[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6MNFFVAEK6ZDXNCAPW8NN2K":3,"skill-same:01M6MNFFVAEK6ZDXNCAPW8NN2K":88},{"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":26,"publishedAt":49,"linkOnly":50,"markdownContent":51,"markdownBody":52,"frontMatter":53,"refName":64,"commitSha":65,"skillDirectory":66,"forksCount":67,"repositoryHtmlUrl":68,"repositoryHomepageUrl":69,"ownerHtmlUrl":70,"ownerBlogUrl":71,"ownerDescription":72,"updatedAt":73,"install":74,"resources":87},"01M6MNFFVAEK6ZDXNCAPW8NN2K","kling-4-keyframe-film",null,"Make a cinematic short film, music video or story video with Kling 4 the way it works best: beat sheet, a cast and look reference, every key shot made as a still on GPT Image 2.5, then one 30-second Kling 4 reference-to-video take per beat from two to four stills and a short prompt, then cut the usable seconds like live-action takes. Includes the still prompt template (\"Image 1 is the man to match exactly…\"), the take prompt, dialogue scenes, a fix pass for faces and hands, costs and the varg calls. Use when someone wants a short film, music video, Halloween or holiday film, comedy sketch, trailer or narrative scene made with Kling 4 (kling_v4), asks how to get cinematic Kling 4 results, or says their Kling 4 output looks like AI slop. For prompt rules only use kling-4-prompting; for a single action montage use kling-4-action-montage.","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\u002Fkling-4-keyframe-film\u002FSKILL.md",[18,23],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000016","图像与多媒体","SCENARIO","使用场景",{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",[27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48],"kling","kling 4 keyframe film","FiLM","man","when","music video","slop","narrative","how to","join","cut","MCP","get","only","fix","short","template","Bash","how","Video","api","image","2026-11-10 10:12:30",false,"---\nname: kling-4-keyframe-film\ndescription: >-\n  Make a cinematic short film, music video or story video with Kling 4 the way it works best:\n  beat sheet, a cast and look reference, every key shot made as a still on GPT Image 2.5, then one\n  30-second Kling 4 reference-to-video take per beat from two to four stills and a short prompt,\n  then cut the usable seconds like live-action takes. Includes the still prompt template (\"Image 1\n  is the man to match exactly…\"), the take prompt, dialogue scenes, a fix pass for faces and\n  hands, costs and the varg calls. Use when someone wants a short film, music video, Halloween or\n  holiday film, comedy sketch, trailer or narrative scene made with Kling 4 (kling_v4), asks how\n  to get cinematic Kling 4 results, or says their Kling 4 output looks like AI slop. For prompt\n  rules only use kling-4-prompting; for a single action montage use kling-4-action-montage.\nlicense: MIT\nmetadata:\n  author: vargHQ\n  version: \"1.0.0\"\n  openclaw:\n    requires:\n      anyBins:\n        - curl\n    homepage: https:\u002F\u002Fvarg.ai\u002Fhow-to\ncompatibility: >-\n  Needs a VARG_API_KEY with curl (see the varg-ai skill) or the varg MCP connection\n  (https:\u002F\u002Fmcp.varg.ai\u002Fmcp). ffmpeg to cut and join takes.\nallowed-tools: Bash(curl:*) Bash(jq:*) Bash(ffmpeg:*) Bash(ffprobe:*) Read Write Edit\n---\n\n# A short film with Kling 4: stills first, 30-second takes, cut like live action\n\nKling 4 animates well and badly frames shots it invents. So the image model does the cinematography and Kling 4 does the acting, motion, voices and the in-between. This is how fal's Kling 4 Halloween music video was made ([YouTube, 2026-10-30](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=WzXKggH-0Io)): about 18 key stills on GPT Image 2.5, mostly 30-second Kling 4 takes at 1080p 21:9, then an edit that kept the best seconds of each. Prompt rules and the failure table live in `kling-4-prompting`.\n\nGeneration runs on varg: REST `https:\u002F\u002Fapi.varg.ai\u002Fv2` (the `varg-ai` skill) or the MCP server `https:\u002F\u002Fmcp.varg.ai\u002Fmcp`. Price every take first (`POST \u002Fv2\u002Festimate` or `estimate_cost` with `\"model\": \"kling_v4\"`).\n\n## 1. Ask, then go\n\n- **Story:** 3–6 beats, one sentence each (setup, joke or turn, action, payoff, button line). A 60–90 s film is 3–6 takes.\n- **Cast:** a photo or sheet per character (`varg-character-design`), the outfit written as a list of details.\n- **Place:** a real, named location if possible (\"Washington Square Park\", \"the Brooklyn Banks\"). GPT Image 2.5 researches real places well, which Kling 4 text-to-video does not.\n- **Look:** aspect ratio (21:9 for cinema, 9:16 for social), lens (ultra-wide fisheye, 35 mm, telephoto), film stock and grade, grain, motion blur. One look image (a frame you like) used as \"reference only for color grade\".\n- **Budget:** a 30 s take at 1080p ≈ $7.05 (705 credits); at 720p about two thirds of that. Plan 2–4 takes per beat.\n\n## 2. Key stills on GPT Image 2.5\n\nOne still per moment Kling must hit: the opening of each beat, any shot with a specific angle (over-the-shoulder, overhead), the peak of an action, the end state. Template:\n\n```\nCinematic \u003C21:9> film still, \u003Cangle>, \u003Clens and distortion>.\nUse the \u003CN> reference images: Image 1 is \u003Cperson> to match exactly: \u003Cface, hair, glasses,\ncap, top with text, trousers, shoes>. Image 2 is \u003Cperson> to match exactly: \u003C…>.\nImage 3 is a reference only for \u003Cthe bike \u002F the prop> (do NOT show \u003Cwhat to leave out>).\nImage 4 is a reference only for color grade, \u003Cfilm stock> tone, grain and motion blur; do not\ninclude its people.\n\nScene: \u003Cwho is where doing what, in the present tense, mid-motion, with blur on what moves>.\n\u003CBackground people, blurred, at the frame edges>. \u003CLight>.\n\u003CFilm look> like Image 4: \u003Chighlight color>, \u003Cshadow color>, deep blacks, coarse grain, motion\nblur. Avoid text overlays, clean digital look, \u003Cwrong props>, \u003Cwrong time of day>.\n```\n\n```bash\ncurl -s -X POST https:\u002F\u002Fapi.varg.ai\u002Fv2\u002Ftools\u002Fimage\u002Fcall -H \"Authorization: Bearer $VARG_API_KEY\" \\\n  -H \"Content-Type: application\u002Fjson\" -d '{\"model\":\"gpt_image_2_5\",\"prompt\":\"\u003Cstill prompt>\",\n  \"files\":[{\"url\":\"CAST_1\"},{\"url\":\"CAST_2\"},{\"url\":\"PROP\"},{\"url\":\"LOOK\"}],\"aspect_ratio\":\"21:9\"}'\n```\n\n- Check each still before you animate: hands, the bike or board, faces against the cast photos. A warped object in a still becomes the worst part of the take.\n- Block the scene across stills so it makes sense in time: if he walks past her in still 1, he is on her other side in still 2.\n- Make the second angle of a dialogue (the over-the-shoulder) as a still too; do not leave it to Kling.\n\n## 3. One take per beat\n\nPin the reference route (with plain `kling_v4`, two files become start and end frame and a third is not used):\n\n```bash\ncurl -s -X POST https:\u002F\u002Fapi.varg.ai\u002Fv2\u002Ftools\u002Fvideo\u002Fcall -H \"Authorization: Bearer $VARG_API_KEY\" \\\n  -H \"Content-Type: application\u002Fjson\" -d '{\n  \"model\": \"fal:fal-ai\u002Fkling-video\u002Fv4\u002Freference-to-video\",\n  \"prompt\": \"\u003Cbeat prompt>\",\n  \"files\": [{\"url\":\"STILL_A\"},{\"url\":\"STILL_B\"},{\"url\":\"STILL_C\"}],\n  \"aspect_ratio\": \"21:9\", \"resolution\": \"1080p\", \"duration\": 30, \"audio\": true}'\n```\n\nThe beat prompt is short: what happens in order, the line in quotes, the camera event, the look, the length.\n\n```\n21:9 the man walks by the woman as she places a white pumpkin on the table. the man says\n\"what does the white one do?\" she smiles and smashes the white pumpkin on the top of the man's\nhead with both hands. The camera shakes and falls to the ground and fades to black. handheld\nshaky 16mm documentary style footage. 15 seconds.\n```\n\n- Order matters when you need it: use `provider_options.fal.multi_prompt` with seconds per shot (see `kling-4-prompting`). Keep each take in one place; a location change is a new take, cut in the edit.\n- Dialogue: Kling 4 makes the voice itself. For the same voice in every take, make an element with a `voice_id` (front photo + 1–3 more angles) and write `@Element1 says \"…\"`.\n- Action: add \"No slow motion, everything moves at real speed, motion blur.\"\n- Draft at 720p; rerun the chosen take at 1080p with the same stills and prompt.\n\n## 4. Cut it like live action\n\nA 30 s take holds several cuts, retries of the same move and a ramp-up. Watch it at full speed, mark the 2–6 s pieces that work (a clean landing, a good line read, a new angle you did not ask for) and drop the rest. From the film: \"I ended up using the ending part of it\", \"we used that double tail whip… that's the crash we used\", \"this shot made the final cut\".\n\n```bash\nffmpeg -ss 12.4 -to 17.9 -i take3.mp4 -c:v libx264 -crf 16 -c:a aac piece_07.mp4\nprintf \"file '%s'\\n\" piece_*.mp4 > list.txt && ffmpeg -f concat -safe 0 -i list.txt -c copy film.mp4\n```\n\nLay the music last over the whole cut (`varg-music-video` for beat-synced cuts).\n\n## 5. Fix pass\n\n| Problem in a take | Fix |\n|---|---|\n| A close-up changed someone's face | \"Same sequence, add this reference of what she looks like\" + her photo; for a lasting lock make her an element with 2–4 photos. |\n| An element job fails at once | The element has one photo. Add more angles (or the same photo twice as a last resort). |\n| Shots Kling invented look softer and more \"AI\" | Make that shot as a still too, or use it only as a short bridge. |\n| A trick or dance move is nonsense | Rerun, or add a real reference clip of the move as `@Video1` (3–30 s). |\n| Wrong lens on an invented shot | Name the lens for that shot. |\n| Odd behaviour in the background crowd | Cut around it; keep crowds blurred at the frame edges in the stills. |\n\n## 6. Kling 4 or Seedance 2.5?\n\nWith the same pre-made stills, references and lighting, they are \"very comparable\"; Kling 4 is sharper and does 30 s takes with dialogue, Seedance 2.5 does better with only sheets and a long prompt. Pick Kling 4 when you have (or will make) the stills; pick Seedance 2.5 when you want the video model to invent the shots.\n\n## Example plan (60 s, 21:9)\n\n| Beat | Stills (GPT Image 2.5) | Take |\n|---|---|---|\n| Setup + joke line | wide: he walks past her stall; OTS on her | 15 s dialogue, camera falls, fade to black |\n| Action 1 | 3 dance poses in the crowd ring | 30 s, \"everyone bobs their heads\", shaky handheld |\n| Action 2 | rider between cabs, overhead, steam | 30 s, \"no slow motion, high speed, motion blur\" |\n| Climax + button | 3 tricks + the crash with her helping him up | 30 s, tricks, crash, her line in quotes |\n\nAbout 13 stills (≈ $3) and 4 takes at 1080p (≈ $26), more for retries; keep 60 s.\n\n## Related skills\n\n`kling-4-prompting` (inputs, prompt rules, failure table), `kling-4-action-montage`, `varg-character-design`, `varg-consistent-characters`, `varg-music-video`, `varg-ai`.\n","# A short film with Kling 4: stills first, 30-second takes, cut like live action\n\nKling 4 animates well and badly frames shots it invents. So the image model does the cinematography and Kling 4 does the acting, motion, voices and the in-between. This is how fal's Kling 4 Halloween music video was made ([YouTube, 2026-10-30](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=WzXKggH-0Io)): about 18 key stills on GPT Image 2.5, mostly 30-second Kling 4 takes at 1080p 21:9, then an edit that kept the best seconds of each. Prompt rules and the failure table live in `kling-4-prompting`.\n\nGeneration runs on varg: REST `https:\u002F\u002Fapi.varg.ai\u002Fv2` (the `varg-ai` skill) or the MCP server `https:\u002F\u002Fmcp.varg.ai\u002Fmcp`. Price every take first (`POST \u002Fv2\u002Festimate` or `estimate_cost` with `\"model\": \"kling_v4\"`).\n\n## 1. Ask, then go\n\n- **Story:** 3–6 beats, one sentence each (setup, joke or turn, action, payoff, button line). A 60–90 s film is 3–6 takes.\n- **Cast:** a photo or sheet per character (`varg-character-design`), the outfit written as a list of details.\n- **Place:** a real, named location if possible (\"Washington Square Park\", \"the Brooklyn Banks\"). GPT Image 2.5 researches real places well, which Kling 4 text-to-video does not.\n- **Look:** aspect ratio (21:9 for cinema, 9:16 for social), lens (ultra-wide fisheye, 35 mm, telephoto), film stock and grade, grain, motion blur. One look image (a frame you like) used as \"reference only for color grade\".\n- **Budget:** a 30 s take at 1080p ≈ $7.05 (705 credits); at 720p about two thirds of that. Plan 2–4 takes per beat.\n\n## 2. Key stills on GPT Image 2.5\n\nOne still per moment Kling must hit: the opening of each beat, any shot with a specific angle (over-the-shoulder, overhead), the peak of an action, the end state. Template:\n\n```\nCinematic \u003C21:9> film still, \u003Cangle>, \u003Clens and distortion>.\nUse the \u003CN> reference images: Image 1 is \u003Cperson> to match exactly: \u003Cface, hair, glasses,\ncap, top with text, trousers, shoes>. Image 2 is \u003Cperson> to match exactly: \u003C…>.\nImage 3 is a reference only for \u003Cthe bike \u002F the prop> (do NOT show \u003Cwhat to leave out>).\nImage 4 is a reference only for color grade, \u003Cfilm stock> tone, grain and motion blur; do not\ninclude its people.\n\nScene: \u003Cwho is where doing what, in the present tense, mid-motion, with blur on what moves>.\n\u003CBackground people, blurred, at the frame edges>. \u003CLight>.\n\u003CFilm look> like Image 4: \u003Chighlight color>, \u003Cshadow color>, deep blacks, coarse grain, motion\nblur. Avoid text overlays, clean digital look, \u003Cwrong props>, \u003Cwrong time of day>.\n```\n\n```bash\ncurl -s -X POST https:\u002F\u002Fapi.varg.ai\u002Fv2\u002Ftools\u002Fimage\u002Fcall -H \"Authorization: Bearer $VARG_API_KEY\" \\\n  -H \"Content-Type: application\u002Fjson\" -d '{\"model\":\"gpt_image_2_5\",\"prompt\":\"\u003Cstill prompt>\",\n  \"files\":[{\"url\":\"CAST_1\"},{\"url\":\"CAST_2\"},{\"url\":\"PROP\"},{\"url\":\"LOOK\"}],\"aspect_ratio\":\"21:9\"}'\n```\n\n- Check each still before you animate: hands, the bike or board, faces against the cast photos. A warped object in a still becomes the worst part of the take.\n- Block the scene across stills so it makes sense in time: if he walks past her in still 1, he is on her other side in still 2.\n- Make the second angle of a dialogue (the over-the-shoulder) as a still too; do not leave it to Kling.\n\n## 3. One take per beat\n\nPin the reference route (with plain `kling_v4`, two files become start and end frame and a third is not used):\n\n```bash\ncurl -s -X POST https:\u002F\u002Fapi.varg.ai\u002Fv2\u002Ftools\u002Fvideo\u002Fcall -H \"Authorization: Bearer $VARG_API_KEY\" \\\n  -H \"Content-Type: application\u002Fjson\" -d '{\n  \"model\": \"fal:fal-ai\u002Fkling-video\u002Fv4\u002Freference-to-video\",\n  \"prompt\": \"\u003Cbeat prompt>\",\n  \"files\": [{\"url\":\"STILL_A\"},{\"url\":\"STILL_B\"},{\"url\":\"STILL_C\"}],\n  \"aspect_ratio\": \"21:9\", \"resolution\": \"1080p\", \"duration\": 30, \"audio\": true}'\n```\n\nThe beat prompt is short: what happens in order, the line in quotes, the camera event, the look, the length.\n\n```\n21:9 the man walks by the woman as she places a white pumpkin on the table. the man says\n\"what does the white one do?\" she smiles and smashes the white pumpkin on the top of the man's\nhead with both hands. The camera shakes and falls to the ground and fades to black. handheld\nshaky 16mm documentary style footage. 15 seconds.\n```\n\n- Order matters when you need it: use `provider_options.fal.multi_prompt` with seconds per shot (see `kling-4-prompting`). Keep each take in one place; a location change is a new take, cut in the edit.\n- Dialogue: Kling 4 makes the voice itself. For the same voice in every take, make an element with a `voice_id` (front photo + 1–3 more angles) and write `@Element1 says \"…\"`.\n- Action: add \"No slow motion, everything moves at real speed, motion blur.\"\n- Draft at 720p; rerun the chosen take at 1080p with the same stills and prompt.\n\n## 4. Cut it like live action\n\nA 30 s take holds several cuts, retries of the same move and a ramp-up. Watch it at full speed, mark the 2–6 s pieces that work (a clean landing, a good line read, a new angle you did not ask for) and drop the rest. From the film: \"I ended up using the ending part of it\", \"we used that double tail whip… that's the crash we used\", \"this shot made the final cut\".\n\n```bash\nffmpeg -ss 12.4 -to 17.9 -i take3.mp4 -c:v libx264 -crf 16 -c:a aac piece_07.mp4\nprintf \"file '%s'\\n\" piece_*.mp4 > list.txt && ffmpeg -f concat -safe 0 -i list.txt -c copy film.mp4\n```\n\nLay the music last over the whole cut (`varg-music-video` for beat-synced cuts).\n\n## 5. Fix pass\n\n| Problem in a take | Fix |\n|---|---|\n| A close-up changed someone's face | \"Same sequence, add this reference of what she looks like\" + her photo; for a lasting lock make her an element with 2–4 photos. |\n| An element job fails at once | The element has one photo. Add more angles (or the same photo twice as a last resort). |\n| Shots Kling invented look softer and more \"AI\" | Make that shot as a still too, or use it only as a short bridge. |\n| A trick or dance move is nonsense | Rerun, or add a real reference clip of the move as `@Video1` (3–30 s). |\n| Wrong lens on an invented shot | Name the lens for that shot. |\n| Odd behaviour in the background crowd | Cut around it; keep crowds blurred at the frame edges in the stills. |\n\n## 6. Kling 4 or Seedance 2.5?\n\nWith the same pre-made stills, references and lighting, they are \"very comparable\"; Kling 4 is sharper and does 30 s takes with dialogue, Seedance 2.5 does better with only sheets and a long prompt. Pick Kling 4 when you have (or will make) the stills; pick Seedance 2.5 when you want the video model to invent the shots.\n\n## Example plan (60 s, 21:9)\n\n| Beat | Stills (GPT Image 2.5) | Take |\n|---|---|---|\n| Setup + joke line | wide: he walks past her stall; OTS on her | 15 s dialogue, camera falls, fade to black |\n| Action 1 | 3 dance poses in the crowd ring | 30 s, \"everyone bobs their heads\", shaky handheld |\n| Action 2 | rider between cabs, overhead, steam | 30 s, \"no slow motion, high speed, motion blur\" |\n| Climax + button | 3 tricks + the crash with her helping him up | 30 s, tricks, crash, her line in quotes |\n\nAbout 13 stills (≈ $3) and 4 takes at 1080p (≈ $26), more for retries; keep 60 s.\n\n## Related skills\n\n`kling-4-prompting` (inputs, prompt rules, failure table), `kling-4-action-montage`, `varg-character-design`, `varg-consistent-characters`, `varg-music-video`, `varg-ai`.\n",{"name":5,"license":15,"metadata":54,"description":7,"allowed-tools":62,"compatibility":63},{"author":55,"version":56,"openclaw":57},"vargHQ","1.0.0",{"homepage":58,"requires":59},"https:\u002F\u002Fvarg.ai\u002Fhow-to",{"anyBins":60},[61],"curl","Bash(curl:*) Bash(jq:*) Bash(ffmpeg:*) Bash(ffprobe:*) Read Write Edit","Needs a VARG_API_KEY with curl (see the varg-ai skill) or the varg MCP connection (https:\u002F\u002Fmcp.varg.ai\u002Fmcp). ffmpeg to cut and join takes.","main","2b63f856ce19c2a797929cacabd9e0fc936812fa","plugins\u002FvargHQ\u002Fskills\u002Fkling-4-keyframe-film",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 kling-4-keyframe-film",{"tool":80,"command":81},"bunx","bunx skills add hashgraph-online\u002Fawesome-codex-plugins --skill kling-4-keyframe-film",{"tool":83,"command":84},"pnpm","pnpm dlx skills add hashgraph-online\u002Fawesome-codex-plugins --skill kling-4-keyframe-film","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FvargHQ\u002Fskills\u002Fkling-4-keyframe-film\u002FSKILL.md",true,[],[89,98,106,114,122,130],{"skillNo":90,"name":91,"nameZh":6,"description":92,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":93,"sourceHtmlUrl":94,"categories":95,"keywords":96,"publishedAt":97},"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":99,"name":100,"nameZh":6,"description":101,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":102,"sourceHtmlUrl":103,"categories":104,"keywords":105,"publishedAt":97},"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":107,"name":108,"nameZh":6,"description":109,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":110,"sourceHtmlUrl":111,"categories":112,"keywords":113,"publishedAt":97},"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":115,"name":116,"nameZh":6,"description":117,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":118,"sourceHtmlUrl":119,"categories":120,"keywords":121,"publishedAt":97},"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":123,"name":124,"nameZh":6,"description":125,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":126,"sourceHtmlUrl":127,"categories":128,"keywords":129,"publishedAt":97},"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":131,"name":132,"nameZh":6,"description":133,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":134,"sourceHtmlUrl":135,"categories":136,"keywords":137,"publishedAt":97},"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",[],[]]