[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6DBJ6ESBC0RGEPSFTA36ZHT":3,"skill-same:01M6DBJ6ESBC0RGEPSFTA36ZHT":63},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":38,"linkOnly":39,"markdownContent":40,"markdownBody":41,"frontMatter":42,"refName":43,"commitSha":44,"skillDirectory":45,"forksCount":14,"repositoryHtmlUrl":46,"repositoryHomepageUrl":6,"ownerHtmlUrl":47,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":48,"install":49,"resources":62},"01M6DBJ6ESBC0RGEPSFTA36ZHT","media-dub",null,"Use when producing a local DUB of a video - re-voicing speech into another language (or restyling it same-language) while KEEPING the original speaker's voice, fully offline. Safe-ship engine is Chatterbox-Multilingual (Resemble AI, MIT, 23-lang zero-shot clone); rides media_studio (ASR, CTC word-alignment, ffmpeg atempo duration-fit, ducking, mux). NOT for pure TTS (use speech).","Prekzursil\u002Fagent-skills-toolchain","Prekzursil","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F54636077?v=4","01M6DACZ1PCQHD99SCR1YXG28B","Andrei Mihai Visalon","01M6DACZ670WZF535V3WYYSS4Z",0,"MIT","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fmedia-dub\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37],"media dub","Media","voice","ffmpeg","local","language","multilingual","alignment","use","engine","Word","safe","tts","ship","Video","ASR","ZeRO","offline","speech","2026-11-10 10:12:30",false,"---\nname: media-dub\ndescription: Use when producing a local DUB of a video - re-voicing speech into another language (or restyling it same-language) while KEEPING the original speaker's voice, fully offline. Safe-ship engine is Chatterbox-Multilingual (Resemble AI, MIT, 23-lang zero-shot clone); rides media_studio (ASR, CTC word-alignment, ffmpeg atempo duration-fit, ducking, mux). NOT for pure TTS (use speech).\n---\n# media-dub — local voice-clone dubbing (Chatterbox safe ship)\n\nDistilled from the REAL implementation. Cite these when in doubt:\n\n- `media_studio\u002Ffeatures\u002Fdub.py` — the whole feature: the `dub.start` RPC, the\n  `DubLicenseGate` (SHADOW), `build_dub_plan`, the `atempo` fit, the VO-timeline\n  and duck\u002Fmux argv builders, and `run_dub_pipeline` (the end-to-end orchestrator).\n- Substrate it RIDES (do not reinvent) — from the media_studio package\n  (`sidecar\u002Fmedia_studio\u002Ffeatures\u002F` in the Reframe checkout):\n  - `transcribe.py` \u002F `parakeet_asr.py` — ASR to the §3 `Transcript` schema.\n  - `ctc_align.py` — karaoke-grade word-timing refinement (optional 2nd pass).\n  - `audiomix.py` — the `sidechaincompress` -> `amix` -> `loudnorm` duck\u002Fmux graph\n    (`build_mix_filter`); the dub mux uses the identical convention + labels.\n\nEvidence: gem-hunt MASTER **E.3** — \"Local dubbing stack — biggest missing flagship\nfeature: Chatterbox-Multilingual (MIT, 23-lang clone) + IndexTTS2 duration-control\n+ optional LatentSync lip-sync; the whole substrate (Parakeet+CTC+ducking+mux)\nexists. *[verify IndexTTS2 weights license before commercial embed; Chatterbox\nalone is the safe ship.]*\" · COUNCIL **C5** (risk-tiered SHADOW ladder — a\nheuristic\u002Fnagging\u002Fblocking gate ships observe-and-log FIRST).\n\n## Wire surface (NET-NEW)\n\n```\ndub.start({videoId|path, targetLang, sourceLang?, engine?, durationFit?,\n           lipsync?, posture?, allowGated?, bgPath?})\n    -> {jobId} -> {path, engine, durationFit, lipsync, targetLang,\n                   sourceLang, segments, license, notices}\n```\n\nA long job: returns `{jobId}` immediately, streams `job.progress`, and the final\n`job.done.result` carries the output path + the license receipt.\n\n- `targetLang` (required) — ISO-639-1 (e.g. `es`, `de`, `ja`).\n- `engine` — `chatterbox` (default, safe) | `indextts2` (gated).\n- `lipsync` — `latentsync` (gated) | omit.\n- `posture` — `personal` (default; local\u002Fnon-commercial) | `commercial`.\n- `allowGated` — owner opt-in to keep a gated engine under a commercial posture.\n- `bgPath` — an optional music\u002Fambient bed ducked UNDER the new VO.\n\n## Pipeline (ride the bus)\n\n1. **ASR** — `transcribe_fn(in_path, settings)` -> §3 `Transcript`\n   (`{language, durationSec, segments:[{start,end,text,words?,speaker?}]}`).\n2. **align** *(optional)* — `align_fn(transcript)` refines word timings via\n   `ctc_align`; a miss degrades to segment timings (never raises).\n3. **translate** *(optional)* — `translate_fn(text, targetLang, sourceLang)` per\n   segment; ABSENT -> `target_text = source_text` (same-language voice re-read).\n4. **synthesize** — `synth_fn(text, lang, speaker, target_sec, engine, out_path)`\n   -> `(wav_path, synth_sec)`. Chatterbox clones the source speaker and speaks the\n   target text. `target_sec` is a duration HINT the native engine (IndexTTS2)\n   honors; the timestretch path fits afterward.\n5. **duration-fit** — land each clip in its source slot:\n   - `timestretch` (Chatterbox-only, SAFE): `atempo_factor(synth_sec, slot_sec)`\n     = `synth_sec \u002F slot_sec`, clamped to `[0.5, 2.0]`; `build_atempo_chain`\n     decomposes a factor outside `[0.5, 2.0]` into in-range stages (a single\n     `atempo` is linear only in that range). A factor within `±0.02` of 1.0 is\n     left untouched (no needless re-encode).\n   - `native` (IndexTTS2, GATED): trust the synth duration (the engine already\n     hit the target) — better quality, no time-stretch artifacts.\n6. **assemble** — `build_vo_timeline_argv` places every fitted clip at its source\n   start on ONE full-length VO track: a silent `anullsrc` base of `durationSec`,\n   each clip `adelay`-ed to its start (ms, stereo), all summed with\n   `amix=...:normalize=0` (nothing auto-attenuated).\n7. **duck + mux** — `build_dub_mux_argv` stream-copies the source VIDEO\n   (`-map 0:v -c:v copy`) and rebuilds the audio: the VO is `loudnorm`-ed to the\n   target LUFS; with a `bgPath` the bed is ducked under the VO via\n   `sidechaincompress` keyed off the VO (the exact `audiomix` convention).\n8. **lip-sync** *(optional, GATED)* — LatentSync re-renders the mouth to match the\n   dub. Commercial embed gated on `dub-license`.\n\n## License gate — SHADOW mode (the crux)\n\n`Chatterbox-Multilingual is MIT` -> commercial-safe, the DEFAULT, always admitted.\n`IndexTTS2` and `LatentSync` weights are **not confirmed commercial-safe** -> a\ncommercial embed routes to the **`dub-license`** needsDecision.\n\n`DubLicenseGate.evaluate(requested, posture)` is **advisory (SHADOW)**:\n- it is PURE and NEVER raises, blocks, or nags;\n- it returns a `LicenseVerdict` (`admitted` \u002F `gated` \u002F `needsDecision` \u002F\n  `decisionId=\"dub-license\"`) and LOGS it to a bounded, injected `shadow_log`\n  sink (production points this at a separate auto-rotating sink — never the main\n  event ledger, per C5(iii));\n- `personal` posture admits every engine (local\u002Fnon-commercial use of the gated\n  weights is unrestricted); `commercial` posture flags the gated engines.\n\n`build_dub_plan` uses the verdict only to pick a DEFAULT: under `commercial`\nWITHOUT `allowGated` a gated engine is downgraded to Chatterbox + timestretch and\na notice is recorded — the gate never forces this, the plan just defaults safe.\nWith `allowGated` the owner's choice is honored and the needsDecision is STILL\nrecorded for them. This is \"observe + log, never block.\"\n\n## Chatterbox's 23 languages\n\n`ar da de el en es fi fr he hi it ja ko ms nl no pl pt ru sv sw tr zh`\n(verify against the Resemble AI model card at wire time). A target outside this\nset emits a LOUD notice (never a silent wrong-language dub). **Romanian (`ro`) is\nNOT in the set** — Parakeet can ASR it, but Chatterbox cannot yet synthesize it.\n\n## Assets to install (follow-on, out of the single-file build)\n\n- `chatterbox-multilingual` (MIT) — the safe-ship TTS weights + the\n  `dub_backend.RealChatterboxSynth` loader (the heavy `synth_fn` seam).\n- `indextts2` \u002F `latentsync` — install ONLY after the `dub-license` decision\n  resolves them for a commercial embed.\n\n## Pitfalls that actually bite\n\n- **argv-list only, never `shell=True`** — the filter graph + paths are single\n  argv elements (CONTRACTS discipline).\n- **`atempo` linear range** — one `atempo` only works in `[0.5, 2.0]`; always go\n  through `build_atempo_chain` for larger stretches or you get an ffmpeg error.\n- **Don't strip the original background** — the safe ship REPLACES the speech with\n  the dub VO and optionally ducks a provided bed under it; separating the original\n  speaker's voice from music (source separation) is a heavier, separate step — do\n  not claim it's done here.\n- **Slot overflow** — if a translation is much longer than its slot the clamp to\n  2.0x leaves the clip slightly overrunning the next; the fit notice surfaces it.\n  Prefer IndexTTS2 native fit (once licensed) for tight lip timing.\n- **Shadow sink must never break the dub** — `_observe` swallows a sink failure;\n  a logging outage can't fail a render.\n\n## When NOT to use\n\n- Pure narration with no source voice to clone -> `speech`.\n- Muxing an already-finished dub\u002FVO track -> `audio-extract-mix`.\n- Transcription \u002F subtitles only -> `transcribe` \u002F `caption-burn`.\n- Trimming dead air \u002F silence -> `silence-trim`.\n","# media-dub — local voice-clone dubbing (Chatterbox safe ship)\n\nDistilled from the REAL implementation. Cite these when in doubt:\n\n- `media_studio\u002Ffeatures\u002Fdub.py` — the whole feature: the `dub.start` RPC, the\n  `DubLicenseGate` (SHADOW), `build_dub_plan`, the `atempo` fit, the VO-timeline\n  and duck\u002Fmux argv builders, and `run_dub_pipeline` (the end-to-end orchestrator).\n- Substrate it RIDES (do not reinvent) — from the media_studio package\n  (`sidecar\u002Fmedia_studio\u002Ffeatures\u002F` in the Reframe checkout):\n  - `transcribe.py` \u002F `parakeet_asr.py` — ASR to the §3 `Transcript` schema.\n  - `ctc_align.py` — karaoke-grade word-timing refinement (optional 2nd pass).\n  - `audiomix.py` — the `sidechaincompress` -> `amix` -> `loudnorm` duck\u002Fmux graph\n    (`build_mix_filter`); the dub mux uses the identical convention + labels.\n\nEvidence: gem-hunt MASTER **E.3** — \"Local dubbing stack — biggest missing flagship\nfeature: Chatterbox-Multilingual (MIT, 23-lang clone) + IndexTTS2 duration-control\n+ optional LatentSync lip-sync; the whole substrate (Parakeet+CTC+ducking+mux)\nexists. *[verify IndexTTS2 weights license before commercial embed; Chatterbox\nalone is the safe ship.]*\" · COUNCIL **C5** (risk-tiered SHADOW ladder — a\nheuristic\u002Fnagging\u002Fblocking gate ships observe-and-log FIRST).\n\n## Wire surface (NET-NEW)\n\n```\ndub.start({videoId|path, targetLang, sourceLang?, engine?, durationFit?,\n           lipsync?, posture?, allowGated?, bgPath?})\n    -> {jobId} -> {path, engine, durationFit, lipsync, targetLang,\n                   sourceLang, segments, license, notices}\n```\n\nA long job: returns `{jobId}` immediately, streams `job.progress`, and the final\n`job.done.result` carries the output path + the license receipt.\n\n- `targetLang` (required) — ISO-639-1 (e.g. `es`, `de`, `ja`).\n- `engine` — `chatterbox` (default, safe) | `indextts2` (gated).\n- `lipsync` — `latentsync` (gated) | omit.\n- `posture` — `personal` (default; local\u002Fnon-commercial) | `commercial`.\n- `allowGated` — owner opt-in to keep a gated engine under a commercial posture.\n- `bgPath` — an optional music\u002Fambient bed ducked UNDER the new VO.\n\n## Pipeline (ride the bus)\n\n1. **ASR** — `transcribe_fn(in_path, settings)` -> §3 `Transcript`\n   (`{language, durationSec, segments:[{start,end,text,words?,speaker?}]}`).\n2. **align** *(optional)* — `align_fn(transcript)` refines word timings via\n   `ctc_align`; a miss degrades to segment timings (never raises).\n3. **translate** *(optional)* — `translate_fn(text, targetLang, sourceLang)` per\n   segment; ABSENT -> `target_text = source_text` (same-language voice re-read).\n4. **synthesize** — `synth_fn(text, lang, speaker, target_sec, engine, out_path)`\n   -> `(wav_path, synth_sec)`. Chatterbox clones the source speaker and speaks the\n   target text. `target_sec` is a duration HINT the native engine (IndexTTS2)\n   honors; the timestretch path fits afterward.\n5. **duration-fit** — land each clip in its source slot:\n   - `timestretch` (Chatterbox-only, SAFE): `atempo_factor(synth_sec, slot_sec)`\n     = `synth_sec \u002F slot_sec`, clamped to `[0.5, 2.0]`; `build_atempo_chain`\n     decomposes a factor outside `[0.5, 2.0]` into in-range stages (a single\n     `atempo` is linear only in that range). A factor within `±0.02` of 1.0 is\n     left untouched (no needless re-encode).\n   - `native` (IndexTTS2, GATED): trust the synth duration (the engine already\n     hit the target) — better quality, no time-stretch artifacts.\n6. **assemble** — `build_vo_timeline_argv` places every fitted clip at its source\n   start on ONE full-length VO track: a silent `anullsrc` base of `durationSec`,\n   each clip `adelay`-ed to its start (ms, stereo), all summed with\n   `amix=...:normalize=0` (nothing auto-attenuated).\n7. **duck + mux** — `build_dub_mux_argv` stream-copies the source VIDEO\n   (`-map 0:v -c:v copy`) and rebuilds the audio: the VO is `loudnorm`-ed to the\n   target LUFS; with a `bgPath` the bed is ducked under the VO via\n   `sidechaincompress` keyed off the VO (the exact `audiomix` convention).\n8. **lip-sync** *(optional, GATED)* — LatentSync re-renders the mouth to match the\n   dub. Commercial embed gated on `dub-license`.\n\n## License gate — SHADOW mode (the crux)\n\n`Chatterbox-Multilingual is MIT` -> commercial-safe, the DEFAULT, always admitted.\n`IndexTTS2` and `LatentSync` weights are **not confirmed commercial-safe** -> a\ncommercial embed routes to the **`dub-license`** needsDecision.\n\n`DubLicenseGate.evaluate(requested, posture)` is **advisory (SHADOW)**:\n- it is PURE and NEVER raises, blocks, or nags;\n- it returns a `LicenseVerdict` (`admitted` \u002F `gated` \u002F `needsDecision` \u002F\n  `decisionId=\"dub-license\"`) and LOGS it to a bounded, injected `shadow_log`\n  sink (production points this at a separate auto-rotating sink — never the main\n  event ledger, per C5(iii));\n- `personal` posture admits every engine (local\u002Fnon-commercial use of the gated\n  weights is unrestricted); `commercial` posture flags the gated engines.\n\n`build_dub_plan` uses the verdict only to pick a DEFAULT: under `commercial`\nWITHOUT `allowGated` a gated engine is downgraded to Chatterbox + timestretch and\na notice is recorded — the gate never forces this, the plan just defaults safe.\nWith `allowGated` the owner's choice is honored and the needsDecision is STILL\nrecorded for them. This is \"observe + log, never block.\"\n\n## Chatterbox's 23 languages\n\n`ar da de el en es fi fr he hi it ja ko ms nl no pl pt ru sv sw tr zh`\n(verify against the Resemble AI model card at wire time). A target outside this\nset emits a LOUD notice (never a silent wrong-language dub). **Romanian (`ro`) is\nNOT in the set** — Parakeet can ASR it, but Chatterbox cannot yet synthesize it.\n\n## Assets to install (follow-on, out of the single-file build)\n\n- `chatterbox-multilingual` (MIT) — the safe-ship TTS weights + the\n  `dub_backend.RealChatterboxSynth` loader (the heavy `synth_fn` seam).\n- `indextts2` \u002F `latentsync` — install ONLY after the `dub-license` decision\n  resolves them for a commercial embed.\n\n## Pitfalls that actually bite\n\n- **argv-list only, never `shell=True`** — the filter graph + paths are single\n  argv elements (CONTRACTS discipline).\n- **`atempo` linear range** — one `atempo` only works in `[0.5, 2.0]`; always go\n  through `build_atempo_chain` for larger stretches or you get an ffmpeg error.\n- **Don't strip the original background** — the safe ship REPLACES the speech with\n  the dub VO and optionally ducks a provided bed under it; separating the original\n  speaker's voice from music (source separation) is a heavier, separate step — do\n  not claim it's done here.\n- **Slot overflow** — if a translation is much longer than its slot the clamp to\n  2.0x leaves the clip slightly overrunning the next; the fit notice surfaces it.\n  Prefer IndexTTS2 native fit (once licensed) for tight lip timing.\n- **Shadow sink must never break the dub** — `_observe` swallows a sink failure;\n  a logging outage can't fail a render.\n\n## When NOT to use\n\n- Pure narration with no source voice to clone -> `speech`.\n- Muxing an already-finished dub\u002FVO track -> `audio-extract-mix`.\n- Transcription \u002F subtitles only -> `transcribe` \u002F `caption-burn`.\n- Trimming dead air \u002F silence -> `silence-trim`.\n",{"name":5,"description":7},"main","a298c929b6cbd662e1fce54302ce520d5ceea1a5",".agents\u002Fskills\u002Fmedia-dub","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain","https:\u002F\u002Fgithub.com\u002FPrekzursil","2026-11-02 14:30:57",{"source":8,"skillName":5,"commands":50,"prompt":60,"zipAvailable":61},[51,54,57],{"tool":52,"command":53},"npx","npx skills add Prekzursil\u002Fagent-skills-toolchain --skill media-dub",{"tool":55,"command":56},"bunx","bunx skills add Prekzursil\u002Fagent-skills-toolchain --skill media-dub",{"tool":58,"command":59},"pnpm","pnpm dlx skills add Prekzursil\u002Fagent-skills-toolchain --skill media-dub","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fmedia-dub\u002FSKILL.md",true,[],[64,85,115,142,156,172],{"skillNo":65,"name":66,"nameZh":6,"description":67,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":68,"categories":69,"keywords":70,"publishedAt":38},"01M6DF7D7478R55P46REYH4QAC","clarify-requirements","Resolve genuine pre-execution ambiguity by scanning repo context, generating 1-6 grounded options, and asking 1-3 focused questions via AskUserQuestion. NOT for mid-task use (injection risk); NOT when the goal is already unambiguous; use to disambiguate vague prompts before any file edits.","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Fworkspace-hooks\u002Fskills\u002Fclarify-requirements\u002FSKILL.md",[],[71,72,73,74,75,76,77,78,79,27,80,81,82,83,84],"clarify requirements","clarify","requirements","risk","options","task","prompts","goal","scanning","context","repo","injection","execution","file",{"skillNo":86,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":89,"categories":90,"keywords":96,"publishedAt":38},"01M6DF79CA4BHJS66J8EZDBPWJ","openmm-md","Run FREE, open-source, Windows-native GPU molecular dynamics via the openmm-md MCP (OpenMM + CUDA on the local NVIDIA GPU). Use for protein \u002F protein-ligand MD when you want a free stack or are on Windows without a Schrodinger license. Covers the full workflow (prepare, solvate, minimize, equilibrate, production, analyze, mmgbsa) AND an honest decision guide vs Schrodinger Desmond, including how to run Desmond legitimately on Linux or a cloud GPU with a real license. This is a deliberately LESSER free alternative and does NOT replace the schrodinger MCP tools. Do NOT use it to pick a free tool when a validated FEP+, WaterMap, IFD-MD, or Prime MM-GBSA result is actually required.","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Fmcp\u002Fopenmm-md-mcp\u002Fskill\u002Fopenmm-md\u002FSKILL.md",[91],{"categoryNo":92,"categoryName":93,"taxonomyType":94,"taxonomyTypeDesc":95},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[97,98,99,100,101,102,103,104,105,106,107,108,109,110,27,111,112,23,113,114],"openmm md","how","decision","pick","linux","analyze","tool","stack","open","NVIDIA","gpu","license","workflow","windows","free","molecular dynamics","do","MCP",{"skillNo":116,"name":117,"nameZh":6,"description":118,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":119,"categories":120,"keywords":127,"publishedAt":38},"01M6DF76C1MG85VEWP8VZCBNMN","visual-review","Take screenshots of web pages and UI using Playwright for visual review and iteration","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Feditor\u002Fmetaswarm\u002Fskills\u002Fvisual-review\u002FSKILL.md",[121,124],{"categoryNo":122,"categoryName":123,"taxonomyType":94,"taxonomyTypeDesc":95},"01JBSEEDCAT000000000000003","演示文稿",{"categoryNo":125,"categoryName":126,"taxonomyType":94,"taxonomyTypeDesc":95},"01JBSEEDCAT000000000000008","测试与质量",[128,129,130,131,132,133,134,135,136,137,98,138,139,140,141],"review","visual","visual review","pages","web","false","iteration","take","check","slides","ui","screenshot","playwright","screenshots",{"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":6,"sourceHtmlUrl":146,"categories":147,"keywords":148,"publishedAt":38},"01M6DF73AQVCBZKEN0YXEX9FXP","status","Diagnostic status report — shows metaswarm installation state, project setup, and potential issues","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Feditor\u002Fmetaswarm\u002Fskills\u002Fstatus\u002FSKILL.md",[],[144,149,150,151,152,153,154,155],"setup","report","project","installation","project setup","issues","state",{"skillNo":157,"name":158,"nameZh":6,"description":159,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":160,"categories":161,"keywords":163,"publishedAt":38},"01M6DF6X6C2XB0P6GX76P7TTYV","start","Use when starting work on any task, when the user mentions metaswarm, or when the user wants to begin tracked development work","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Feditor\u002Fmetaswarm\u002Fskills\u002Fstart\u002FSKILL.md",[162],{"categoryNo":92,"categoryName":93,"taxonomyType":94,"taxonomyTypeDesc":95},[158,164,76,165,166,167,27,168,169,170,171],"start issue","issue","ready","work on issue","user","work","work on","development",{"skillNo":173,"name":149,"nameZh":6,"description":174,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":175,"categories":176,"keywords":177,"publishedAt":38},"01M6DF6QMJ9AJKFKHHKRT005PQ","Interactive project setup — detects your project, configures metaswarm, writes project-local files","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Feditor\u002Fmetaswarm\u002Fskills\u002Fsetup\u002FSKILL.md",[],[149,151,23,178,153,179],"files","interactive"]