[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6MNCBTMK5TSP406Z01XEN99":3,"skill-same:01M6MNCBTMK5TSP406Z01XEN99":249},{"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":37,"publishedAt":58,"linkOnly":59,"markdownContent":60,"markdownBody":61,"frontMatter":62,"refName":73,"commitSha":74,"skillDirectory":75,"forksCount":76,"repositoryHtmlUrl":77,"repositoryHomepageUrl":78,"ownerHtmlUrl":79,"ownerBlogUrl":80,"ownerDescription":81,"updatedAt":82,"install":83,"resources":96},"01M6MNCBTMK5TSP406Z01XEN99","character-passport",null,"Cast an AI video before anything moves: for every character and hero prop, a passport (one paragraph, every visible detail, pasted word for word into every prompt), a turnaround sheet in the moodboard's look, six expressions written as cause + physical tells, a measured voice line (pace in words per minute, accent, one verbal habit), and for props the materials, wear and how they move and sound. Includes anti-slop design rules, a prompt builder that refuses paraphrased passports, code routes (three.js, VRM, SVG face rig) and tested reference sites. Use for \"make a character\", \"consistent character\", \"character sheet\", \"turnaround\", \"character bible\", \"expression sheet\", \"voice for my character\", \"prop sheet\", \"same person in every shot\", or characters that look generic, plastic or different from shot to shot. Not for category looks (varg-character-design), real actor photos in multi-scene ads (varg-consistent-characters) or the film's look (video-moodboard).","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\u002Fcharacter-passport\u002FSKILL.md",[18,23,26,29,34],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000015","视觉设计","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",{"categoryNo":30,"categoryName":31,"taxonomyType":32,"taxonomyTypeDesc":33},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",{"categoryNo":35,"categoryName":36,"taxonomyType":32,"taxonomyTypeDesc":33},"01JBSEEDCAT000000000000032","设计师",[38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57],"character passport","character","character sheet","pillow","take","edit","write","read","how","banana","ads","character bible","character-design","image","MCP","design","expression","move","slop","Video","2026-11-10 10:12:30",false,"---\nname: character-passport\ndescription: >-\n  Cast an AI video before anything moves: for every character and hero prop, a passport (one paragraph, every\n  visible detail, pasted word for word into every prompt), a turnaround sheet in the moodboard's look, six\n  expressions written as cause + physical tells, a measured voice line (pace in words per minute, accent, one verbal\n  habit), and for props the materials, wear and how they move and sound. Includes anti-slop design rules, a prompt\n  builder that refuses paraphrased passports, code routes (three.js, VRM, SVG face rig) and tested reference sites.\n  Use for \"make a character\", \"consistent character\", \"character sheet\", \"turnaround\", \"character bible\",\n  \"expression sheet\", \"voice for my character\", \"prop sheet\", \"same person in every shot\", or characters that look\n  generic, plastic or different from shot to shot. Not for category looks (varg-character-design), real actor photos\n  in multi-scene ads (varg-consistent-characters) or the film's look (video-moodboard).\nlicense: MIT\nmetadata:\n  author: vargHQ\n  version: \"1.0.2\"\n  openclaw:\n    requires:\n      anyBins:\n        - python3\n    homepage: https:\u002F\u002Fgithub.com\u002FvargHQ\u002Fskills\u002Ftree\u002Fmain\u002Fcharacter-passport\ncompatibility: >-\n  Works in any agent with a shell. scripts\u002Fprompt.py needs Python 3; crop_sheet.py needs Pillow; voice_check.py\n  needs ffmpeg. Images and voices through varg (MCP https:\u002F\u002Fmcp.varg.ai\u002Fmcp or VARG_API_KEY): about $0.05 per\n  image on Nano Banana 2.1 and $0.01 per voice take on Gemini 3.8 Flash TTS. Code routes need a browser or bun.\nallowed-tools: Bash(python3:*) Bash(curl:*) Bash(ffmpeg:*) Bash(ffprobe:*) Read Write Edit\n---\n\n# Character passport\n\n> Step 5 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\u002Fdesign-characters-and-props-for-ai-video (as Markdown: add `.md`).\n\nCharacter slop comes from letting the model choose the face, the clothes and the feeling. This skill takes those\nchoices back, one checkable line at a time, and proves each step on a still before any video is paid for.\n\nWhat our test showed (Nano Banana 2.1, 2026-11-03, full write-up: https:\u002F\u002Fvarg.ai\u002Fhow-to\u002Fdesign-characters-and-props-for-ai-video):\n\n- **The passport gets you halfway; the sheet finishes the job.** Two blind AI judges scored \"same person across four\n  shots\" 2\u002F10 for the moodboard's one-line subject, 5\u002F10 for the passport alone, and 7.5-8.5\u002F10 with a sheet as\n  Image 1. Grey and moodboard-lit sheets tied; neither leaked its grid or backdrop.\n- **Big features survive, small and side-specific ones don't.** Collar, scarf, hair and eye shadows: 89-100%.\n  Hair behind the right ear 0\u002F23, scar on the left 0\u002F14 (mirrored), salt-marked boots 0\u002F12, worn umbrella handle\n  0\u002F22 when its own prop sheet was not attached.\n- **Cause + tells beats adjectives for acting.** Stills: more real (7 vs 5) and less theatrical (3.5 vs 6).\n  Video, same start frame: the adjective prompt made Kling 4 under-act and Seedance 2.5 over-act into a snarl;\n  cause + tells + timing played as written on both (one clip each).\n- **Measure the voice.** \"Slow, half-second pauses\" came out at 92 wpm against a 130 target; the corrected line\n  landed at 129.\n\n## Files you produce\n\n```\ncast\u002F\u003Cid>.md        one per character and hero prop: premise, ```passport, ```voice or ```motion, never-change list\ncast\u002F\u003Cid>-sheet.png turnaround sheet (approved), plus panels\u002F cut by scripts\u002Fcrop_sheet.py\ncast\u002F\u003Cid>-faces.png six-expression sheet (characters)\ncast\u002F\u003Cid>-voice.wav approved voice take + its voice_check.py result\ncast\u002Fboard.md       the cast at a glance: one row per character\u002Fprop with sheet, faces, voice, status\n```\n\n## Step by step\n\n### 0. Inputs\n\nRead `moodboard.md` (video-moodboard) for the look block and `script.md` \u002F `story.md` for what each character does.\nNo moodboard yet: run video-moodboard first, or write a 3-line look block (light, palette, film stock) and say so.\n\n### 1. Design the person before the picture\n\nAnswer in `cast\u002F\u003Cid>.md`, one line each: premise (who, in one sentence) · job and history · what they want in this\nfilm and what stops them · one visible flaw · one BIG signature detail readable at phone size · a silhouette that reads\nas a black shape · why each garment is on them (job, money, weather, era). Category looks (grandmas, big guys,\nmascots, beautiful women, cartoon): open the matching varg-character-design recipe.\nRules and the slop-tell list: [references\u002Fdesign.md](references\u002Fdesign.md).\n\n### 2. Write the passport\n\nOne paragraph, fixed order: who (name, age as a number, origin, job) → height, build, posture → face top to bottom\n→ skin → hair → clothes outer to inner, top to bottom, each with colour, material and one sign of wear → hands.\nOnly what a camera sees; side and size for every mark (then check it: models mirror sides); no value words; no\ndetail that hides another (a scarf over the missing button); under ~900 characters. Put it in a\n```passport fenced block. Template and filled examples: [references\u002Fpassport.md](references\u002Fpassport.md).\n\n### 3. Turnaround sheet in the moodboard look\n\nFront, side, back full body (same scale, one ground line, empty hands) over three big close-ups (front,\nthree-quarter, profile). Light it with the film's key direction and colour temperature, the film stock's texture,\na plain backdrop in the palette's darkest tone, and a fill that keeps every feature readable. Use flat 18% grey\ninstead when the character moves between very different lights. Prompts: [references\u002Fsheets.md](references\u002Fsheets.md).\n\n**Check** the sheet against the passport line by line; fix misses with an edit pass on the sheet, not a re-roll.\nCut panels: `python3 scripts\u002Fcrop_sheet.py cast\u002F\u003Cid>-sheet.png --out cast\u002F\u003Cid>-panels`.\n\n### 4. Six expressions (characters)\n\nPick six moments the film needs. Write each as **a cause in the film + physical tells** (brows, lids, mouth,\njaw, head, breath), never an adjective. Default set: listening (rest face), real laugh, anger held in, worry,\nstartle, contempt. Generate one 3x2 sheet with the turnaround as Image 1. Tells per emotion and what video models\nget wrong: [references\u002Facting.md](references\u002Facting.md).\n\n### 5. Voice line (characters who speak)\n\nWrite a ```voice block: pace in words per minute + where the pauses go · pitch and texture · accent (region,\nclass, first language) · one verbal habit · default emotion. Generate a test line in the character's words, then\n`python3 scripts\u002Fvoice_check.py take.wav --text \"\u003Cline>\" --target-wpm \u003Cn>`. Fix the instruction, not the target,\nuntil it passes. Then listen for the accent: no script checks it. Details and model notes:\n[references\u002Fvoice.md](references\u002Fvoice.md).\n\n### 6. Props\n\nEvery object the camera lingers on or a character touches twice gets its own `cast\u002F\u003Cid>.md`: a ```passport\n(what it is, materials and finish, size, wear and where it comes from, never-change) and a ```motion block\n(weight, how it moves, what it sounds like). Sheet: five views on the same backdrop, no hands, one close-up of\nthe wear. Attach the prop sheet as Image 2 in every shot where the prop must read: without it, the worn handle came\nout right 0 of 22 times. [references\u002Fprops.md](references\u002Fprops.md).\n\n### 7. Use them in every shot\n\nBuild each shot prompt with the script, so the passports go in word for word and the prompt stays under the\nmodel's limit:\n\n```bash\npython3 scripts\u002Fprompt.py build --sheet \"Vesna\" --shot \"Close-up, 50mm: ...\" \\\n  --cast cast\u002Fvesna.md --cast cast\u002Fumbrella.md --look moodboard.md [--video]\npython3 scripts\u002Fprompt.py check prompts\u002F*.txt --cast cast\u002Fvesna.md --cast cast\u002Fumbrella.md   # before any batch\n```\n\nImages: the sheet (or its panels) as Image 1, prop sheet as Image 2, location master as Image 3, each named by\njob, plus a winner rule. Video: animate an approved still (Kling 4), or give Seedance 2.5 the face close-up and the\nfull-body front. Model table: [references\u002Fgenerate.md](references\u002Fgenerate.md). On GPT Image 2.6 \u002F ChatGPT: [references\u002Fgpt-image.md](references\u002Fgpt-image.md).\n\n### 8. Judge and rank takes\n\nCode first: `scripts\u002Fface_check.py` for identity, `scripts\u002Fvoice_check.py` for pace, `scripts\u002Fprompt.py check` for\npassports. Then AI judges on one binary criterion per call, blind, reference first, three model families, takes\nranked in pairs in both orders. Calibrate each criterion against people (`scripts\u002Fjudge_agreement.py`) before\ntrusting it. Rubric, judge prompt and the biases to design against: [references\u002Fjudge.md](references\u002Fjudge.md).\n\n### 9. STOP for approval\n\nShow `cast\u002Fboard.md` with sheet, faces, prop sheet and the voice take's numbers. Nothing moves before a yes.\n\n## Other routes\n\n- **Build them in code** when the shape must be exact or reused a lot: a three.js blockout or VRM puppet rendered\n  from four cameras, an SVG face rig driven by FACS action units, a PBR prop, or image-to-3D from an approved front\n  view; then one image-edit pass dresses it in the film's look (tested: same pose, proportions and prop placement).\n  Code in `code\u002F`, routes and gotchas in [references\u002Fcode.md](references\u002Fcode.md).\n- **Find references first** (real faces, costumes, props, accents): [references\u002Freference-sites.md](references\u002Freference-sites.md)\n  and the find-references skill.\n\n## Never\n\n\"beautiful\", \"perfect\", \"stunning\", \"flawless\", \"cinematic\" in a passport · a celebrity's or a living actor's name ·\nparaphrasing a passport between shots · props in the character's hands on the sheet · two looks on one sheet ·\nexpressions as bare adjectives · a voice without a measured take · brand names (they draw logos) · real people's\nfaces without consent.\n\n## Files in this skill\n\n- `references\u002Fdesign.md`: designing a specific person; the slop tells\n- `references\u002Fpassport.md`: template, rules, filled examples\n- `references\u002Fsheets.md`: turnaround, expression and prop sheet prompts; moodboard vs grey\n- `references\u002Facting.md`: six expressions with physical tells; making emotion read as real in video\n- `references\u002Fvoice.md`: the voice line, pace numbers, accents, verbal habits, TTS models\n- `references\u002Fprops.md`: prop passport, materials, wear, motion and sound\n- `references\u002Fgenerate.md`: models and reference order for stills and video\n- `references\u002Fgpt-image.md`: GPT Image 2.6 (ChatGPT's model): settings, measured drift, fixes, prompts\n- `references\u002Fcode.md`: three.js, VRM, SVG and Blender routes\n- `references\u002Freference-sites.md`: tested sites for faces, costumes, props, poses and accents\n- `references\u002Fpeople.md`: who to learn from on X and in the craft, why to trust them, and red flags\n- `references\u002Fx-evidence.md`: 200+ techniques from X by topic, verbatim, with links and metrics\n- `references\u002Fcraft-evidence.md`: design, slop, acting, voice, prop and sheet rules from studios, research and model guides, with quotes\n- `references\u002Fevidence.md`: the blind-judged test behind this skill (numbers, prompts, cost)\n- `references\u002Fjudge.md`: judging and ranking takes with AI judges: rubric, prompt, protocol, biases\n- `references\u002Fjudge-evidence.md`: the research behind judge.md (biases with numbers, VLM failure modes, sources)\n- `references\u002Fgoal-prompt.md`: the whole skill as one copy-paste prompt\n- `scripts\u002Fprompt.py`, `scripts\u002Fvoice_check.py`, `scripts\u002Fcrop_sheet.py`, `scripts\u002Fface_check.py` (identity by face\n  embedding), `scripts\u002Fjudge_agreement.py` (judge vs judge vs human: kappa, TPR, TNR)\n- `code\u002F`: tested three.js blockout turnaround, VRM expression sheet, SVG FACS face rig, PBR prop, GLB turnaround,\n  image-to-3D client scripts, and `shoot.ts` (Bun + Playwright headless renderer)\n- `examples\u002Fvesna\u002F`: the worked example (passport, voice, six expressions, umbrella, all image URLs)\n","# Character passport\n\n> Step 5 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\u002Fdesign-characters-and-props-for-ai-video (as Markdown: add `.md`).\n\nCharacter slop comes from letting the model choose the face, the clothes and the feeling. This skill takes those\nchoices back, one checkable line at a time, and proves each step on a still before any video is paid for.\n\nWhat our test showed (Nano Banana 2.1, 2026-11-03, full write-up: https:\u002F\u002Fvarg.ai\u002Fhow-to\u002Fdesign-characters-and-props-for-ai-video):\n\n- **The passport gets you halfway; the sheet finishes the job.** Two blind AI judges scored \"same person across four\n  shots\" 2\u002F10 for the moodboard's one-line subject, 5\u002F10 for the passport alone, and 7.5-8.5\u002F10 with a sheet as\n  Image 1. Grey and moodboard-lit sheets tied; neither leaked its grid or backdrop.\n- **Big features survive, small and side-specific ones don't.** Collar, scarf, hair and eye shadows: 89-100%.\n  Hair behind the right ear 0\u002F23, scar on the left 0\u002F14 (mirrored), salt-marked boots 0\u002F12, worn umbrella handle\n  0\u002F22 when its own prop sheet was not attached.\n- **Cause + tells beats adjectives for acting.** Stills: more real (7 vs 5) and less theatrical (3.5 vs 6).\n  Video, same start frame: the adjective prompt made Kling 4 under-act and Seedance 2.5 over-act into a snarl;\n  cause + tells + timing played as written on both (one clip each).\n- **Measure the voice.** \"Slow, half-second pauses\" came out at 92 wpm against a 130 target; the corrected line\n  landed at 129.\n\n## Files you produce\n\n```\ncast\u002F\u003Cid>.md        one per character and hero prop: premise, ```passport, ```voice or ```motion, never-change list\ncast\u002F\u003Cid>-sheet.png turnaround sheet (approved), plus panels\u002F cut by scripts\u002Fcrop_sheet.py\ncast\u002F\u003Cid>-faces.png six-expression sheet (characters)\ncast\u002F\u003Cid>-voice.wav approved voice take + its voice_check.py result\ncast\u002Fboard.md       the cast at a glance: one row per character\u002Fprop with sheet, faces, voice, status\n```\n\n## Step by step\n\n### 0. Inputs\n\nRead `moodboard.md` (video-moodboard) for the look block and `script.md` \u002F `story.md` for what each character does.\nNo moodboard yet: run video-moodboard first, or write a 3-line look block (light, palette, film stock) and say so.\n\n### 1. Design the person before the picture\n\nAnswer in `cast\u002F\u003Cid>.md`, one line each: premise (who, in one sentence) · job and history · what they want in this\nfilm and what stops them · one visible flaw · one BIG signature detail readable at phone size · a silhouette that reads\nas a black shape · why each garment is on them (job, money, weather, era). Category looks (grandmas, big guys,\nmascots, beautiful women, cartoon): open the matching varg-character-design recipe.\nRules and the slop-tell list: [references\u002Fdesign.md](references\u002Fdesign.md).\n\n### 2. Write the passport\n\nOne paragraph, fixed order: who (name, age as a number, origin, job) → height, build, posture → face top to bottom\n→ skin → hair → clothes outer to inner, top to bottom, each with colour, material and one sign of wear → hands.\nOnly what a camera sees; side and size for every mark (then check it: models mirror sides); no value words; no\ndetail that hides another (a scarf over the missing button); under ~900 characters. Put it in a\n```passport fenced block. Template and filled examples: [references\u002Fpassport.md](references\u002Fpassport.md).\n\n### 3. Turnaround sheet in the moodboard look\n\nFront, side, back full body (same scale, one ground line, empty hands) over three big close-ups (front,\nthree-quarter, profile). Light it with the film's key direction and colour temperature, the film stock's texture,\na plain backdrop in the palette's darkest tone, and a fill that keeps every feature readable. Use flat 18% grey\ninstead when the character moves between very different lights. Prompts: [references\u002Fsheets.md](references\u002Fsheets.md).\n\n**Check** the sheet against the passport line by line; fix misses with an edit pass on the sheet, not a re-roll.\nCut panels: `python3 scripts\u002Fcrop_sheet.py cast\u002F\u003Cid>-sheet.png --out cast\u002F\u003Cid>-panels`.\n\n### 4. Six expressions (characters)\n\nPick six moments the film needs. Write each as **a cause in the film + physical tells** (brows, lids, mouth,\njaw, head, breath), never an adjective. Default set: listening (rest face), real laugh, anger held in, worry,\nstartle, contempt. Generate one 3x2 sheet with the turnaround as Image 1. Tells per emotion and what video models\nget wrong: [references\u002Facting.md](references\u002Facting.md).\n\n### 5. Voice line (characters who speak)\n\nWrite a ```voice block: pace in words per minute + where the pauses go · pitch and texture · accent (region,\nclass, first language) · one verbal habit · default emotion. Generate a test line in the character's words, then\n`python3 scripts\u002Fvoice_check.py take.wav --text \"\u003Cline>\" --target-wpm \u003Cn>`. Fix the instruction, not the target,\nuntil it passes. Then listen for the accent: no script checks it. Details and model notes:\n[references\u002Fvoice.md](references\u002Fvoice.md).\n\n### 6. Props\n\nEvery object the camera lingers on or a character touches twice gets its own `cast\u002F\u003Cid>.md`: a ```passport\n(what it is, materials and finish, size, wear and where it comes from, never-change) and a ```motion block\n(weight, how it moves, what it sounds like). Sheet: five views on the same backdrop, no hands, one close-up of\nthe wear. Attach the prop sheet as Image 2 in every shot where the prop must read: without it, the worn handle came\nout right 0 of 22 times. [references\u002Fprops.md](references\u002Fprops.md).\n\n### 7. Use them in every shot\n\nBuild each shot prompt with the script, so the passports go in word for word and the prompt stays under the\nmodel's limit:\n\n```bash\npython3 scripts\u002Fprompt.py build --sheet \"Vesna\" --shot \"Close-up, 50mm: ...\" \\\n  --cast cast\u002Fvesna.md --cast cast\u002Fumbrella.md --look moodboard.md [--video]\npython3 scripts\u002Fprompt.py check prompts\u002F*.txt --cast cast\u002Fvesna.md --cast cast\u002Fumbrella.md   # before any batch\n```\n\nImages: the sheet (or its panels) as Image 1, prop sheet as Image 2, location master as Image 3, each named by\njob, plus a winner rule. Video: animate an approved still (Kling 4), or give Seedance 2.5 the face close-up and the\nfull-body front. Model table: [references\u002Fgenerate.md](references\u002Fgenerate.md). On GPT Image 2.6 \u002F ChatGPT: [references\u002Fgpt-image.md](references\u002Fgpt-image.md).\n\n### 8. Judge and rank takes\n\nCode first: `scripts\u002Fface_check.py` for identity, `scripts\u002Fvoice_check.py` for pace, `scripts\u002Fprompt.py check` for\npassports. Then AI judges on one binary criterion per call, blind, reference first, three model families, takes\nranked in pairs in both orders. Calibrate each criterion against people (`scripts\u002Fjudge_agreement.py`) before\ntrusting it. Rubric, judge prompt and the biases to design against: [references\u002Fjudge.md](references\u002Fjudge.md).\n\n### 9. STOP for approval\n\nShow `cast\u002Fboard.md` with sheet, faces, prop sheet and the voice take's numbers. Nothing moves before a yes.\n\n## Other routes\n\n- **Build them in code** when the shape must be exact or reused a lot: a three.js blockout or VRM puppet rendered\n  from four cameras, an SVG face rig driven by FACS action units, a PBR prop, or image-to-3D from an approved front\n  view; then one image-edit pass dresses it in the film's look (tested: same pose, proportions and prop placement).\n  Code in `code\u002F`, routes and gotchas in [references\u002Fcode.md](references\u002Fcode.md).\n- **Find references first** (real faces, costumes, props, accents): [references\u002Freference-sites.md](references\u002Freference-sites.md)\n  and the find-references skill.\n\n## Never\n\n\"beautiful\", \"perfect\", \"stunning\", \"flawless\", \"cinematic\" in a passport · a celebrity's or a living actor's name ·\nparaphrasing a passport between shots · props in the character's hands on the sheet · two looks on one sheet ·\nexpressions as bare adjectives · a voice without a measured take · brand names (they draw logos) · real people's\nfaces without consent.\n\n## Files in this skill\n\n- `references\u002Fdesign.md`: designing a specific person; the slop tells\n- `references\u002Fpassport.md`: template, rules, filled examples\n- `references\u002Fsheets.md`: turnaround, expression and prop sheet prompts; moodboard vs grey\n- `references\u002Facting.md`: six expressions with physical tells; making emotion read as real in video\n- `references\u002Fvoice.md`: the voice line, pace numbers, accents, verbal habits, TTS models\n- `references\u002Fprops.md`: prop passport, materials, wear, motion and sound\n- `references\u002Fgenerate.md`: models and reference order for stills and video\n- `references\u002Fgpt-image.md`: GPT Image 2.6 (ChatGPT's model): settings, measured drift, fixes, prompts\n- `references\u002Fcode.md`: three.js, VRM, SVG and Blender routes\n- `references\u002Freference-sites.md`: tested sites for faces, costumes, props, poses and accents\n- `references\u002Fpeople.md`: who to learn from on X and in the craft, why to trust them, and red flags\n- `references\u002Fx-evidence.md`: 200+ techniques from X by topic, verbatim, with links and metrics\n- `references\u002Fcraft-evidence.md`: design, slop, acting, voice, prop and sheet rules from studios, research and model guides, with quotes\n- `references\u002Fevidence.md`: the blind-judged test behind this skill (numbers, prompts, cost)\n- `references\u002Fjudge.md`: judging and ranking takes with AI judges: rubric, prompt, protocol, biases\n- `references\u002Fjudge-evidence.md`: the research behind judge.md (biases with numbers, VLM failure modes, sources)\n- `references\u002Fgoal-prompt.md`: the whole skill as one copy-paste prompt\n- `scripts\u002Fprompt.py`, `scripts\u002Fvoice_check.py`, `scripts\u002Fcrop_sheet.py`, `scripts\u002Fface_check.py` (identity by face\n  embedding), `scripts\u002Fjudge_agreement.py` (judge vs judge vs human: kappa, TPR, TNR)\n- `code\u002F`: tested three.js blockout turnaround, VRM expression sheet, SVG FACS face rig, PBR prop, GLB turnaround,\n  image-to-3D client scripts, and `shoot.ts` (Bun + Playwright headless renderer)\n- `examples\u002Fvesna\u002F`: the worked example (passport, voice, six expressions, umbrella, all image URLs)\n",{"name":5,"license":15,"metadata":63,"description":7,"allowed-tools":71,"compatibility":72},{"author":64,"version":65,"openclaw":66},"vargHQ","1.0.2",{"homepage":67,"requires":68},"https:\u002F\u002Fgithub.com\u002FvargHQ\u002Fskills\u002Ftree\u002Fmain\u002Fcharacter-passport",{"anyBins":69},[70],"python3","Bash(python3:*) Bash(curl:*) Bash(ffmpeg:*) Bash(ffprobe:*) Read Write Edit","Works in any agent with a shell. scripts\u002Fprompt.py needs Python 3; crop_sheet.py needs Pillow; voice_check.py needs ffmpeg. Images and voices through varg (MCP https:\u002F\u002Fmcp.varg.ai\u002Fmcp or VARG_API_KEY): about $0.05 per image on Nano Banana 2.1 and $0.01 per voice take on Gemini 3.8 Flash TTS. Code routes need a browser or bun.","main","2a6d24be2ed571c5ff2319c506b60741bbcb1cb0","plugins\u002FvargHQ\u002Fskills\u002Fcharacter-passport",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":84,"prompt":94,"zipAvailable":95},[85,88,91],{"tool":86,"command":87},"npx","npx skills add hashgraph-online\u002Fawesome-codex-plugins --skill character-passport",{"tool":89,"command":90},"bunx","bunx skills add hashgraph-online\u002Fawesome-codex-plugins --skill character-passport",{"tool":92,"command":93},"pnpm","pnpm dlx skills add hashgraph-online\u002Fawesome-codex-plugins --skill character-passport","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FvargHQ\u002Fskills\u002Fcharacter-passport\u002FSKILL.md",true,[97,103,109,113,117,121,125,129,133,137,141,145,149,153,157,161,165,169,173,177,181,185,189,193,197,201,205,209,213,217,221,225,229,233,237,241,245],{"path":98,"resourceType":99,"resourceTypeDesc":100,"sizeBytes":101,"sourceHtmlUrl":102},"code\u002Fblockout_turnaround.html","REFERENCE","参考文档",6794,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FvargHQ\u002Fskills\u002Fcharacter-passport\u002Fcode\u002Fblockout_turnaround.html",{"path":104,"resourceType":105,"resourceTypeDesc":106,"sizeBytes":107,"sourceHtmlUrl":108},"code\u002Fface_rig.py","SCRIPT","脚本",6227,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FvargHQ\u002Fskills\u002Fcharacter-passport\u002Fcode\u002Fface_rig.py",{"path":110,"resourceType":99,"resourceTypeDesc":100,"sizeBytes":111,"sourceHtmlUrl":112},"code\u002Fglb_turnaround.html",2582,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FvargHQ\u002Fskills\u002Fcharacter-passport\u002Fcode\u002Fglb_turnaround.html",{"path":114,"resourceType":105,"resourceTypeDesc":106,"sizeBytes":115,"sourceHtmlUrl":116},"code\u002Fhunyuan3d_space.py",899,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FvargHQ\u002Fskills\u002Fcharacter-passport\u002Fcode\u002Fhunyuan3d_space.py",{"path":118,"resourceType":99,"resourceTypeDesc":100,"sizeBytes":119,"sourceHtmlUrl":120},"code\u002Fpackage.json",137,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FvargHQ\u002Fskills\u002Fcharacter-passport\u002Fcode\u002Fpackage.json",{"path":122,"resourceType":99,"resourceTypeDesc":100,"sizeBytes":123,"sourceHtmlUrl":124},"code\u002Fprop_pbr.html",4801,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FvargHQ\u002Fskills\u002Fcharacter-passport\u002Fcode\u002Fprop_pbr.html",{"path":126,"resourceType":105,"resourceTypeDesc":106,"sizeBytes":127,"sourceHtmlUrl":128},"code\u002Fshoot.ts",1613,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FvargHQ\u002Fskills\u002Fcharacter-passport\u002Fcode\u002Fshoot.ts",{"path":130,"resourceType":105,"resourceTypeDesc":106,"sizeBytes":131,"sourceHtmlUrl":132},"code\u002Ftrellis2_space.py",734,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FvargHQ\u002Fskills\u002Fcharacter-passport\u002Fcode\u002Ftrellis2_space.py",{"path":134,"resourceType":99,"resourceTypeDesc":100,"sizeBytes":135,"sourceHtmlUrl":136},"code\u002Fvrm_expressions.html",3921,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FvargHQ\u002Fskills\u002Fcharacter-passport\u002Fcode\u002Fvrm_expressions.html",{"path":138,"resourceType":99,"resourceTypeDesc":100,"sizeBytes":139,"sourceHtmlUrl":140},"examples\u002Fvesna\u002Fboard.md",1320,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FvargHQ\u002Fskills\u002Fcharacter-passport\u002Fexamples\u002Fvesna\u002Fboard.md",{"path":142,"resourceType":99,"resourceTypeDesc":100,"sizeBytes":143,"sourceHtmlUrl":144},"examples\u002Fvesna\u002Flook.md",453,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FvargHQ\u002Fskills\u002Fcharacter-passport\u002Fexamples\u002Fvesna\u002Flook.md",{"path":146,"resourceType":99,"resourceTypeDesc":100,"sizeBytes":147,"sourceHtmlUrl":148},"examples\u002Fvesna\u002FREADME.md",3721,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FvargHQ\u002Fskills\u002Fcharacter-passport\u002Fexamples\u002Fvesna\u002FREADME.md",{"path":150,"resourceType":99,"resourceTypeDesc":100,"sizeBytes":151,"sourceHtmlUrl":152},"examples\u002Fvesna\u002Fumbrella.md",1116,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FvargHQ\u002Fskills\u002Fcharacter-passport\u002Fexamples\u002Fvesna\u002Fumbrella.md",{"path":154,"resourceType":99,"resourceTypeDesc":100,"sizeBytes":155,"sourceHtmlUrl":156},"examples\u002Fvesna\u002Fvesna.md",3566,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FvargHQ\u002Fskills\u002Fcharacter-passport\u002Fexamples\u002Fvesna\u002Fvesna.md",{"path":158,"resourceType":99,"resourceTypeDesc":100,"sizeBytes":159,"sourceHtmlUrl":160},"README.md",6732,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FvargHQ\u002Fskills\u002Fcharacter-passport\u002FREADME.md",{"path":162,"resourceType":99,"resourceTypeDesc":100,"sizeBytes":163,"sourceHtmlUrl":164},"references\u002Facting.md",7836,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FvargHQ\u002Fskills\u002Fcharacter-passport\u002Freferences\u002Facting.md",{"path":166,"resourceType":99,"resourceTypeDesc":100,"sizeBytes":167,"sourceHtmlUrl":168},"references\u002Fcode.md",14106,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FvargHQ\u002Fskills\u002Fcharacter-passport\u002Freferences\u002Fcode.md",{"path":170,"resourceType":99,"resourceTypeDesc":100,"sizeBytes":171,"sourceHtmlUrl":172},"references\u002Fcraft-evidence.md",74754,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FvargHQ\u002Fskills\u002Fcharacter-passport\u002Freferences\u002Fcraft-evidence.md",{"path":174,"resourceType":99,"resourceTypeDesc":100,"sizeBytes":175,"sourceHtmlUrl":176},"references\u002Fdesign.md",4934,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FvargHQ\u002Fskills\u002Fcharacter-passport\u002Freferences\u002Fdesign.md",{"path":178,"resourceType":99,"resourceTypeDesc":100,"sizeBytes":179,"sourceHtmlUrl":180},"references\u002Fevidence.md",4055,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FvargHQ\u002Fskills\u002Fcharacter-passport\u002Freferences\u002Fevidence.md",{"path":182,"resourceType":99,"resourceTypeDesc":100,"sizeBytes":183,"sourceHtmlUrl":184},"references\u002Fgenerate.md",3488,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FvargHQ\u002Fskills\u002Fcharacter-passport\u002Freferences\u002Fgenerate.md",{"path":186,"resourceType":99,"resourceTypeDesc":100,"sizeBytes":187,"sourceHtmlUrl":188},"references\u002Fgoal-prompt.md",4612,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FvargHQ\u002Fskills\u002Fcharacter-passport\u002Freferences\u002Fgoal-prompt.md",{"path":190,"resourceType":99,"resourceTypeDesc":100,"sizeBytes":191,"sourceHtmlUrl":192},"references\u002Fgpt-image.md",6855,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FvargHQ\u002Fskills\u002Fcharacter-passport\u002Freferences\u002Fgpt-image.md",{"path":194,"resourceType":99,"resourceTypeDesc":100,"sizeBytes":195,"sourceHtmlUrl":196},"references\u002Fjudge-evidence.md",59495,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FvargHQ\u002Fskills\u002Fcharacter-passport\u002Freferences\u002Fjudge-evidence.md",{"path":198,"resourceType":99,"resourceTypeDesc":100,"sizeBytes":199,"sourceHtmlUrl":200},"references\u002Fjudge.md",8050,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FvargHQ\u002Fskills\u002Fcharacter-passport\u002Freferences\u002Fjudge.md",{"path":202,"resourceType":99,"resourceTypeDesc":100,"sizeBytes":203,"sourceHtmlUrl":204},"references\u002Fpassport.md",6273,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FvargHQ\u002Fskills\u002Fcharacter-passport\u002Freferences\u002Fpassport.md",{"path":206,"resourceType":99,"resourceTypeDesc":100,"sizeBytes":207,"sourceHtmlUrl":208},"references\u002Fpeople.md",27856,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FvargHQ\u002Fskills\u002Fcharacter-passport\u002Freferences\u002Fpeople.md",{"path":210,"resourceType":99,"resourceTypeDesc":100,"sizeBytes":211,"sourceHtmlUrl":212},"references\u002Fprops.md",5791,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FvargHQ\u002Fskills\u002Fcharacter-passport\u002Freferences\u002Fprops.md",{"path":214,"resourceType":99,"resourceTypeDesc":100,"sizeBytes":215,"sourceHtmlUrl":216},"references\u002Freference-sites.md",17951,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FvargHQ\u002Fskills\u002Fcharacter-passport\u002Freferences\u002Freference-sites.md",{"path":218,"resourceType":99,"resourceTypeDesc":100,"sizeBytes":219,"sourceHtmlUrl":220},"references\u002Fsheets.md",6168,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FvargHQ\u002Fskills\u002Fcharacter-passport\u002Freferences\u002Fsheets.md",{"path":222,"resourceType":99,"resourceTypeDesc":100,"sizeBytes":223,"sourceHtmlUrl":224},"references\u002Fvoice.md",6416,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FvargHQ\u002Fskills\u002Fcharacter-passport\u002Freferences\u002Fvoice.md",{"path":226,"resourceType":99,"resourceTypeDesc":100,"sizeBytes":227,"sourceHtmlUrl":228},"references\u002Fx-evidence.md",111653,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FvargHQ\u002Fskills\u002Fcharacter-passport\u002Freferences\u002Fx-evidence.md",{"path":230,"resourceType":105,"resourceTypeDesc":106,"sizeBytes":231,"sourceHtmlUrl":232},"scripts\u002Fcrop_sheet.py",1429,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FvargHQ\u002Fskills\u002Fcharacter-passport\u002Fscripts\u002Fcrop_sheet.py",{"path":234,"resourceType":105,"resourceTypeDesc":106,"sizeBytes":235,"sourceHtmlUrl":236},"scripts\u002Fface_check.py",11918,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FvargHQ\u002Fskills\u002Fcharacter-passport\u002Fscripts\u002Fface_check.py",{"path":238,"resourceType":105,"resourceTypeDesc":106,"sizeBytes":239,"sourceHtmlUrl":240},"scripts\u002Fjudge_agreement.py",2935,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FvargHQ\u002Fskills\u002Fcharacter-passport\u002Fscripts\u002Fjudge_agreement.py",{"path":242,"resourceType":105,"resourceTypeDesc":106,"sizeBytes":243,"sourceHtmlUrl":244},"scripts\u002Fprompt.py",4011,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FvargHQ\u002Fskills\u002Fcharacter-passport\u002Fscripts\u002Fprompt.py",{"path":246,"resourceType":105,"resourceTypeDesc":106,"sizeBytes":247,"sourceHtmlUrl":248},"scripts\u002Fvoice_check.py",2764,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FvargHQ\u002Fskills\u002Fcharacter-passport\u002Fscripts\u002Fvoice_check.py",[250,259,267,275,283,291],{"skillNo":251,"name":252,"nameZh":6,"description":253,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":254,"sourceHtmlUrl":255,"categories":256,"keywords":257,"publishedAt":258},"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":260,"name":261,"nameZh":6,"description":262,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":263,"sourceHtmlUrl":264,"categories":265,"keywords":266,"publishedAt":258},"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":268,"name":269,"nameZh":6,"description":270,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":271,"sourceHtmlUrl":272,"categories":273,"keywords":274,"publishedAt":258},"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":276,"name":277,"nameZh":6,"description":278,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":279,"sourceHtmlUrl":280,"categories":281,"keywords":282,"publishedAt":258},"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":284,"name":285,"nameZh":6,"description":286,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":287,"sourceHtmlUrl":288,"categories":289,"keywords":290,"publishedAt":258},"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":292,"name":293,"nameZh":6,"description":294,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":295,"sourceHtmlUrl":296,"categories":297,"keywords":298,"publishedAt":258},"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",[],[]]