[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6MNW601FQXTKG2V47QDE968":3,"skill-same:01M6MNW601FQXTKG2V47QDE968":141},{"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":29,"publishedAt":50,"linkOnly":51,"markdownContent":52,"markdownBody":53,"frontMatter":54,"refName":64,"commitSha":65,"skillDirectory":66,"forksCount":67,"repositoryHtmlUrl":68,"repositoryHomepageUrl":69,"ownerHtmlUrl":70,"ownerBlogUrl":71,"ownerDescription":72,"updatedAt":73,"install":74,"resources":87},"01M6MNW601FQXTKG2V47QDE968","video-moodboard",null,"Build a moodboard that AI image and video models actually follow, in the order that matters most, and prove it on stills before any video is paid for. Ranked from a 48-still test, 6,086 X posts and 14 official prompt guides: references, light, subject lock, framing, palette, motion, texture, type, sound. Every line is a number or a named thing (hex, Kelvin, lens mm, % of frame, film stock, font, seconds), never \"cinematic\". Writes moodboard.md and a visual board.html, checks test stills line by line (palette by ΔE), and links 450+ sources: reference libraries, palette, light, type and motion tools, vendor guides, benchmarks, creators' posts. Use for \"make a moodboard\", \"mood board for my video\", \"style bible\", \"look and feel\", \"art direction\", \"visual brief\", \"make it not look like AI\", or before prompting Seedance, Kling, Veo, Nano Banana or Midjourney. Not for finding references from scratch (find-references) or per-shot prompts after the board is approved (varg-video-prompting).","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\u002Fvideo-moodboard\u002FSKILL.md",[18,23,26],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000008","测试与质量","SCENARIO","使用场景",{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000016","图像与多媒体",{"categoryNo":27,"categoryName":28,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",[30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49],"video moodboard","Video","python3","links","mm","prompting","pillow","edit","write","read","banana","palette","lock","guides","image","number","free","hex","direction","posts","2026-11-10 10:12:30",false,"---\nname: video-moodboard\ndescription: >-\n  Build a moodboard that AI image and video models actually follow, in the order that matters most, and prove it on\n  stills before any video is paid for. Ranked from a 48-still test, 6,086 X posts and 14 official prompt guides:\n  references, light, subject lock, framing, palette, motion, texture, type, sound. Every line is a number or a named\n  thing (hex, Kelvin, lens mm, % of frame, film stock, font, seconds), never \"cinematic\". Writes moodboard.md and a\n  visual board.html, checks test stills line by line (palette by ΔE), and links 450+ sources: reference libraries,\n  palette, light, type and motion tools, vendor guides, benchmarks, creators' posts. Use for \"make a moodboard\",\n  \"mood board for my video\", \"style bible\", \"look and feel\", \"art direction\", \"visual brief\", \"make it not look like\n  AI\", or before prompting Seedance, Kling, Veo, Nano Banana or Midjourney. Not for finding references from scratch\n  (find-references) or per-shot prompts after the board is approved (varg-video-prompting).\nlicense: MIT\nmetadata:\n  author: vargHQ\n  version: \"1.0.1\"\n  openclaw:\n    requires:\n      anyBins:\n        - python3\n    homepage: https:\u002F\u002Fgithub.com\u002FvargHQ\u002Fskills\u002Ftree\u002Fmain\u002Fvideo-moodboard\ncompatibility: >-\n  Works in any agent with a shell and web access. scripts\u002Fpalette.py needs Python 3 and Pillow. Test stills cost\n  about $0.05 each through varg (Nano Banana 2.1 or Seedream 5 Pro); everything else is free. Reference MCPs\n  (FrameThrower, Refs, Are.na) are optional and used through find-references.\nallowed-tools: Bash(python3:*) Bash(curl:*) Read Write Edit\n---\n\n# Video moodboard\n\n> Step 2 of 10 in [How to make a video with an AI agent in ten steps](https:\u002F\u002Fvarg.ai\u002Fhow-to\u002Fmake-a-video-in-ten-steps). The full guide, with every test and source: https:\u002F\u002Fvarg.ai\u002Fhow-to\u002Fmake-a-moodboard-for-an-ai-video (as Markdown: add `.md`).\n\nA moodboard for an AI video is not a mood. It is a short list of lines a model can obey and a person can check:\nwhere the light comes from, which five colours, which lens, which film stock, which font, which camera move. Write\nit that way and the model follows; write \"cinematic, moody, premium\" and it falls back to its default look.\n\nWhat the data says (full write-up: https:\u002F\u002Fvarg.ai\u002Fhow-to\u002Fmake-a-moodboard-for-an-ai-video):\n\n- **A board works.** In a blind test of 48 stills on Nano Banana 2.1 and Seedream 5 Pro, the full board made frames\n  1.0 point more film-like (1–10) than no board, and every line lifted its own match by 31–73 points.\n- **Light is the realism lever.** It was the only line that made frames look more like real film when written\n  (+0.50, p 0.04).\n- **Invented palettes cost realism.** The hex line was obeyed best (89%), but frames looked less like film with an\n  invented palette (−0.67, p 0.03). Take hex from a real reference frame.\n- **Adjectives cost saves.** On X, posts built on \"cinematic\", \"8k\", \"stunning\" got 31% fewer saves; posts with hex\n  codes got 1.58× and posts naming fonts 2.19× (n = 4,722, controlled for views, age, media, length).\n\n## The ranking\n\n| # | Line | Why it ranks here | Write |\n|---|---|---|---|\n| 1 | **References** | Words land camera moves about half the time (VBench mean 49.58%) and exact text in at best 0.67 of layouts; a reference carries both. All 14 guides cover style or image references; Kling 4.0, MiniMax H3, Seedance 2.5 put reference roles first. Posts mentioning references: ×1.25 saves, the highest. | 3–5 refs, each with ONE job |\n| 2 | **Light** | Only line that raised film-likeness. Veo: cinematography is \"the most powerful tool for conveying tone and emotion\". Vision models read light right only 41.6% of the time (ShotBench), so write it, don't infer it. | one source, direction, hardness, Kelvin, motivation |\n| 3 | **Subject lock** | All 14 guides cover the subject; five put it first. \"if your character sheet is bad, you'll just waste tokens\" (2,624 saves). | identity block + sheet (18% grey or in the board's light); full cast: character-passport |\n| 4 | **Framing** | Unprompted models default to a medium shot; a straight-down aerial was met only 58–71%. Vision models read lens size worst (37.7%). | shot size, height, angle, mm, placement % |\n| 5 | **Palette** | Obeyed best; colour is the easiest attribute for video models (T2V-CompBench). Invented hex hurt realism. | 3–5 hex from a reference, roles, grade |\n| 6 | **Motion** | Matters most once it moves, followed least (57% even when written). | one move, one action, duration, ref clip |\n| 7 | **Texture** | Smallest lift: models add a film look half the time unasked. Matters most for skin and UGC. | one capture medium and its flaws |\n| 8 | **Type** | Never appears unless written; exact text is weak (best T2VTextBench 0.37). | font, weight, size, hex, position; set in code |\n| 9 | **Sound** | 8 of 14 guides; \"You've made it look right. We'll make it sound right.\" (4,303 saves). | voice, music, room tone |\n\n## Rules\n\n1. **Every line must be checkable against a frame:** hex, Kelvin, lens mm, % of frame, film stock, font, px,\n   seconds. If a line has no number or named thing, rewrite it.\n2. **References first, one job each.** Say what each reference lends (light, palette, framing, texture, type or\n   motion) and what it must not copy. Borrow the look, never actors, logos or a living filmmaker's name.\n3. **Respect the sites.** ShotDeck, FrameSet, Eyecannndy, Shot Cafe, Film-Grab and Pinterest are human-only or\n   forbid bots: hand the person search links, never scrape. Feed a model only CC0, licensed or your own images\n   (Unsplash, Pexels, The Met, Poly Haven, approved stills). Section 2 of `references\u002Flinks.md` lists the terms.\n4. **Take the palette from a reference frame** (`scripts\u002Fpalette.py extract`), never invent hex.\n5. **One light source family for the whole film**, written the same in every shot.\n6. **Type and captions are set in code** (HyperFrames, Remotion), not drawn by the video model.\n7. **Prove it on stills, with numbers, judged by a second agent.** Fix the one line that failed, not the board.\n8. **Use the links.** `references\u002Flinks.md` has every database, tool, vendor guide, benchmark and creator post\n   behind this skill (450+ URLs). Each step below names the sections to open. Open them; don't work from memory.\n\n## Files you produce\n\n```\nbrief.md        six lines: what, who, where (platform, aspect), length, brand, taste\nrefs\u002F           the 3-5 kept references (or links.md entries for link-only sites)\nmoodboard.md    the board, in ranked order (template: references\u002Fmoodboard-template.md)\nboard.html      the board as one page to look at (copy assets\u002Fboard.html, fill its JSON)\nstills\u002F         3 test stills of the hero shot\nchecks.md       one row per line per still: measure, target, result\n```\n\n## Step by step\n\n### 0. Brief\n\nSix lines in `brief.md`. If the person gave references, they go first. Ask once for a missing line, then go on\nwith a stated assumption.\n\n### 1. References (rank 1)\n\nRun the **find-references** skill if it is installed (https:\u002F\u002Fgithub.com\u002FvargHQ\u002Fskills\u002Ftree\u002Fmain\u002Ffind-references);\notherwise follow its order: varg how to search → X last 7 days → Refs MCP → FrameThrower MCP → film-still\nlibraries as links for the person → Are.na → YouTube.\nOpen: `references\u002Flinks.md` §2 References and Style codes, §3, §6 \"Moodboards overall\".\nKeep 3–5 references, each tagged with one job. **STOP:** show the reference grid and wait for a pick.\n\n### 2. Numbers out of the references\n\n- Palette: `python3 scripts\u002Fpalette.py extract refs\u002F02.jpg --k 6` → hex with % share.\n- Light, lens, shot size per frame: describe them, and mark them \"estimated\" (vision models get lighting right\n  41.6% and lens size 37.7% of the time in ShotBench). Ask the person to confirm the light if it matters.\n- Motion: time the reference clip's shots (average shot length) and name each camera move.\n\n### 3. Write moodboard.md\n\nCopy `references\u002Fmoodboard-template.md`. Fill it in ranked order. For each line, `references\u002Fdimensions.md` has the\nrule, wording that works, wording that fails, the model limit and a board line to copy; `references\u002Fdimensions-evidence.md`\nhas every tip from the 1,540 posts read, with links. Vendor-specific wording is in `references\u002Flinks.md` §4.\n\n### 4. Make it visible: board.html\n\nCopy `assets\u002Fboard.html` next to `moodboard.md` and fill the JSON block at the top (same fields as the template).\nIt draws: the reference grid with each one's job and rights badge, the subject sheet, a top-down light diagram from\nthe key angle, palette swatches with roles and shares, a framing guide (thirds grid, subject box at its position and\nsize), the texture chip, a motion beat timeline, a live type specimen in the chosen Google Font, sound, the Never\nlist, and the test stills with their check table. Example: `examples\u002Flast-bus\u002F`.\n\n### 5. Test on stills\n\nGenerate 3 stills of the hero shot from `moodboard.md` alone, on two image models if you can (with varg:\n`nano_banana_2_1` and `seedream_5_pro`, about $0.05 each; quote the price first). Use the board lines as the prompt,\nin this order: subject and action, light, palette, framing, texture, motion, type.\n\n### 6. Check every line\n\n| Line | Check | Pass |\n|---|---|---|\n| Palette | `python3 scripts\u002Fpalette.py check stills\u002F*.png --hex 0F3B3F,E07A2E,C1272D --ref refs\u002F02.jpg` | within the reference frame's ΔE + 5 (or ≤ 15 without `--ref`); closer than a still made without the palette line |\n| Light | key side and hardness match; shadows fall the right way; one source family | yes\u002Fno |\n| Framing | shot size, camera height, subject position and % of frame | within one size step |\n| Texture | grain \u002F halation \u002F flaws visible at 100% | yes\u002Fno |\n| Motion | frozen-motion cue present (stills) or the move happened (video) | yes\u002Fno |\n| Type | not in the still; set in code later | — |\n\nUse a second agent with fresh context as the critic: give it the board and the stills, not your reasoning, and\nfollow `references\u002Fjudge.md` (blind ids, line-by-line 0\u002F1\u002F2 with evidence, code measures first, pairs in both\norders, never \"rate the quality\": without criteria our judges preferred the frames that ignored the board). When a\nline fails, rewrite that line or attach a reference image for it. Typical fixes: unusual angles need a 3D blockout\n(threejs-animatic) or a reference frame; a palette that looks graded needs hex from a real frame and a softer grade.\n\n### 7. STOP for approval\n\nShow `board.html` with the stills and the check table. No video generation before the person approves.\n\n### 8. Hand over to video prompts\n\nWrite prompts in this order: reference roles first (what each attached image or clip is for), then subject and\naction, then light, palette and texture, then camera. One camera move and one subject action per shot. For\nimage-to-video, write only the motion line; the start frame already carries the look. Per-model wording:\n`references\u002Flinks.md` §4; per-shot prompting: varg-video-prompting.\n\n## Never\n\n\"cinematic\", \"8k\", \"stunning\", \"premium\", \"moody\" without numbers · evenly lit scenes · perfect symmetry ·\ninvented hex palettes · Inter, Roboto, Arial, system-ui · purple gradients · centred text fading in · text drawn\nby the video model · more than one camera move per shot · scraping sites that forbid it · feeding a model frames\nyou have no rights to.\n\n## Files in this skill\n\n- `references\u002Flinks.md`: every link (databases, X tools, 14 vendor guides, research, creator posts, varg skills)\n- `references\u002Fdimensions.md`: how to write each line, with sources\n- `references\u002Fdimensions-evidence.md`: every tip, failure and vocabulary list per dimension, linked to the posts\n- `references\u002Fevidence.md`: the test, the X statistics, the guide matrix, the benchmark numbers\n- `references\u002Fmoodboard-template.md`: the blank board\n- `references\u002Fgoal-prompt.md`: the whole skill as one copy-paste prompt\n- `references\u002Fjudge.md`: how to rank frames with an unbiased LLM judge, with our bias tests and the judge prompt\n- `assets\u002Fboard.html`: the visual board template\n- `scripts\u002Fpalette.py`: extract a palette from a reference, check a still against hex (ΔE)\n- `examples\u002Flast-bus\u002F`: a filled board with the 3 test stills\n","# Video moodboard\n\n> Step 2 of 10 in [How to make a video with an AI agent in ten steps](https:\u002F\u002Fvarg.ai\u002Fhow-to\u002Fmake-a-video-in-ten-steps). The full guide, with every test and source: https:\u002F\u002Fvarg.ai\u002Fhow-to\u002Fmake-a-moodboard-for-an-ai-video (as Markdown: add `.md`).\n\nA moodboard for an AI video is not a mood. It is a short list of lines a model can obey and a person can check:\nwhere the light comes from, which five colours, which lens, which film stock, which font, which camera move. Write\nit that way and the model follows; write \"cinematic, moody, premium\" and it falls back to its default look.\n\nWhat the data says (full write-up: https:\u002F\u002Fvarg.ai\u002Fhow-to\u002Fmake-a-moodboard-for-an-ai-video):\n\n- **A board works.** In a blind test of 48 stills on Nano Banana 2.1 and Seedream 5 Pro, the full board made frames\n  1.0 point more film-like (1–10) than no board, and every line lifted its own match by 31–73 points.\n- **Light is the realism lever.** It was the only line that made frames look more like real film when written\n  (+0.50, p 0.04).\n- **Invented palettes cost realism.** The hex line was obeyed best (89%), but frames looked less like film with an\n  invented palette (−0.67, p 0.03). Take hex from a real reference frame.\n- **Adjectives cost saves.** On X, posts built on \"cinematic\", \"8k\", \"stunning\" got 31% fewer saves; posts with hex\n  codes got 1.58× and posts naming fonts 2.19× (n = 4,722, controlled for views, age, media, length).\n\n## The ranking\n\n| # | Line | Why it ranks here | Write |\n|---|---|---|---|\n| 1 | **References** | Words land camera moves about half the time (VBench mean 49.58%) and exact text in at best 0.67 of layouts; a reference carries both. All 14 guides cover style or image references; Kling 4.0, MiniMax H3, Seedance 2.5 put reference roles first. Posts mentioning references: ×1.25 saves, the highest. | 3–5 refs, each with ONE job |\n| 2 | **Light** | Only line that raised film-likeness. Veo: cinematography is \"the most powerful tool for conveying tone and emotion\". Vision models read light right only 41.6% of the time (ShotBench), so write it, don't infer it. | one source, direction, hardness, Kelvin, motivation |\n| 3 | **Subject lock** | All 14 guides cover the subject; five put it first. \"if your character sheet is bad, you'll just waste tokens\" (2,624 saves). | identity block + sheet (18% grey or in the board's light); full cast: character-passport |\n| 4 | **Framing** | Unprompted models default to a medium shot; a straight-down aerial was met only 58–71%. Vision models read lens size worst (37.7%). | shot size, height, angle, mm, placement % |\n| 5 | **Palette** | Obeyed best; colour is the easiest attribute for video models (T2V-CompBench). Invented hex hurt realism. | 3–5 hex from a reference, roles, grade |\n| 6 | **Motion** | Matters most once it moves, followed least (57% even when written). | one move, one action, duration, ref clip |\n| 7 | **Texture** | Smallest lift: models add a film look half the time unasked. Matters most for skin and UGC. | one capture medium and its flaws |\n| 8 | **Type** | Never appears unless written; exact text is weak (best T2VTextBench 0.37). | font, weight, size, hex, position; set in code |\n| 9 | **Sound** | 8 of 14 guides; \"You've made it look right. We'll make it sound right.\" (4,303 saves). | voice, music, room tone |\n\n## Rules\n\n1. **Every line must be checkable against a frame:** hex, Kelvin, lens mm, % of frame, film stock, font, px,\n   seconds. If a line has no number or named thing, rewrite it.\n2. **References first, one job each.** Say what each reference lends (light, palette, framing, texture, type or\n   motion) and what it must not copy. Borrow the look, never actors, logos or a living filmmaker's name.\n3. **Respect the sites.** ShotDeck, FrameSet, Eyecannndy, Shot Cafe, Film-Grab and Pinterest are human-only or\n   forbid bots: hand the person search links, never scrape. Feed a model only CC0, licensed or your own images\n   (Unsplash, Pexels, The Met, Poly Haven, approved stills). Section 2 of `references\u002Flinks.md` lists the terms.\n4. **Take the palette from a reference frame** (`scripts\u002Fpalette.py extract`), never invent hex.\n5. **One light source family for the whole film**, written the same in every shot.\n6. **Type and captions are set in code** (HyperFrames, Remotion), not drawn by the video model.\n7. **Prove it on stills, with numbers, judged by a second agent.** Fix the one line that failed, not the board.\n8. **Use the links.** `references\u002Flinks.md` has every database, tool, vendor guide, benchmark and creator post\n   behind this skill (450+ URLs). Each step below names the sections to open. Open them; don't work from memory.\n\n## Files you produce\n\n```\nbrief.md        six lines: what, who, where (platform, aspect), length, brand, taste\nrefs\u002F           the 3-5 kept references (or links.md entries for link-only sites)\nmoodboard.md    the board, in ranked order (template: references\u002Fmoodboard-template.md)\nboard.html      the board as one page to look at (copy assets\u002Fboard.html, fill its JSON)\nstills\u002F         3 test stills of the hero shot\nchecks.md       one row per line per still: measure, target, result\n```\n\n## Step by step\n\n### 0. Brief\n\nSix lines in `brief.md`. If the person gave references, they go first. Ask once for a missing line, then go on\nwith a stated assumption.\n\n### 1. References (rank 1)\n\nRun the **find-references** skill if it is installed (https:\u002F\u002Fgithub.com\u002FvargHQ\u002Fskills\u002Ftree\u002Fmain\u002Ffind-references);\notherwise follow its order: varg how to search → X last 7 days → Refs MCP → FrameThrower MCP → film-still\nlibraries as links for the person → Are.na → YouTube.\nOpen: `references\u002Flinks.md` §2 References and Style codes, §3, §6 \"Moodboards overall\".\nKeep 3–5 references, each tagged with one job. **STOP:** show the reference grid and wait for a pick.\n\n### 2. Numbers out of the references\n\n- Palette: `python3 scripts\u002Fpalette.py extract refs\u002F02.jpg --k 6` → hex with % share.\n- Light, lens, shot size per frame: describe them, and mark them \"estimated\" (vision models get lighting right\n  41.6% and lens size 37.7% of the time in ShotBench). Ask the person to confirm the light if it matters.\n- Motion: time the reference clip's shots (average shot length) and name each camera move.\n\n### 3. Write moodboard.md\n\nCopy `references\u002Fmoodboard-template.md`. Fill it in ranked order. For each line, `references\u002Fdimensions.md` has the\nrule, wording that works, wording that fails, the model limit and a board line to copy; `references\u002Fdimensions-evidence.md`\nhas every tip from the 1,540 posts read, with links. Vendor-specific wording is in `references\u002Flinks.md` §4.\n\n### 4. Make it visible: board.html\n\nCopy `assets\u002Fboard.html` next to `moodboard.md` and fill the JSON block at the top (same fields as the template).\nIt draws: the reference grid with each one's job and rights badge, the subject sheet, a top-down light diagram from\nthe key angle, palette swatches with roles and shares, a framing guide (thirds grid, subject box at its position and\nsize), the texture chip, a motion beat timeline, a live type specimen in the chosen Google Font, sound, the Never\nlist, and the test stills with their check table. Example: `examples\u002Flast-bus\u002F`.\n\n### 5. Test on stills\n\nGenerate 3 stills of the hero shot from `moodboard.md` alone, on two image models if you can (with varg:\n`nano_banana_2_1` and `seedream_5_pro`, about $0.05 each; quote the price first). Use the board lines as the prompt,\nin this order: subject and action, light, palette, framing, texture, motion, type.\n\n### 6. Check every line\n\n| Line | Check | Pass |\n|---|---|---|\n| Palette | `python3 scripts\u002Fpalette.py check stills\u002F*.png --hex 0F3B3F,E07A2E,C1272D --ref refs\u002F02.jpg` | within the reference frame's ΔE + 5 (or ≤ 15 without `--ref`); closer than a still made without the palette line |\n| Light | key side and hardness match; shadows fall the right way; one source family | yes\u002Fno |\n| Framing | shot size, camera height, subject position and % of frame | within one size step |\n| Texture | grain \u002F halation \u002F flaws visible at 100% | yes\u002Fno |\n| Motion | frozen-motion cue present (stills) or the move happened (video) | yes\u002Fno |\n| Type | not in the still; set in code later | — |\n\nUse a second agent with fresh context as the critic: give it the board and the stills, not your reasoning, and\nfollow `references\u002Fjudge.md` (blind ids, line-by-line 0\u002F1\u002F2 with evidence, code measures first, pairs in both\norders, never \"rate the quality\": without criteria our judges preferred the frames that ignored the board). When a\nline fails, rewrite that line or attach a reference image for it. Typical fixes: unusual angles need a 3D blockout\n(threejs-animatic) or a reference frame; a palette that looks graded needs hex from a real frame and a softer grade.\n\n### 7. STOP for approval\n\nShow `board.html` with the stills and the check table. No video generation before the person approves.\n\n### 8. Hand over to video prompts\n\nWrite prompts in this order: reference roles first (what each attached image or clip is for), then subject and\naction, then light, palette and texture, then camera. One camera move and one subject action per shot. For\nimage-to-video, write only the motion line; the start frame already carries the look. Per-model wording:\n`references\u002Flinks.md` §4; per-shot prompting: varg-video-prompting.\n\n## Never\n\n\"cinematic\", \"8k\", \"stunning\", \"premium\", \"moody\" without numbers · evenly lit scenes · perfect symmetry ·\ninvented hex palettes · Inter, Roboto, Arial, system-ui · purple gradients · centred text fading in · text drawn\nby the video model · more than one camera move per shot · scraping sites that forbid it · feeding a model frames\nyou have no rights to.\n\n## Files in this skill\n\n- `references\u002Flinks.md`: every link (databases, X tools, 14 vendor guides, research, creator posts, varg skills)\n- `references\u002Fdimensions.md`: how to write each line, with sources\n- `references\u002Fdimensions-evidence.md`: every tip, failure and vocabulary list per dimension, linked to the posts\n- `references\u002Fevidence.md`: the test, the X statistics, the guide matrix, the benchmark numbers\n- `references\u002Fmoodboard-template.md`: the blank board\n- `references\u002Fgoal-prompt.md`: the whole skill as one copy-paste prompt\n- `references\u002Fjudge.md`: how to rank frames with an unbiased LLM judge, with our bias tests and the judge prompt\n- `assets\u002Fboard.html`: the visual board template\n- `scripts\u002Fpalette.py`: extract a palette from a reference, check a still against hex (ΔE)\n- `examples\u002Flast-bus\u002F`: a filled board with the 3 test stills\n",{"name":5,"license":15,"metadata":55,"description":7,"allowed-tools":62,"compatibility":63},{"author":56,"version":57,"openclaw":58},"vargHQ","1.0.1",{"homepage":59,"requires":60},"https:\u002F\u002Fgithub.com\u002FvargHQ\u002Fskills\u002Ftree\u002Fmain\u002Fvideo-moodboard",{"anyBins":61},[32],"Bash(python3:*) Bash(curl:*) Read Write Edit","Works in any agent with a shell and web access. scripts\u002Fpalette.py needs Python 3 and Pillow. Test stills cost about $0.05 each through varg (Nano Banana 2.1 or Seedream 5 Pro); everything else is free. Reference MCPs (FrameThrower, Refs, Are.na) are optional and used through find-references.","main","2a6d24be2ed571c5ff2319c506b60741bbcb1cb0","plugins\u002FvargHQ\u002Fskills\u002Fvideo-moodboard",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":75,"prompt":85,"zipAvailable":86},[76,79,82],{"tool":77,"command":78},"npx","npx skills add hashgraph-online\u002Fawesome-codex-plugins --skill video-moodboard",{"tool":80,"command":81},"bunx","bunx skills add hashgraph-online\u002Fawesome-codex-plugins --skill video-moodboard",{"tool":83,"command":84},"pnpm","pnpm dlx skills add hashgraph-online\u002Fawesome-codex-plugins --skill video-moodboard","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FvargHQ\u002Fskills\u002Fvideo-moodboard\u002FSKILL.md",true,[88,94,99,103,107,111,115,119,123,127,131,135],{"path":89,"resourceType":90,"resourceTypeDesc":91,"sizeBytes":92,"sourceHtmlUrl":93},"assets\u002Fboard.html","ASSET","资产文件",20888,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FvargHQ\u002Fskills\u002Fvideo-moodboard\u002Fassets\u002Fboard.html",{"path":95,"resourceType":96,"resourceTypeDesc":97,"sizeBytes":92,"sourceHtmlUrl":98},"examples\u002Flast-bus\u002Fboard.html","REFERENCE","参考文档","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FvargHQ\u002Fskills\u002Fvideo-moodboard\u002Fexamples\u002Flast-bus\u002Fboard.html",{"path":100,"resourceType":96,"resourceTypeDesc":97,"sizeBytes":101,"sourceHtmlUrl":102},"examples\u002Flast-bus\u002Fmoodboard.md",3362,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FvargHQ\u002Fskills\u002Fvideo-moodboard\u002Fexamples\u002Flast-bus\u002Fmoodboard.md",{"path":104,"resourceType":96,"resourceTypeDesc":97,"sizeBytes":105,"sourceHtmlUrl":106},"README.md",6416,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FvargHQ\u002Fskills\u002Fvideo-moodboard\u002FREADME.md",{"path":108,"resourceType":96,"resourceTypeDesc":97,"sizeBytes":109,"sourceHtmlUrl":110},"references\u002Fdimensions-evidence.md",54698,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FvargHQ\u002Fskills\u002Fvideo-moodboard\u002Freferences\u002Fdimensions-evidence.md",{"path":112,"resourceType":96,"resourceTypeDesc":97,"sizeBytes":113,"sourceHtmlUrl":114},"references\u002Fdimensions.md",17816,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FvargHQ\u002Fskills\u002Fvideo-moodboard\u002Freferences\u002Fdimensions.md",{"path":116,"resourceType":96,"resourceTypeDesc":97,"sizeBytes":117,"sourceHtmlUrl":118},"references\u002Fevidence.md",5461,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FvargHQ\u002Fskills\u002Fvideo-moodboard\u002Freferences\u002Fevidence.md",{"path":120,"resourceType":96,"resourceTypeDesc":97,"sizeBytes":121,"sourceHtmlUrl":122},"references\u002Fgoal-prompt.md",4715,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FvargHQ\u002Fskills\u002Fvideo-moodboard\u002Freferences\u002Fgoal-prompt.md",{"path":124,"resourceType":96,"resourceTypeDesc":97,"sizeBytes":125,"sourceHtmlUrl":126},"references\u002Fjudge.md",4834,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FvargHQ\u002Fskills\u002Fvideo-moodboard\u002Freferences\u002Fjudge.md",{"path":128,"resourceType":96,"resourceTypeDesc":97,"sizeBytes":129,"sourceHtmlUrl":130},"references\u002Flinks.md",258980,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FvargHQ\u002Fskills\u002Fvideo-moodboard\u002Freferences\u002Flinks.md",{"path":132,"resourceType":96,"resourceTypeDesc":97,"sizeBytes":133,"sourceHtmlUrl":134},"references\u002Fmoodboard-template.md",2337,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FvargHQ\u002Fskills\u002Fvideo-moodboard\u002Freferences\u002Fmoodboard-template.md",{"path":136,"resourceType":137,"resourceTypeDesc":138,"sizeBytes":139,"sourceHtmlUrl":140},"scripts\u002Fpalette.py","SCRIPT","脚本",5524,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FvargHQ\u002Fskills\u002Fvideo-moodboard\u002Fscripts\u002Fpalette.py",[142,151,159,167,175,183],{"skillNo":143,"name":144,"nameZh":6,"description":145,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":146,"sourceHtmlUrl":147,"categories":148,"keywords":149,"publishedAt":150},"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",[],[],"2026-11-15 14:19:17",{"skillNo":152,"name":153,"nameZh":6,"description":154,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":155,"sourceHtmlUrl":156,"categories":157,"keywords":158,"publishedAt":150},"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":160,"name":161,"nameZh":6,"description":162,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":163,"sourceHtmlUrl":164,"categories":165,"keywords":166,"publishedAt":150},"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":168,"name":169,"nameZh":6,"description":170,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":171,"sourceHtmlUrl":172,"categories":173,"keywords":174,"publishedAt":150},"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":176,"name":177,"nameZh":6,"description":178,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":179,"sourceHtmlUrl":180,"categories":181,"keywords":182,"publishedAt":150},"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":184,"name":185,"nameZh":6,"description":186,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":187,"sourceHtmlUrl":188,"categories":189,"keywords":190,"publishedAt":150},"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",[],[]]