt_image_2_6` (estimate on 2026-11-13: up to $0.06 (6 credits) per 9:16 image), approved first, then animate with `kling_v4` (estimate on the same day: up to $0.79 (79 credits) for a 5 s 9:16 clip, priced as text-to-video; price the image-to-video call itself before the batch; `kling_v4_flash` for drafts). Run `estimate_cost` before each batch. The honest caveat: video models drift on stick figures. Limbs multiply or thicken, heads detach, hair and clothes appear, and two shots rarely match. Keep shots to 5 s, reuse the same reference, judge every take, and keep anything that must stay jointed (a walk, a fight, a pose that carries the joke) in code. A hybrid works: generated background stills under the code figure.\n\n## 10. What not to do\n\n- Do not copy a named channel's characters, names, catchphrases, signature outfit or episode premises. Make your own figure and your own premise; \"inspired by a format\" is fine, a look-alike is not.\n- Do not use real people's names, faces or cloned voices; use generic stand-ins in fights and contrasts, not real logos.\n- Label AI content where the platform asks for it (TikTok's AI-generated label, YouTube's altered or synthetic content disclosure for realistic material), and write \"AI voice\" in the caption when the narrator is synthetic.\n- Do not present invented stories as true, and do not invent facts in explainers. Keep survival stories PG: tension, not gore.\n- Do not promise views or income: the numbers in the posts above are the posters' claims.\n- Do not use `Math.random`, `Date.now`, timers or the previous frame as state; do not swap images for poses; do not stretch bones; do not put text below 1330 px on 9:16.\n\n## Sources\n\n- X research, collected 2026-11-13: the posts linked in section 2, the stickman-video-director launch and updates by [@CrazyKaomei](https:\u002F\u002Fx.com\u002FCrazyKaomei\u002Fstatus\u002F2084217266703393186), and user questions under them ([limbs and monotone motion](https:\u002F\u002Fx.com\u002FGazunH26262\u002Fstatus\u002F2121123319143633304), [two-bone IK arms and lip sync by loudness](https:\u002F\u002Fx.com\u002Ftebet007\u002Fstatus\u002F2116324211002401064)).\n- kaomei\u002Fstickman-video-director: `SKILL.md` (Director pacing of about 20–25 voice words per 10 s clip, a visual change every 2–3 s) and `references\u002Fautopilot.md` (no principal-picture inactivity over 2.5 s; camera moves or text entrances alone do not count as animation).\n- HyperFrames CLI 0.9.41 documentation (`hyperframes`, `hyperframes-core`, `hyperframes-cli` skills).\n- Measured on the example: voice job on varg on `eleven_v3` for $0.04 (4 credits), whisper.cpp `small.en`, ffmpeg loudness, HyperFrames render log.\n","# Stickman video: a jointed figure, a few rules, a choice\n\nStickman reels are a format wave on X, TikTok and Shorts in autumn 2026, and the pitch that travels is \"100% code, $0 video generation\" ([@finnardley](https:\u002F\u002Fx.com\u002Ffinnardley\u002Fstatus\u002F2115786060231770351), 65,440 views). The complaints are just as consistent: limbs too long, a character that only moves its head, monotone animation ([a user replying to the stickman-video-director author](https:\u002F\u002Fx.com\u002FGazunH26262\u002Fstatus\u002F2121123319143633304)). This skill fixes those with a real rig: bones of fixed length, poses as angles, legs solved by inverse kinematics, and several motion layers running at once.\n\nThe example in `assets\u002Fexample\u002F` is a 24.3 s \"Day 1: lighthouse rules\" reel built with this skill: an original premise, a 60-word voice for $0.04 (4 credits), procedural sound, word-timed captions, three rules, a two-choice ending, rendered in 17 s.\n\n## 1. Ask, then go\n\nAsk once, in one message, with a default for each. Then write the script and show it before building.\n\n| Ask | Options | Default |\n|---|---|---|\n| Format | survival choice (DAY N + rules + 1\u002F2 ending), POV, contrast (fake vs real), history explainer, stick fight | survival choice |\n| Length | 15–25 s (one episode, Shorts\u002FReels), 45–60 s, longer = a series of episodes | 20–25 s |\n| Ratio | 9:16, 16:9 (YouTube long form), 1:1 | 9:16, 1080x1920, 30 fps |\n| Voice | AI narrator on varg at about $0.04 (4 credits) per 60 words, their own recording, no voice (captions + sound only) | AI narrator, calm and tense |\n| Style | night set with a white figure; paper white with a black figure; retro TV glow; one set drawn in code | night set |\n\nIf they bring a premise, use it. If not, offer three one-line premises that are not copies of a known channel's episodes (see section 9).\n\n## 2. Five formats and why each travels\n\nView counts are the X posts' own counters on the collection date (2026-11-13). Follower and income figures inside those posts are the posters' claims, not verified.\n\n| Format | What it is | Why it travels | Evidence |\n|---|---|---|---|\n| **Survival choice** | Second person (\"you\"), a DAY counter, 3–4 rules that appear one at a time, a rule gets tested, the ending card \"1: … \u002F 2: …\" and \"FOLLOW FOR DAY 2\" | The choice asks for a comment, the DAY counter promises a series, the rules give the viewer something to check against the picture | [@finnardley](https:\u002F\u002Fx.com\u002Ffinnardley\u002Fstatus\u002F2115786060231770351) code-only prompt with exactly this structure, 65,440 views; [@brainextends](https:\u002F\u002Fx.com\u002Fbrainextends\u002Fstatus\u002F2111569272732553535) zombie-on-a-farm interactive episodes (\"22M views, 154K followers in 5 days\"), 50,885 views; [@laurgrowth](https:\u002F\u002Fx.com\u002Flaurgrowth\u002Fstatus\u002F2117973871513194869) empty subway, \"1: GET ON \u002F 2: STAY\", 6,615 views; [@CrazyKaomei](https:\u002F\u002Fx.com\u002FCrazyKaomei\u002Fstatus\u002F2119617667623776480) doomsday-survival style with an A-or-B ending, 21,050 views |\n| **POV** | \"POV: you're the last one in …\"; the viewer is the figure, the first frame is the situation | No setup needed; the hook is the situation itself; easy to make 4–5 hook variants of one story | [@FeyiLux](https:\u002F\u002Fx.com\u002FFeyiLux\u002Fstatus\u002F2103734366182441001) \"how to start the POV stickman niche\" (and: the niche is crowded, write 4–5 hooks), 26,076 views; [@nolantoken](https:\u002F\u002Fx.com\u002Fnolantoken\u002Fstatus\u002F2113601722253758649) creepy stickman stories with choice endings, an app account claiming 56.3k followers in 15 posts, 12,034 views |\n| **Contrast** | Two figures, the same situation twice: fake friend vs real friend, you vs you, white figure vs yellow figure; one line of text | Readable with the sound off in under a second; relatable; ends in \"tag your real friend\" | [@ghosstty_](https:\u002F\u002Fx.com\u002Fghosstty_\u002Fstatus\u002F2117010986812998119) on 4 \"fake friend vs real friend\" reels over 50M views each (top 97.3M), 7,620 views; [@maubaron](https:\u002F\u002Fx.com\u002Fmaubaron\u002Fstatus\u002F2119163598660665748) on 11-second stick-figure clips, black background, one line of text, \"225M views in a few days\", 13,229 views |\n| **History explainer** | A deadpan narrator; a grand event told through one small stickman's absurd problem; each claim one picture | The contrast between the serious voice and the silly picture; evergreen topics; long watch time | [@CrazyKaomei](https:\u002F\u002Fx.com\u002FCrazyKaomei\u002Fstatus\u002F2112791668332319070) \"history picture book\" style, \"deadpan absurd contrast\", 57,439 views; [@sarpstar](https:\u002F\u002Fx.com\u002Fsarpstar\u002Fstatus\u002F2119082994925211686) an 8-minute documentary made in code overnight, 540,864 views; a reply asking how to get this style with a consistent character was pointed to the stickman-video-director repo |\n| **Stick fight** | Two figures stand in for two teams, apps or models and fight in three exchanges | Rivalry, a clear winner, short; the \"made 100% in code\" claim is part of the post | [@rayanabdulcader](https:\u002F\u002Fx.com\u002Frayanabdulcader\u002Fstatus\u002F2119995155625181371) two chat-app dock icons fighting as stick figures, 100% code, 137,490 views; [@Framer_X](https:\u002F\u002Fx.com\u002FFramer_X\u002Fstatus\u002F2117995586528104755) a stickman fight used as the motion reference for other characters, 72,629 views |\n\nAlso cited for the size of the wave: [@Aygramm_](https:\u002F\u002Fx.com\u002FAygramm_\u002Fstatus\u002F2112481704724004911) \"stickman animations are the new gold rush\", 40,656 views; [@theoardley](https:\u002F\u002Fx.com\u002Ftheoardley\u002Fstatus\u002F2116684286837330374) listing \"stickman survival stories\" among free Claude video skills, 499,979 views.\n\n## 3. Script templates\n\n**Pace, measured.** ElevenLabs v3 \"Adam\" read the 60-word example in 25.1 s raw (2.4 words\u002Fs, sentence pauses of about 0.4 s). Shortening every pause to 0.2 s gave 22.2 s (2.7 words\u002Fs) without stretching speech. Plan at 2.5 words per second of voice, then tighten pauses. Leave 2 s after the last word for the ending card.\n\n### Survival choice, 20–25 s, 55–65 words\n\n| Beat | Seconds | Words | Line pattern | Picture |\n|---|---|---|---|---|\n| Hook | 0–1.2 | 2 | \"Day one.\" | DAY N title already on frame 0 over the figure mid-stride |\n| Situation | 1.2–5 | 10–12 | \"You're the new [role]. The last [role] left three rules.\" | walk in, stop, look back over the shoulder, look up, look at the camera on \"three rules\" |\n| Rule 1 | 5–7.6 | 6–8 | \"Rule one: [simple instruction].\" | rule card 1 lands on the word \"Rule\"; the figure shows it (points at the thing) |\n| Rule 2 | 7.6–12.3 | 12–14 | \"Rule two: [instruction]. If [condition], [don't do X].\" | the condition comes true on screen; the figure almost does X and stops |\n| Rule 3 | 12.3–15.2 | 7–8 | \"Rule three: never [the thing about to happen].\" | the figure walks to the danger and looks at it |\n| Break | 15.2–20.2 | 12–14 | \"It's [time]. [The rule is tested]. And [a twist that makes it personal].\" | the HUD clock flips; shock jump; crouch and tremble; the camera creeps toward the danger |\n| Choice | 20.2–22.3 | 8 | \"[Option 1], or [option 2]?\" | \"1:\" lands on option 1's first word, \"2:\" on option 2's; the figure looks between the two |\n| Hold | 22.3–24.3 | 0 | none | \"FOLLOW FOR DAY 2\" for at least 2 s |\n\nThe example's script: \"Day one. You're the new lighthouse keeper. The last keeper left three rules. Rule one: the light never stops turning. Rule two: count the ships. If there's one more than yesterday, don't wave. Rule three: never open the door after midnight. It's twelve-oh-one. Someone knocks. And the voice outside sounds like yours. Open the door, or keep the light on?\" Write numbers as words for the voice (\"twelve-oh-one\") and fix them back in the captions.\n\n### POV, 15–20 s, 35–50 words\n\n0–1 s: the text \"POV: [situation]\" on frame 0 (on screen; the voice may read it). Then three escalating beats of 3–4 s, 8–12 words each, each one a new action or a new thing in the set. End on a question or a choice (6–8 words). Write 4–5 hook variants and test them as separate posts.\n\n### Contrast, 10–15 s, 0–25 words\n\n0–1.5 s: one line of setup text (\"When you trip in public:\"). Then the same staging twice, 4–6 s each, label on top (\"FAKE FRIEND\" \u002F \"REAL FRIEND\"): the same trigger, opposite reactions, a 0.4 s hold on each reaction. 1–2 s ending: \"Tag your real friend\". Often no voice: music bed and two or three effects.\n\n### History explainer, 45–60 s, 110–150 words\n\n\"In [year], [grand event].\" in a deadpan voice, then one claim per sentence, one picture per claim, a change every 2–3 s. Every third beat cuts from the grand scale (a map, a crowd of identical figures) to one small figure's problem. End on an ironic payoff and a question. Every fact needs a source you can name; never invent dates, numbers or quotes.\n\n### Stick fight, 10–20 s, 0–10 words\n\nName tags over two figures (generic stand-ins, not real logos). Three exchanges: anticipation 0.15–0.2 s (wind up the opposite way), hit in 2–3 frames, reaction held 0.3–0.5 s, a hit sound on the contact frame. A reversal in the third exchange, then a winner pose and one line of text.\n\n## 4. The rig, and the fixes for stiff stickmen\n\nThe figure is `assets\u002Fstickman-rig.html` (a 9-second pose tour that renders as is) and the same code as `assets\u002Fexample\u002Frig.js`. API, channel table and pose values: `references\u002Frig.md`.\n\n| Complaint | Fix in the rig |\n|---|---|\n| Limbs too long, proportions drift | Fixed bones in local units: head radius 36, neck 12, torso 124, upper arm 70, forearm 66, thigh 86, shin 84. Nothing ever stretches; an unreachable foot target stops where the leg ends. |\n| Limbs detach, poses pop | One SVG path per limb, recomputed every frame from joint angles. Never swap whole images between poses. |\n| Feet slide | The walk phase comes from the distance the hips have travelled, not from time: the stance foot is planted at any speed. Legs are two-bone IK with the knee bending forward. |\n| Only the head moves; monotone | Every shot has a body action. Motion is layered: keyed pose, walk cycle, breathing (3.1 s) and weight shift (5.7 s), tremble, blinks, and a line boil (seeded jitter of 0.8 px redrawn 12 times a second). |\n| Everything moves at once, on one curve | Overlapping action: the head leads by 0.05 s, the near arm follows by 0.05–0.07 s, the far arm by 0.09–0.11 s. Eases by job: `snap` for reactions, `back` for gestures, `inOut` for looks, `walk` (short ramps, constant speed) for travel. |\n| The face says nothing | A head turn is the eyes sliding across the head (spacing narrows toward profile). Brows appear only with an emotion; an O-mouth for shock; eyes up to 1.6x. |\n| Arms vanish when they cross the body | The near arm and leg get a dark outline pass that starts partway down the bone, so the shoulder and hip joins stay clean. |\n\nActing rules:\n\n- One action per beat: anticipate (0.1–0.2 s), act fast (`snap`, 0.1–0.15 s), hold the reaction 0.4–0.8 s.\n- Shock is a sequence, not a pose: jump back 40 px with arms up and eyes 1.5x, land with the knees absorbing (`hipDrop` 34), then crouch (`hipDrop` 80, lean 26, tremble). Keep the eyes visible after the crouch: drop the near arm to the knees when the figure peeks.\n- Look-around: over the shoulder (`lookX` -1), then up, then at the camera on the line that matters.\n- Never both arms in unison, never a perfectly mirrored pose.\n- No principal picture holds still for more than 2.5 s. Breathing alone does not count, and neither does a camera move or a text entrance on its own: give the figure an action.\n- Turning around is a 0.16 s flip through edge-on; author a blink on it.\n\n## 5. Sound and captions\n\n**Voice.** On varg: `check_balance`, then `search_voices` with an intent such as \"calm, tense, low male English narrator for a dark survival short\", then `estimate_cost`, then one `generate_speech`. The example used \"Adam\" (Deep English Story Voice, varg voice id `preset_610bdb815cd5`) on `eleven_v3`: 354 characters, 60 words, **$0.04 (4 credits)**, one take. Download the file, then shorten the pauses: `bun tighten-pauses.mjs voice.mp3 assets\u002Faudio\u002Fvoice.wav` (pauses over 0.25 s become 0.2 s; speech is never time-stretched).\n\n**Word timings, free.** `bunx hyperframes transcribe assets\u002Faudio\u002Fvoice.wav --model small.en --language en` runs whisper.cpp locally (2 s for 22 s of voice) and writes `assets\u002Faudio\u002Ftranscript.json`. Read it: the example's ASR wrote \"twelve-oh-one\" as \"1201\". Do not pay for transcription.\n\n**Captions.** `bun captions.mjs assets\u002Faudio\u002Ftranscript.json \u003Cvoice start> \u003Cwords already on a title> \u003Cending card start>` writes the groups into `index.html`: at most 3 words, one line of at most 18 characters (font shrinks from 74 px for long lines), a break at punctuation or a pause of 0.15 s or more, the active word in yellow. Place them under the rules and above the figure's head, inside the 168–1330 px band of a 1080x1920 frame. Hide them while the ending card shows the same words.\n\n**Ambience and effects.** One bed plus 2–4 effects, each on a visible cause. `bun sfx.mjs assets\u002Faudio 25` synthesizes everything with ffmpeg, so nothing needs a licence: a sea, wind and lamp-motor bed normalised to -30 LUFS; a low thud for the title stamp; a door knock in three takes at different pitch; an electrical buzz gated by the same on\u002Foff table as the lamp flicker in the picture; a whoosh that peaks 0.8 s after it starts. If you use a library sound instead, keep its URL and licence (CC0 or the library's own terms) next to the file. Levels in the example: voice 1.0, bed 1.0, knocks 0.65–0.8, thud 0.45–0.55, buzz 0.3, whoosh 0.4; the mix measured -13.5 LUFS integrated, -1.0 dBTP true peak, no clipping (measured with `hyperframes audio`, not listened to).\n\n## 6. Build it in HyperFrames\n\n1. `bunx hyperframes init my-reel --resolution portrait --non-interactive --skip-transcribe` (or `npx`).\n2. Copy `assets\u002Fexample\u002F` into it (`index.html`, `rig.js`, `captions.mjs`, `sfx.mjs`, `tighten-pauses.mjs`), or start from `assets\u002Fstickman-rig.html` as `index.html` for a bare stage. The example has no media: make `assets\u002Faudio\u002F` with steps 3 and 4.\n3. Voice, pauses, transcript, captions (section 5).\n4. `bun sfx.mjs assets\u002Faudio \u003Cfilm seconds + 1>`; place each effect so its peak lands one frame after its picture.\n5. Write the film in `index.html`:\n   - One clock. A proxy object with a setter, tweened from 0 to the duration on the paused GSAP timeline, redraws the set and the rig for that exact time. Nothing reads a clock, `Math.random` or the previous frame.\n   - The set is SVG inside a camera group (`translate · scale · translate` from three keyed channels `cx`, `cy`, `cs`). Draw it in code: walls, a window, a door, a lamp. A world wider than the frame lets the camera pan between places.\n   - The figure: `Stickman.create(group, { scale, ground, blinks })`, a `Stickman.track(...)` of pose keys written as `P.move(start, duration, { channel: value }, ease)` on the voice's word times, and `Stickman.draw(fig, P, t)` inside the clock.\n   - HUD, rules, captions and the ending card are HTML clips animated on the same timeline. Rules land on the word \"Rule\"; the clock flips on its word.\n6. `bunx hyperframes lint`, then `bunx hyperframes check --json --no-cache`. Use `bunx hyperframes`, not `bunx --bun hyperframes`: under the Bun runtime `check` printed nothing on repeat runs.\n7. Look: `bunx hyperframes snapshot --at \u003C12 beat times> --no-end`, then `--range \u003Cwalk start>,\u003Cwalk end> --frames 8` for the walk, and zoomed crops of the figure at the reaction poses.\n8. `bunx hyperframes render --quality delivery --output out.mp4`, then `ffprobe` (duration equals the root `data-duration`), `bunx hyperframes audio out.mp4 --json`, and a contact sheet decoded from the MP4.\n\nTwo traps the example hit:\n\n- **Caption hard-kill.** Under a clip host, GSAP records the inherited `visibility: hidden` as the start value, so `tl.set(group, { visibility: \"hidden\" }, end)` leaves every group hidden after a backward seek. Kill caption groups with `opacity: 0` only.\n- **Two-line captions** collide with things drawn in the set (the example's ship numbers). Keep one line per group.\n\nThe example is one `index.html` on purpose (one clock drives the rig and the set), so `lint` warns that the scenes are not sub-compositions; that warning is expected.\n\n## 7. Checks before delivery\n\n- [ ] Frame 0 is the hook: the DAY title or the POV line plus the figure mid-action, never black.\n- [ ] Limbs attached in every sampled frame, bones the same length, feet on the ground except in a jump, no foot sliding during the walk (8-frame strip).\n- [ ] Walk, breathing idle, a head turn, one reaction (shock or crouch) and blinks all appear; nothing principal holds for more than 2.5 s.\n- [ ] Rules appear one at a time on their words; the clock or DAY counter changes on its word.\n- [ ] Captions one line, word-timed, inside 168–1330 px, nothing readable under the right-hand action rail.\n- [ ] The ending: \"1:\" and \"2:\" on screen with the spoken options, \"FOLLOW FOR DAY 2\" for at least 2 s.\n- [ ] Sound present, effects on their pictures, about -14 LUFS, true peak at or under -1 dBTP; say it was measured, not heard.\n- [ ] `check` has no errors; duration and size match (1080x1920, 30 fps).\n\n## 8. Costs\n\n| Item | Measured |\n|---|---|\n| Voice, 60 words, ElevenLabs v3 on varg | $0.04 (4 credits), one take |\n| Word timings (local whisper.cpp) | free, 2 s |\n| Sound effects and ambience (ffmpeg) | free |\n| Render, 24.3 s at 1080x1920, 729 frames | free, 17.3 s on an Apple M1 Pro (hardware GPU, screenshot capture) |\n| Total for the example | $0.04 (4 credits) |\n\n## 9. Other routes\n\n- **kaomei\u002Fstickman-video-director** ([GitHub](https:\u002F\u002Fgithub.com\u002Fkaomei\u002Fstickman-video-director), MIT, by [@CrazyKaomei](https:\u002F\u002Fx.com\u002FCrazyKaomei), about 5,900 stars in November 2026). Director mode writes a treatment, then one prompt per roughly 10-second clip for Google Flow (Gemini Omni Flash), Veo, Kling, Runway or Luma; you generate and edit the clips yourself. Autopilot renders a narrated, captioned MP4 locally (Node 20+, FFmpeg) after a 20-second sample is approved; the author recommends Codex. Eleven visual styles. Install by pasting the repo URL into your agent with \"Install this Skill for me\"; the installed skill is called `directing-stickman-videos`. Use it when the person wants generated clips or one of its styles.\n- **Generated 2.5D look on varg.** A character sheet and set stills with `gpt_image_2_6` (estimate on 2026-11-13: up to $0.06 (6 credits) per 9:16 image), approved first, then animate with `kling_v4` (estimate on the same day: up to $0.79 (79 credits) for a 5 s 9:16 clip, priced as text-to-video; price the image-to-video call itself before the batch; `kling_v4_flash` for drafts). Run `estimate_cost` before each batch. The honest caveat: video models drift on stick figures. Limbs multiply or thicken, heads detach, hair and clothes appear, and two shots rarely match. Keep shots to 5 s, reuse the same reference, judge every take, and keep anything that must stay jointed (a walk, a fight, a pose that carries the joke) in code. A hybrid works: generated background stills under the code figure.\n\n## 10. What not to do\n\n- Do not copy a named channel's characters, names, catchphrases, signature outfit or episode premises. Make your own figure and your own premise; \"inspired by a format\" is fine, a look-alike is not.\n- Do not use real people's names, faces or cloned voices; use generic stand-ins in fights and contrasts, not real logos.\n- Label AI content where the platform asks for it (TikTok's AI-generated label, YouTube's altered or synthetic content disclosure for realistic material), and write \"AI voice\" in the caption when the narrator is synthetic.\n- Do not present invented stories as true, and do not invent facts in explainers. Keep survival stories PG: tension, not gore.\n- Do not promise views or income: the numbers in the posts above are the posters' claims.\n- Do not use `Math.random`, `Date.now`, timers or the previous frame as state; do not swap images for poses; do not stretch bones; do not put text below 1330 px on 9:16.\n\n## Sources\n\n- X research, collected 2026-11-13: the posts linked in section 2, the stickman-video-director launch and updates by [@CrazyKaomei](https:\u002F\u002Fx.com\u002FCrazyKaomei\u002Fstatus\u002F2084217266703393186), and user questions under them ([limbs and monotone motion](https:\u002F\u002Fx.com\u002FGazunH26262\u002Fstatus\u002F2121123319143633304), [two-bone IK arms and lip sync by loudness](https:\u002F\u002Fx.com\u002Ftebet007\u002Fstatus\u002F2116324211002401064)).\n- kaomei\u002Fstickman-video-director: `SKILL.md` (Director pacing of about 20–25 voice words per 10 s clip, a visual change every 2–3 s) and `references\u002Fautopilot.md` (no principal-picture inactivity over 2.5 s; camera moves or text entrances alone do not count as animation).\n- HyperFrames CLI 0.9.41 documentation (`hyperframes`, `hyperframes-core`, `hyperframes-cli` skills).\n- Measured on the example: voice job on varg on `eleven_v3` for $0.04 (4 credits), whisper.cpp `small.en`, ffmpeg loudness, HyperFrames render log.\n",{"name":5,"license":15,"metadata":24,"description":7,"allowed-tools":36,"compatibility":37},{"author":25,"version":26,"openclaw":27,"varg.models":32,"varg.outputs":33,"varg.cost.typical":34,"varg.runtime.typical":35},"vargHQ","1.0.0",{"homepage":28,"requires":29},"https:\u002F\u002Fvarg.ai\u002Fhow-to",{"anyBins":30},[31],"ffmpeg","eleven_v3 (voice, optional)","mp4 1080x1920 30 fps, contact sheet","$0.04 (4 credits) for a 60-word ElevenLabs v3 voiceover; picture, sound and render free","17 s to render 24 s of 1080x1920 at 30 fps on an Apple M1 Pro","Bash(bunx:*) Bash(npx:*) Bash(bun:*) Bash(ffmpeg:*) Bash(ffprobe:*) Bash(curl:*) Read Write Edit","HyperFrames 0.9 (bunx hyperframes or npx hyperframes; brings Chrome, needs Node 22 and ffmpeg). The voice is optional: the varg MCP (https:\u002F\u002Fmcp.varg.ai\u002Fmcp) or a VARG_API_KEY, or any recorded file. Word timings come from local whisper.cpp through hyperframes transcribe. No key is needed for the picture, the sound effects or the render.","main","70b6a3a3a7c774671e45af646306e1448baf0511","plugins\u002FvargHQ\u002Fskills\u002Fstickman-video",491,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins","https:\u002F\u002Fhol.org\u002Fplugins\u002Fbest-codex-plugins","https:\u002F\u002Fgithub.com\u002Fhashgraph-online","https:\u002F\u002Fhol.org","Open-source standards and developer tools for interoperable AI agents: discovery, identity, communication, payments, privacy and security.","2026-11-14 14:06:13",{"source":8,"skillName":5,"commands":49,"prompt":59,"zipAvailable":60},[50,53,56],{"tool":51,"command":52},"npx","npx skills add hashgraph-online\u002Fawesome-codex-plugins --skill stickman-video",{"tool":54,"command":55},"bunx","bunx skills add hashgraph-online\u002Fawesome-codex-plugins --skill stickman-video",{"tool":57,"command":58},"pnpm","pnpm dlx skills add hashgraph-online\u002Fawesome-codex-plugins --skill stickman-video","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FvargHQ\u002Fskills\u002Fstickman-video\u002FSKILL.md",true,[62,68,74,78,82,86,90,96,100],{"path":63,"resourceType":64,"resourceTypeDesc":65,"sizeBytes":66,"sourceHtmlUrl":67},"assets\u002Fexample\u002Fcaptions.mjs","SCRIPT","脚本",3326,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FvargHQ\u002Fskills\u002Fstickman-video\u002Fassets\u002Fexample\u002Fcaptions.mjs",{"path":69,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":72,"sourceHtmlUrl":73},"assets\u002Fexample\u002Findex.html","ASSET","资产文件",44528,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FvargHQ\u002Fskills\u002Fstickman-video\u002Fassets\u002Fexample\u002Findex.html",{"path":75,"resourceType":64,"resourceTypeDesc":65,"sizeBytes":76,"sourceHtmlUrl":77},"assets\u002Fexample\u002Frig.js",16485,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FvargHQ\u002Fskills\u002Fstickman-video\u002Fassets\u002Fexample\u002Frig.js",{"path":79,"resourceType":64,"resourceTypeDesc":65,"sizeBytes":80,"sourceHtmlUrl":81},"assets\u002Fexample\u002Fsfx.mjs",4089,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FvargHQ\u002Fskills\u002Fstickman-video\u002Fassets\u002Fexample\u002Fsfx.mjs",{"path":83,"resourceType":64,"resourceTypeDesc":65,"sizeBytes":84,"sourceHtmlUrl":85},"assets\u002Fexample\u002Ftighten-pauses.mjs",1713,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FvargHQ\u002Fskills\u002Fstickman-video\u002Fassets\u002Fexample\u002Ftighten-pauses.mjs",{"path":87,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":88,"sourceHtmlUrl":89},"assets\u002Fstickman-rig.html",21751,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FvargHQ\u002Fskills\u002Fstickman-video\u002Fassets\u002Fstickman-rig.html",{"path":91,"resourceType":92,"resourceTypeDesc":93,"sizeBytes":94,"sourceHtmlUrl":95},"evals\u002Ftrigger_eval.json","REFERENCE","参考文档",981,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FvargHQ\u002Fskills\u002Fstickman-video\u002Fevals\u002Ftrigger_eval.json",{"path":97,"resourceType":92,"resourceTypeDesc":93,"sizeBytes":98,"sourceHtmlUrl":99},"README.md",5490,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FvargHQ\u002Fskills\u002Fstickman-video\u002FREADME.md",{"path":101,"resourceType":92,"resourceTypeDesc":93,"sizeBytes":102,"sourceHtmlUrl":103},"references\u002Frig.md",8493,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FvargHQ\u002Fskills\u002Fstickman-video\u002Freferences\u002Frig.md",[105,113,121,129,137,145],{"skillNo":106,"name":107,"nameZh":6,"description":108,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":109,"sourceHtmlUrl":110,"categories":111,"keywords":112,"publishedAt":19},"01M7DV332YQMGD8WTRJ9DZQXTB","worktable-review-with-annotations","Create, inspect, reply to, update, or resolve situated Worktable annotations. Use when feedback belongs to a Doc section, block, text range, or HTML Doc, or when the user asks to address existing review feedback and coordinate a requested artifact edit.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-review-with-annotations\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-review-with-annotations\u002FSKILL.md",[],[],{"skillNo":114,"name":115,"nameZh":6,"description":116,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":117,"sourceHtmlUrl":118,"categories":119,"keywords":120,"publishedAt":19},"01M7DV2YGHCZVBEB1AHYB6CGHE","worktable-find-and-synthesize-context","Find, assess, and synthesize context from Worktable Docs and Records. Use when the user asks what a workspace contains, wants workspace-backed research, needs current facts reconciled across artifacts, or requests a cited synthesis without changing workspace state.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-find-and-synthesize-context\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-find-and-synthesize-context\u002FSKILL.md",[],[],{"skillNo":122,"name":123,"nameZh":6,"description":124,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":125,"sourceHtmlUrl":126,"categories":127,"keywords":128,"publishedAt":19},"01M7DV2TQN1H11ME2SAF9MXN7V","worktable-create-or-update-docs","Create, edit, rename, or maintain narrative Worktable Docs. Use for plans, decisions, briefs, notes, research syntheses, and other durable prose when the user requests a new artifact or a safe update to an existing one.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-update-docs\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-update-docs\u002FSKILL.md",[],[],{"skillNo":130,"name":131,"nameZh":6,"description":132,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":133,"sourceHtmlUrl":134,"categories":135,"keywords":136,"publishedAt":19},"01M7DV2NE452NEA8TXATKSNAJH","worktable-create-or-manage-records","Organize repeated structured information as durable Worktable Records. Use for research datasets, inventories, directories, pipelines, trackers, and other collections whose items need identity, fields, filtering, links, validation, or individual updates.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-records\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-records\u002FSKILL.md",[],[],{"skillNo":138,"name":139,"nameZh":6,"description":140,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":141,"sourceHtmlUrl":142,"categories":143,"keywords":144,"publishedAt":19},"01M7DV2HENRBR2KSCVM064WH0Y","worktable-create-or-manage-interactive-html","Create or improve durable visual and interactive artifacts in Worktable. Use for dashboards, trackers, calculators, mini apps, slide presentations, and other requests that benefit from a polished HTML Doc.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-interactive-html\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-interactive-html\u002FSKILL.md",[],[],{"skillNo":146,"name":147,"nameZh":6,"description":148,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":149,"sourceHtmlUrl":150,"categories":151,"keywords":152,"publishedAt":19},"01M7DV2CADR5R7RQFFYPNAGR9Y","worktable-collaborate-threads","Read, answer, and hand off messages through durable Worktable threads with users or other authenticated participants. Use when the user asks to check addressed messages, reply to a participant, continue a thread, request another agent's help, wait briefly for a response, or watch for comments and messages sent to the agent.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-collaborate-threads\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-collaborate-threads\u002FSKILL.md",[],[]]