[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M77K2RZQVT528ED39P3SABSA":3,"skill-same:01M77K2RZQVT528ED39P3SABSA":99},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":29,"commitSha":30,"skillDirectory":31,"forksCount":32,"repositoryHtmlUrl":33,"repositoryHomepageUrl":6,"ownerHtmlUrl":34,"ownerBlogUrl":35,"ownerDescription":36,"updatedAt":37,"install":38,"resources":50},"01M77K2RZQVT528ED39P3SABSA","rotoscope",null,"Drawing-by-drawing copy of a reference animation clip: decode it into distinct drawings, trace each to vector paths, render them through the ink.js brush engine, measure each against its source, and fit brush overrides until every drawing passes. Use when: 'rotoscope this', 'trace this clip', 'copy this animation one to one', 'replicate this video exactly', 'match the reference frame by frame', 'measure the replica against the source'. Not for an original film or a style study without a reference clip.","melodic-software\u002Fclaude-code-plugins","melodic-software","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F58273638?v=4","01M77JVQTXNGKCE4MDFY2BC936","Melodic Software","01M77JVQVN9QDWKAH6W03ANP76",30,"MIT","https:\u002F\u002Fgithub.com\u002Fmelodic-software\u002Fclaude-code-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fanimation\u002Fskills\u002Frotoscope\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\ndescription: \"Drawing-by-drawing copy of a reference animation clip: decode it into distinct drawings, trace each to vector paths, render them through the ink.js brush engine, measure each against its source, and fit brush overrides until every drawing passes. Use when: 'rotoscope this', 'trace this clip', 'copy this animation one to one', 'replicate this video exactly', 'match the reference frame by frame', 'measure the replica against the source'. Not for an original film or a style study without a reference clip.\"\nargument-hint: \"\u003Creference video> \u003Cwork dir>\"\nuser-invocable: true\ndisable-model-invocation: false\nmetadata:\n  workflow-stage: implement\n  summary: Trace, render, measure and fit a 1:1 replica of a reference animation\n---\n\n# Rotoscope\n\nProduce a measured 1:1 replica of a reference clip whose pixels come from traced paths and brush\nparameters only. Never replay or embed source bitmaps. Read\n[`reference\u002Fmethod.md`](reference\u002Fmethod.md) first: the defaults, why they hold, and the\ndiagnostics in the order to read them.\n\nRun every script as `python3 ${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fpydeps.py run --data-dir\n\"${CLAUDE_PLUGIN_DATA}\" -- \u003Cscript> ...`; it never installs a package, and a missing tool or\npackage stops it with exit 2 and one remedy line (`\u002Fanimation:setup` checks them all). Below, `$R`\nstands for `${CLAUDE_PLUGIN_ROOT}\u002Fskills\u002Frotoscope\u002Fscripts\u002F`.\n\n## Work directory\n\nOne work directory per reference clip, outside the plugin; it grows to hundreds of MB.\n\n| Path | Written by | Holds |\n|---|---|---|\n| `src\u002FdNNN.png`, `d\u002Findex.json` | `extract.py --video` | distinct drawings; size, duration, `[k, pts, t1]` |\n| `d\u002FdNNN.json` | `extract.py` | T-layer paths with holes, tone layers, colors, applied overrides |\n| `overrides.json` | you, `fit.py` | per-drawing parameters (below); survives re-extraction |\n| `out\u002F\u003Ctag>\u002F` | `measure.py`, `review.py` | replicas, heatmaps, `table-*.md`, `review-*.md`, `crops\u002F` |\n| `learnings.md` | `measure.py`, you | one line per run, plus your findings |\n\n## Override file\n\nTool-neutral JSON that carries every hand decision. Entries apply in file order to each drawing\nwhose `k` (an index or `[k0, k1]`) holds it; later entries win, and `brush` merges key by key.\n\n```json\n{\"overrides\": [\n  {\"k\": [0, 30], \"brush\": {\"bias\": 0.18, \"blur\": 0.7}, \"why\": \"sparse line art, replica too thin\"},\n  {\"k\": [203, 217], \"sharp\": [2.0, 0.6], \"levels\": [40, 80, 170, 215]},\n  {\"k\": [64, 74], \"tint\": true}\n]}\n```\n\n`brush` keys: `bias`, `blur`, `grain`, `tones` (see `roto.js`). `sharp` is the unsharp mask\n`[amount, sigma]` or `null`; `levels` are the tone gray levels; both retrace. `tint` adds\nwarm-paper layers. `why` is for the reader; the tools ignore it. Geometry never goes in this file:\na fix that needs hand-edited paths is a finding to report, not an override.\n\n## Loop\n\n1. Extract: `$R\u002Fextract.py \u003Cwork> --video \u003Cclip>`. After an override change,\n   `$R\u002Fextract.py \u003Cwork> --apply` retraces only drawings whose `sharp` or `levels` changed.\n2. Measure: `$R\u002Fmeasure.py \u003Cwork> [--only K0-K1] [--tag name] --playwright-core\n   '${user_config.playwright_core}'`. It exits 0 only when every drawing meets the `measure.py`\n   target (`reference\u002Fmethod.md`, Target). Run long ranges in the background.\n3. Fit: `$R\u002Ffit.py \u003Cwork> [--only K0-K1] --playwright-core '${user_config.playwright_core}'`\n   bisects `bias` per drawing from the replica-only \u002F source-only balance and appends the result to\n   `overrides.json`; apply it with `--apply`. It fits bias only: blur, sharpening and tone levels\n   are yours, guided by the diagnostics in `method.md`. On shfred0, fitting every drawing from the\n   default bias passes them all at a mean XOR 0.3% below the hand fits.\n4. Review: `$R\u002Freview.py \u003Cwork> \u003Ctag>` adds the manual checks as columns (largest one-color\n   cluster and whether it is a blob, frame-edge XOR, tone-tile difference, paper color) and writes\n   one 1:1 crop per drawing of its hottest window. Read every crop, not only the flagged ones: a\n   passing number can hide a visible defect such as a tint. Never downscale a crop or review a GIF.\n5. Record: append to `\u003Cwork>\u002Flearnings.md` what failed, the cause, the change and the before and\n   after numbers.\n\nRepeat 2-5 by shot or drawing range until the table passes and the crops show no one-color\ncluster.\n\nA film of the replica: `${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Frender.py $R\u002Froto.js \u003Cframes dir> --fps \u003Cthe\nsource's frame rate> --root \u003Cwork> --encode mp4 --playwright-core '${user_config.playwright_core}'`\nwrites the frames, `render.json` and `\u003Cframes dir>.mp4` beside them.\n\n## Retro\n\nAt the end of a clip, read `learnings.md` next to earlier runs' learnings. A finding that recurs\nacross shots or clips with the same fix (the same override on most drawings, the same diagnostic\nleading to the same change) becomes a default: change the constant in `extract.py` or\n`roto.js`, re-run the regression, and record the finding with its numbers in `method.md`. A one-off\nstays in the clip's override file.\n\n## Regression\n\nThe shfred0 study ships as a fixture (`fixtures\u002Fshfred0.overrides.json`, parameters only; the clip\nis not shipped). Given that clip and an empty work directory, `$R\u002Fregress.py \u003Cshfred0.mp4> \u003Cwork>`\nextracts with the fixture, renders and measures every drawing, checks the encoded replica against\nthe woodcut-ink pack, and exits 0 only when every drawing and the replica pass.\n`$R\u002Fregress.py --synthetic \u003Cwork>` needs no clip: it renders, encodes and re-traces\n`fixtures\u002Fsynthetic.js` and checks the render, encode and decode contracts. Run both after any\nchange to the scripts.\n\n## Next\n\n`\u002Fanimation:learn-style \u003Cwork dir> \u003Cpack dir>`\n\nIt measures this work directory's traces and drawings into a style pack.\n\n## Gotchas\n\n- `renderFrame(t)` and `renderDrawing(k)` return Promises; a capture that does not await them\n  saves the canvas before the drawing lands.\n- Chromium's canvas `blur()` filter does nothing below a floor (`reference\u002Fmethod.md`, Rendering,\n  holds the dated record), so `roto.js` blurs in JS; `gauss()` must not add 0.5 before writing to a\n  `Uint8ClampedArray`, which already rounds.\n- A drawing JSON is one line of 1-4 MB. Change parameters through the override file and `--apply`,\n  never by editing the JSON.\n- Gray XOR and SSIM cannot see color. Read `paper_err` and the crops for tints.\n- An all-ink or all-paper frame has a floor near 0.02%; a few hundred border pixels decide it, so\n  judge it by the ratio and the edge column, not by the XOR alone.\n","# Rotoscope\n\nProduce a measured 1:1 replica of a reference clip whose pixels come from traced paths and brush\nparameters only. Never replay or embed source bitmaps. Read\n[`reference\u002Fmethod.md`](reference\u002Fmethod.md) first: the defaults, why they hold, and the\ndiagnostics in the order to read them.\n\nRun every script as `python3 ${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fpydeps.py run --data-dir\n\"${CLAUDE_PLUGIN_DATA}\" -- \u003Cscript> ...`; it never installs a package, and a missing tool or\npackage stops it with exit 2 and one remedy line (`\u002Fanimation:setup` checks them all). Below, `$R`\nstands for `${CLAUDE_PLUGIN_ROOT}\u002Fskills\u002Frotoscope\u002Fscripts\u002F`.\n\n## Work directory\n\nOne work directory per reference clip, outside the plugin; it grows to hundreds of MB.\n\n| Path | Written by | Holds |\n|---|---|---|\n| `src\u002FdNNN.png`, `d\u002Findex.json` | `extract.py --video` | distinct drawings; size, duration, `[k, pts, t1]` |\n| `d\u002FdNNN.json` | `extract.py` | T-layer paths with holes, tone layers, colors, applied overrides |\n| `overrides.json` | you, `fit.py` | per-drawing parameters (below); survives re-extraction |\n| `out\u002F\u003Ctag>\u002F` | `measure.py`, `review.py` | replicas, heatmaps, `table-*.md`, `review-*.md`, `crops\u002F` |\n| `learnings.md` | `measure.py`, you | one line per run, plus your findings |\n\n## Override file\n\nTool-neutral JSON that carries every hand decision. Entries apply in file order to each drawing\nwhose `k` (an index or `[k0, k1]`) holds it; later entries win, and `brush` merges key by key.\n\n```json\n{\"overrides\": [\n  {\"k\": [0, 30], \"brush\": {\"bias\": 0.18, \"blur\": 0.7}, \"why\": \"sparse line art, replica too thin\"},\n  {\"k\": [203, 217], \"sharp\": [2.0, 0.6], \"levels\": [40, 80, 170, 215]},\n  {\"k\": [64, 74], \"tint\": true}\n]}\n```\n\n`brush` keys: `bias`, `blur`, `grain`, `tones` (see `roto.js`). `sharp` is the unsharp mask\n`[amount, sigma]` or `null`; `levels` are the tone gray levels; both retrace. `tint` adds\nwarm-paper layers. `why` is for the reader; the tools ignore it. Geometry never goes in this file:\na fix that needs hand-edited paths is a finding to report, not an override.\n\n## Loop\n\n1. Extract: `$R\u002Fextract.py \u003Cwork> --video \u003Cclip>`. After an override change,\n   `$R\u002Fextract.py \u003Cwork> --apply` retraces only drawings whose `sharp` or `levels` changed.\n2. Measure: `$R\u002Fmeasure.py \u003Cwork> [--only K0-K1] [--tag name] --playwright-core\n   '${user_config.playwright_core}'`. It exits 0 only when every drawing meets the `measure.py`\n   target (`reference\u002Fmethod.md`, Target). Run long ranges in the background.\n3. Fit: `$R\u002Ffit.py \u003Cwork> [--only K0-K1] --playwright-core '${user_config.playwright_core}'`\n   bisects `bias` per drawing from the replica-only \u002F source-only balance and appends the result to\n   `overrides.json`; apply it with `--apply`. It fits bias only: blur, sharpening and tone levels\n   are yours, guided by the diagnostics in `method.md`. On shfred0, fitting every drawing from the\n   default bias passes them all at a mean XOR 0.3% below the hand fits.\n4. Review: `$R\u002Freview.py \u003Cwork> \u003Ctag>` adds the manual checks as columns (largest one-color\n   cluster and whether it is a blob, frame-edge XOR, tone-tile difference, paper color) and writes\n   one 1:1 crop per drawing of its hottest window. Read every crop, not only the flagged ones: a\n   passing number can hide a visible defect such as a tint. Never downscale a crop or review a GIF.\n5. Record: append to `\u003Cwork>\u002Flearnings.md` what failed, the cause, the change and the before and\n   after numbers.\n\nRepeat 2-5 by shot or drawing range until the table passes and the crops show no one-color\ncluster.\n\nA film of the replica: `${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Frender.py $R\u002Froto.js \u003Cframes dir> --fps \u003Cthe\nsource's frame rate> --root \u003Cwork> --encode mp4 --playwright-core '${user_config.playwright_core}'`\nwrites the frames, `render.json` and `\u003Cframes dir>.mp4` beside them.\n\n## Retro\n\nAt the end of a clip, read `learnings.md` next to earlier runs' learnings. A finding that recurs\nacross shots or clips with the same fix (the same override on most drawings, the same diagnostic\nleading to the same change) becomes a default: change the constant in `extract.py` or\n`roto.js`, re-run the regression, and record the finding with its numbers in `method.md`. A one-off\nstays in the clip's override file.\n\n## Regression\n\nThe shfred0 study ships as a fixture (`fixtures\u002Fshfred0.overrides.json`, parameters only; the clip\nis not shipped). Given that clip and an empty work directory, `$R\u002Fregress.py \u003Cshfred0.mp4> \u003Cwork>`\nextracts with the fixture, renders and measures every drawing, checks the encoded replica against\nthe woodcut-ink pack, and exits 0 only when every drawing and the replica pass.\n`$R\u002Fregress.py --synthetic \u003Cwork>` needs no clip: it renders, encodes and re-traces\n`fixtures\u002Fsynthetic.js` and checks the render, encode and decode contracts. Run both after any\nchange to the scripts.\n\n## Next\n\n`\u002Fanimation:learn-style \u003Cwork dir> \u003Cpack dir>`\n\nIt measures this work directory's traces and drawings into a style pack.\n\n## Gotchas\n\n- `renderFrame(t)` and `renderDrawing(k)` return Promises; a capture that does not await them\n  saves the canvas before the drawing lands.\n- Chromium's canvas `blur()` filter does nothing below a floor (`reference\u002Fmethod.md`, Rendering,\n  holds the dated record), so `roto.js` blurs in JS; `gauss()` must not add 0.5 before writing to a\n  `Uint8ClampedArray`, which already rounds.\n- A drawing JSON is one line of 1-4 MB. Change parameters through the override file and `--apply`,\n  never by editing the JSON.\n- Gray XOR and SSIM cannot see color. Read `paper_err` and the crops for tints.\n- An all-ink or all-paper frame has a floor near 0.02%; a few hundred border pixels decide it, so\n  judge it by the ratio and the edge column, not by the XOR alone.\n",{"metadata":24,"description":7,"argument-hint":27,"user-invocable":28,"disable-model-invocation":20},{"summary":25,"workflow-stage":26},"Trace, render, measure and fit a 1:1 replica of a reference animation","implement","\u003Creference video> \u003Cwork dir>",true,"main","d0e68c3f36b92a1d6381f0ba0060d7a0b8b886c5","plugins\u002Fanimation\u002Fskills\u002Frotoscope",7,"https:\u002F\u002Fgithub.com\u002Fmelodic-software\u002Fclaude-code-plugins","https:\u002F\u002Fgithub.com\u002Fmelodic-software","https:\u002F\u002Fmelodicsoftware.com","Independent software studio building developer tools, automation, and application services, with roots in music.","2026-11-15 05:15:06",{"source":8,"skillName":5,"commands":39,"prompt":49,"zipAvailable":28},[40,43,46],{"tool":41,"command":42},"npx","npx skills add melodic-software\u002Fclaude-code-plugins --skill rotoscope",{"tool":44,"command":45},"bunx","bunx skills add melodic-software\u002Fclaude-code-plugins --skill rotoscope",{"tool":47,"command":48},"pnpm","pnpm dlx skills add melodic-software\u002Fclaude-code-plugins --skill rotoscope","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fmelodic-software\u002Fclaude-code-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fanimation\u002Fskills\u002Frotoscope\u002FSKILL.md",[51,57,63,67,71,75,79,83,87,91,95],{"path":52,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":55,"sourceHtmlUrl":56},"fixtures\u002Fshfred0.overrides.json","REFERENCE","参考文档",1426,"https:\u002F\u002Fgithub.com\u002Fmelodic-software\u002Fclaude-code-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fanimation\u002Fskills\u002Frotoscope\u002Ffixtures\u002Fshfred0.overrides.json",{"path":58,"resourceType":59,"resourceTypeDesc":60,"sizeBytes":61,"sourceHtmlUrl":62},"fixtures\u002Fsynthetic.js","SCRIPT","脚本",1474,"https:\u002F\u002Fgithub.com\u002Fmelodic-software\u002Fclaude-code-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fanimation\u002Fskills\u002Frotoscope\u002Ffixtures\u002Fsynthetic.js",{"path":64,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":65,"sourceHtmlUrl":66},"reference\u002Fmethod.md",7273,"https:\u002F\u002Fgithub.com\u002Fmelodic-software\u002Fclaude-code-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fanimation\u002Fskills\u002Frotoscope\u002Freference\u002Fmethod.md",{"path":68,"resourceType":59,"resourceTypeDesc":60,"sizeBytes":69,"sourceHtmlUrl":70},"scripts\u002Fbrush.json",40,"https:\u002F\u002Fgithub.com\u002Fmelodic-software\u002Fclaude-code-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fanimation\u002Fskills\u002Frotoscope\u002Fscripts\u002Fbrush.json",{"path":72,"resourceType":59,"resourceTypeDesc":60,"sizeBytes":73,"sourceHtmlUrl":74},"scripts\u002Fextract.py",10069,"https:\u002F\u002Fgithub.com\u002Fmelodic-software\u002Fclaude-code-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fanimation\u002Fskills\u002Frotoscope\u002Fscripts\u002Fextract.py",{"path":76,"resourceType":59,"resourceTypeDesc":60,"sizeBytes":77,"sourceHtmlUrl":78},"scripts\u002Ffit.py",5217,"https:\u002F\u002Fgithub.com\u002Fmelodic-software\u002Fclaude-code-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fanimation\u002Fskills\u002Frotoscope\u002Fscripts\u002Ffit.py",{"path":80,"resourceType":59,"resourceTypeDesc":60,"sizeBytes":81,"sourceHtmlUrl":82},"scripts\u002Fmeasure.py",7677,"https:\u002F\u002Fgithub.com\u002Fmelodic-software\u002Fclaude-code-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fanimation\u002Fskills\u002Frotoscope\u002Fscripts\u002Fmeasure.py",{"path":84,"resourceType":59,"resourceTypeDesc":60,"sizeBytes":85,"sourceHtmlUrl":86},"scripts\u002Fregress.py",8876,"https:\u002F\u002Fgithub.com\u002Fmelodic-software\u002Fclaude-code-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fanimation\u002Fskills\u002Frotoscope\u002Fscripts\u002Fregress.py",{"path":88,"resourceType":59,"resourceTypeDesc":60,"sizeBytes":89,"sourceHtmlUrl":90},"scripts\u002Freview.py",5396,"https:\u002F\u002Fgithub.com\u002Fmelodic-software\u002Fclaude-code-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fanimation\u002Fskills\u002Frotoscope\u002Fscripts\u002Freview.py",{"path":92,"resourceType":59,"resourceTypeDesc":60,"sizeBytes":93,"sourceHtmlUrl":94},"scripts\u002Froto.js",5018,"https:\u002F\u002Fgithub.com\u002Fmelodic-software\u002Fclaude-code-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fanimation\u002Fskills\u002Frotoscope\u002Fscripts\u002Froto.js",{"path":96,"resourceType":59,"resourceTypeDesc":60,"sizeBytes":97,"sourceHtmlUrl":98},"scripts\u002Ftest_regress.py",1275,"https:\u002F\u002Fgithub.com\u002Fmelodic-software\u002Fclaude-code-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fanimation\u002Fskills\u002Frotoscope\u002Fscripts\u002Ftest_regress.py",[100,107,114,121,126,133],{"skillNo":101,"name":102,"nameZh":6,"description":103,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":104,"categories":105,"keywords":106,"publishedAt":19},"01M7DYYDG31B9YX7N9MB9QW2GW","track","Backlog reads through the bound tracker: search open and closed items, view one item with its comments and state history. Use when another skill searches or reads tracker items.","https:\u002F\u002Fgithub.com\u002Fmelodic-software\u002Fclaude-code-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fsession-flow\u002Fevals\u002Frecall-still-reports-reopened-bug\u002Fwork-items-stub\u002Fskills\u002Ftrack\u002FSKILL.md",[],[],{"skillNo":108,"name":109,"nameZh":6,"description":110,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":111,"categories":112,"keywords":113,"publishedAt":19},"01M7DYXVBAVG3NV30PA7GKW9Q6","reviewer-media","Reviewer media for one pull request: decides whether it needs a narrated walkthrough, builds the storyboard from \u002Freview:explain-change's digest, has \u002Fexplainer-video:produce render it and hands the manifest to \u002Fsource-control:pull-request media. Use when asked for 'reviewer media', 'a walkthrough video for this PR', 'a produced video of this change', or when pull-request ready or monitor hands a PR over.","https:\u002F\u002Fgithub.com\u002Fmelodic-software\u002Fclaude-code-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Freview\u002Fskills\u002Freviewer-media\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":6,"sourceHtmlUrl":118,"categories":119,"keywords":120,"publishedAt":19},"01M7DYRZ5YD44AMYH26YR25GZ8","route","Model and effort per agent role (orchestrator, worker, verifier, retrieval) for a multi-agent run, resolved through the bundled defaults and the user, team and personal override config layers into fenced JSON with single-agent and fan-out variants and the layer behind each value. Use when asked 'which model for the subagents', 'route the roles' or 'model routing', or before a skill passes a role's model on a spawn.","https:\u002F\u002Fgithub.com\u002Fmelodic-software\u002Fclaude-code-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fdiscovery\u002Fevals\u002Fex-model-pin-without-override\u002Fmulti-agent-stub\u002Fskills\u002Froute\u002FSKILL.md",[],[],{"skillNo":122,"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":6,"sourceHtmlUrl":123,"categories":124,"keywords":125,"publishedAt":19},"01M7DYRTVT4FWTGDJY0HCCFJMZ","https:\u002F\u002Fgithub.com\u002Fmelodic-software\u002Fclaude-code-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fdiscovery\u002Fevals\u002Fex-model-override-from-route\u002Fmulti-agent-stub\u002Fskills\u002Froute\u002FSKILL.md",[],[],{"skillNo":127,"name":128,"nameZh":6,"description":129,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":130,"categories":131,"keywords":132,"publishedAt":19},"01M7DYNZC8PNW3T27V2ADKECKJ","principles","Module-design vocabulary for architecture findings, and the checks built on it. Use when: 'what is a deep module', 'what is a seam', 'deep vs shallow module', 'what is the deletion test', 'leverage and locality', 'module design vocabulary', 'which word do we use for X in architecture findings'. Scanning a codebase for friction is \u002Farchitecture:improve.","https:\u002F\u002Fgithub.com\u002Fmelodic-software\u002Fclaude-code-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Farchitecture\u002Fskills\u002Fprinciples\u002FSKILL.md",[],[],{"skillNo":134,"name":135,"nameZh":6,"description":136,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":137,"categories":138,"keywords":139,"publishedAt":19},"01M7DYNMCZNEWBFHV9KTSS6H60","write","Structured five-field bug report (title, steps to reproduce, expected vs actual, justified severity, suggested fix location) from an informal description, read-only. Use when the user names a defect they observed, or asks for one written up ('report a bug', 'file a bug', 'write this up as a bug').","https:\u002F\u002Fgithub.com\u002Fmelodic-software\u002Fclaude-code-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Farchitecture\u002Fevals\u002Fdeepening-defect-goes-to-bugs-write\u002Fbugs-stub\u002Fskills\u002Fwrite\u002FSKILL.md",[],[]]