[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M77K2FWHQ492K7A91Z7VDPNA":3,"skill-same:01M77K2FWHQ492K7A91Z7VDPNA":67},{"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},"01M77K2FWHQ492K7A91Z7VDPNA","learn-style",null,"Style pack from a rotoscoped clip: measure its traces and drawings into knob values and statistic bands, prove the bands against adversarial controls, and check new scenes against the pack. Use when: 'learn this style', 'make a style pack', 'extract the style from this clip', 'does my film match the style', 'check this scene against the woodcut pack', 'which statistics separate styles'. Needs a rotoscope work dir; not for copying a clip one to one.","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\u002Flearn-style\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\ndescription: \"Style pack from a rotoscoped clip: measure its traces and drawings into knob values and statistic bands, prove the bands against adversarial controls, and check new scenes against the pack. Use when: 'learn this style', 'make a style pack', 'extract the style from this clip', 'does my film match the style', 'check this scene against the woodcut pack', 'which statistics separate styles'. Needs a rotoscope work dir; not for copying a clip one to one.\"\nargument-hint: \"\u003Crotoscope work dir> \u003Cpack dir> [--cuts T,T,..] [--credit TEXT] [--negative SUMMARY.json ...]\"\nuser-invocable: true\ndisable-model-invocation: false\nmetadata:\n  workflow-stage: implement\n  summary: Measure a traced clip into a style pack and check new scenes against it\n---\n\n# Learn style\n\nTurn a rotoscoped clip into a style pack: the numbers that make the style what it is, and a check\nthat tells whether a new film shares them. The pack holds statistics only; never copy traced\ngeometry, source frames or the clip into it. Read\n[`reference\u002Fstatistics.md`](reference\u002Fstatistics.md) first: what each statistic measures, how a\nband is set, which statistics separate the woodcut style from a filtered near miss and from other\nstyles, and what the check still cannot separate.\n\nRun each script as `python3 ${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fpydeps.py run --data-dir \"${CLAUDE_PLUGIN_DATA}\" -- \u003Cscript> ...`, alone as its own Bash call: no `cd`, no `--help` run first, and no other command chained to it; this page gives each script's arguments.\nNever probe the host Python, `numpy` or `cv2`, never run `pydeps.py install`, and never list, create or read anything under `${CLAUDE_PLUGIN_DATA}` yourself: `pydeps.py run` finds the packages, and when it exits 2 it prints the repair line, which you report (`\u002Fanimation:setup` checks the requirements). Input is a\nrotoscope work directory (`d\u002FdNNN.json` traces and `src\u002FdNNN.png` drawings). The scripts are\n`${CLAUDE_PLUGIN_ROOT}\u002Fskills\u002Flearn-style\u002Fscripts\u002Flearn.py`,\n`${CLAUDE_PLUGIN_ROOT}\u002Fskills\u002Flearn-style\u002Fscripts\u002Fcontrols.py` and the shared\n`${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Finkstats.py`.\n\n## Pack format\n\n`styles\u002F\u003Cname>\u002F` in the plugin, tool-neutral:\n\n| File | Written by | Holds |\n|---|---|---|\n| `style.json` | `learn.py`, then you | `palette` (ink, paper, tone ramp), `knobs` (the seven-knob schema), `stats` (p10\u002Fp50\u002Fp90), `timing`, `ref` (the source's values), `bands`, `check`, `measured_only`, `heldout` (how each band was set and how it tested), `brush`, `credit`, `rotoscope_fits` |\n| `STYLE.md` | you | the style in words for a reader: credit, knob table with each value marked measured or judgment and pointing at its `style.json` key, how to author in it, the validation result |\n\n`learn.py` measures everything but `credit`, `brush` and the `movement`, `camera` and\n`backgrounds` knobs, which it keeps from an existing `style.json`; fill those knobs from viewing\nthe source and mark them `\"basis\": \"judgment\"`. `check` is `learn.py`'s `CHECK`, the statistics\nshown to separate, less any content-class row the source defines in fewer than two parts;\n`measured_only` lists the subject-sensitive statistics the check prints but never judges. The\nnumbers live in `style.json` only; STYLE.md and other docs point at its keys. Read a pack's `style.json` with the Read tool by absolute path, never with `python3 -c`, `cat`, `jq` or `ls` in a shell.\n\n## Loop\n\n1. Controls: `controls.py measure \u003Cout> --near \u003Ca near-miss film> --other \u003Cfilms in other styles>\n   --source \u003Cthe clip> --replica \u003Crotoscope work dir>` measures a filtered family of the near miss\n   (blur, noise, stripes, dry brush, contour warp), synthetic flat polygons, the other styles, and\n   the same-style positives, alternating the controls between a calibration and an evaluation half.\n2. Learn: `learn.py \u003Cwork> \u003Cpack dir> --cuts \u003Cthe clip's shot starts> --credit \"\u003Cwho made the\n   source, its URL, date>\" --negative \u003Cout>\u002Fcalibration\u002F*.json`. Bands come from film-sized\n   excerpts of the source, split by shot, with half the splits held out; the calibration controls\n   cap each band's widening so they keep failing.\n3. Prove the check: `controls.py check \u003Cout> \u003Cpack dir>` must show every control failing (margin\n   above 0) and the source and replica passing, with the evaluation half held out. Then\n   `controls.py selftest \u003Cpack dir> --near \u003Cthe near-miss film>` (the pack argument is required)\n   must exit 0. Put the table in `reference\u002Fstatistics.md`. A control that passes goes under \"what\n   the check cannot say\"; never narrow a band until it fails.\n4. Describe: fill the judgment knobs in `style.json` and write `STYLE.md`.\n5. Validate: author a scene of at least a third of the source's length (bands are learned from\n   excerpts that long) on a different subject,\n   from ink.js and the scene elements, with geometry you write, never traced; pass the pack's\n   `palette.ink` as every ink.js call's `color` (the engine's `INK` default is not the pack's).\n   Render it at the source's size with `${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Frender.py \u003Cscene.js> \u003Cframes\n   dir> --fps \u003Cthe pack's knobs.frame_rate.base_fps> --encode mp4 --playwright-core\n   '${user_config.playwright_core}'` (it serves the scene's folder and `scripts\u002F`), and run\n   `inkstats.py \u003Cframes dir>.mp4 --cuts \u003Cshot starts> --pack \u003Cpack dir>`. A produce production\n   passes its `shots.json` as `--cuts`. It exits 0 only when every checked row and the palette\n   pass. Each row prints its distance to source (0 is the source value, 1 the band edge on either side); the\n   film's distance ranks passing scenes and its margin names the row nearest failing.\n6. Review: measure each prop with `--region X,Y,W,H --t T0-T1` next to source prop boxes, then\n   read every drawing at 1:1 (tile frames so no image is over the long-edge limit\n   `${CLAUDE_PLUGIN_ROOT}\u002Fskills\u002Frotoscope\u002Freference\u002Fmethod.md`, Reviewing images, records; never\n   downscale, never a GIF) beside source crops. A pass on the numbers with a crop that does not\n   read as the style is a fail; say which mark is wrong.\n7. Record: put the parameters that passed into the pack's `brush` and the result into `STYLE.md`,\n   including where the scene still falls short.\n\nRepeat 5-7 until the check passes and the crops read as the style. Tune the scene against the\ncheck, never the check against the scene. `inkstats.py` with no pack (`--json` for the full\nsummary) measures any film, which is how to compare two films.\n\n## Next\n\n\u002Fanimation:produce \u003Cproduction dir>\n\nIt takes a style pack this skill wrote and makes the film: boards for approval, then shots,\nrender, and review.\n\n## Gotchas\n\n- A post filter must not be what passes the check. Blur, noise, stripes and dry-brush overlays move\n  edge softness and the amount of gray inside the ink, so those rows are measured but not checked.\n  `grain` and `period` are measured only: on the woodcut source they follow codec residue and the\n  pixel grid, and a flat black through h264 lands in `grain`'s band. `flat` rejects texture laid\n  over all the black, and `rough` and `offstep` do not move under blur, noise, stripes or dry brush.\n  `controls.py selftest \u003Cpack dir> [--near \u003Cfilm>]` exits 1 if the review's blur-and-stripes filter\n  (and, with `--near`, the warped, retimed `ATTACK`) gets a synthetic or near-miss film through;\n  rerun it with `--near` after changing a statistic.\n- `straight` and `sliver` follow the subject, so they are checked only inside the content classes\n  `border` and `caption` (`straight_border`, `sliver_caption`, ...) and printed as measured only over\n  the whole frame. `boil` is measured on the border and caption. A scene without a frame line or a\n  caption panel in the top quarter leaves those rows n\u002Fa; draw both, as the source does.\n- Bands are learned per excerpt of the whole source, not per shot, so a very short film is judged\n  against bands that may not fit it; there is no per-shot row.\n- `w50` and `pw50` come from a distance transform and move in 2 px steps; every woodcut source\n  excerpt has `pw50` 8, so neither is checked.\n- A strictly regular timing fails `offstep`: hold a few drawings for 2 or 4 frames.\n- `soft` needs a soften pass after drawing, since a two-tone canvas render has almost no edge ramp.\n  Chromium's `ctx.filter = 'blur()'` does nothing below a floor\n  (`${CLAUDE_PLUGIN_ROOT}\u002Fskills\u002Frotoscope\u002Freference\u002Fmethod.md`, Rendering, holds the dated\n  record); soften in JS instead.\n","# Learn style\n\nTurn a rotoscoped clip into a style pack: the numbers that make the style what it is, and a check\nthat tells whether a new film shares them. The pack holds statistics only; never copy traced\ngeometry, source frames or the clip into it. Read\n[`reference\u002Fstatistics.md`](reference\u002Fstatistics.md) first: what each statistic measures, how a\nband is set, which statistics separate the woodcut style from a filtered near miss and from other\nstyles, and what the check still cannot separate.\n\nRun each script as `python3 ${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fpydeps.py run --data-dir \"${CLAUDE_PLUGIN_DATA}\" -- \u003Cscript> ...`, alone as its own Bash call: no `cd`, no `--help` run first, and no other command chained to it; this page gives each script's arguments.\nNever probe the host Python, `numpy` or `cv2`, never run `pydeps.py install`, and never list, create or read anything under `${CLAUDE_PLUGIN_DATA}` yourself: `pydeps.py run` finds the packages, and when it exits 2 it prints the repair line, which you report (`\u002Fanimation:setup` checks the requirements). Input is a\nrotoscope work directory (`d\u002FdNNN.json` traces and `src\u002FdNNN.png` drawings). The scripts are\n`${CLAUDE_PLUGIN_ROOT}\u002Fskills\u002Flearn-style\u002Fscripts\u002Flearn.py`,\n`${CLAUDE_PLUGIN_ROOT}\u002Fskills\u002Flearn-style\u002Fscripts\u002Fcontrols.py` and the shared\n`${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Finkstats.py`.\n\n## Pack format\n\n`styles\u002F\u003Cname>\u002F` in the plugin, tool-neutral:\n\n| File | Written by | Holds |\n|---|---|---|\n| `style.json` | `learn.py`, then you | `palette` (ink, paper, tone ramp), `knobs` (the seven-knob schema), `stats` (p10\u002Fp50\u002Fp90), `timing`, `ref` (the source's values), `bands`, `check`, `measured_only`, `heldout` (how each band was set and how it tested), `brush`, `credit`, `rotoscope_fits` |\n| `STYLE.md` | you | the style in words for a reader: credit, knob table with each value marked measured or judgment and pointing at its `style.json` key, how to author in it, the validation result |\n\n`learn.py` measures everything but `credit`, `brush` and the `movement`, `camera` and\n`backgrounds` knobs, which it keeps from an existing `style.json`; fill those knobs from viewing\nthe source and mark them `\"basis\": \"judgment\"`. `check` is `learn.py`'s `CHECK`, the statistics\nshown to separate, less any content-class row the source defines in fewer than two parts;\n`measured_only` lists the subject-sensitive statistics the check prints but never judges. The\nnumbers live in `style.json` only; STYLE.md and other docs point at its keys. Read a pack's `style.json` with the Read tool by absolute path, never with `python3 -c`, `cat`, `jq` or `ls` in a shell.\n\n## Loop\n\n1. Controls: `controls.py measure \u003Cout> --near \u003Ca near-miss film> --other \u003Cfilms in other styles>\n   --source \u003Cthe clip> --replica \u003Crotoscope work dir>` measures a filtered family of the near miss\n   (blur, noise, stripes, dry brush, contour warp), synthetic flat polygons, the other styles, and\n   the same-style positives, alternating the controls between a calibration and an evaluation half.\n2. Learn: `learn.py \u003Cwork> \u003Cpack dir> --cuts \u003Cthe clip's shot starts> --credit \"\u003Cwho made the\n   source, its URL, date>\" --negative \u003Cout>\u002Fcalibration\u002F*.json`. Bands come from film-sized\n   excerpts of the source, split by shot, with half the splits held out; the calibration controls\n   cap each band's widening so they keep failing.\n3. Prove the check: `controls.py check \u003Cout> \u003Cpack dir>` must show every control failing (margin\n   above 0) and the source and replica passing, with the evaluation half held out. Then\n   `controls.py selftest \u003Cpack dir> --near \u003Cthe near-miss film>` (the pack argument is required)\n   must exit 0. Put the table in `reference\u002Fstatistics.md`. A control that passes goes under \"what\n   the check cannot say\"; never narrow a band until it fails.\n4. Describe: fill the judgment knobs in `style.json` and write `STYLE.md`.\n5. Validate: author a scene of at least a third of the source's length (bands are learned from\n   excerpts that long) on a different subject,\n   from ink.js and the scene elements, with geometry you write, never traced; pass the pack's\n   `palette.ink` as every ink.js call's `color` (the engine's `INK` default is not the pack's).\n   Render it at the source's size with `${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Frender.py \u003Cscene.js> \u003Cframes\n   dir> --fps \u003Cthe pack's knobs.frame_rate.base_fps> --encode mp4 --playwright-core\n   '${user_config.playwright_core}'` (it serves the scene's folder and `scripts\u002F`), and run\n   `inkstats.py \u003Cframes dir>.mp4 --cuts \u003Cshot starts> --pack \u003Cpack dir>`. A produce production\n   passes its `shots.json` as `--cuts`. It exits 0 only when every checked row and the palette\n   pass. Each row prints its distance to source (0 is the source value, 1 the band edge on either side); the\n   film's distance ranks passing scenes and its margin names the row nearest failing.\n6. Review: measure each prop with `--region X,Y,W,H --t T0-T1` next to source prop boxes, then\n   read every drawing at 1:1 (tile frames so no image is over the long-edge limit\n   `${CLAUDE_PLUGIN_ROOT}\u002Fskills\u002Frotoscope\u002Freference\u002Fmethod.md`, Reviewing images, records; never\n   downscale, never a GIF) beside source crops. A pass on the numbers with a crop that does not\n   read as the style is a fail; say which mark is wrong.\n7. Record: put the parameters that passed into the pack's `brush` and the result into `STYLE.md`,\n   including where the scene still falls short.\n\nRepeat 5-7 until the check passes and the crops read as the style. Tune the scene against the\ncheck, never the check against the scene. `inkstats.py` with no pack (`--json` for the full\nsummary) measures any film, which is how to compare two films.\n\n## Next\n\n\u002Fanimation:produce \u003Cproduction dir>\n\nIt takes a style pack this skill wrote and makes the film: boards for approval, then shots,\nrender, and review.\n\n## Gotchas\n\n- A post filter must not be what passes the check. Blur, noise, stripes and dry-brush overlays move\n  edge softness and the amount of gray inside the ink, so those rows are measured but not checked.\n  `grain` and `period` are measured only: on the woodcut source they follow codec residue and the\n  pixel grid, and a flat black through h264 lands in `grain`'s band. `flat` rejects texture laid\n  over all the black, and `rough` and `offstep` do not move under blur, noise, stripes or dry brush.\n  `controls.py selftest \u003Cpack dir> [--near \u003Cfilm>]` exits 1 if the review's blur-and-stripes filter\n  (and, with `--near`, the warped, retimed `ATTACK`) gets a synthetic or near-miss film through;\n  rerun it with `--near` after changing a statistic.\n- `straight` and `sliver` follow the subject, so they are checked only inside the content classes\n  `border` and `caption` (`straight_border`, `sliver_caption`, ...) and printed as measured only over\n  the whole frame. `boil` is measured on the border and caption. A scene without a frame line or a\n  caption panel in the top quarter leaves those rows n\u002Fa; draw both, as the source does.\n- Bands are learned per excerpt of the whole source, not per shot, so a very short film is judged\n  against bands that may not fit it; there is no per-shot row.\n- `w50` and `pw50` come from a distance transform and move in 2 px steps; every woodcut source\n  excerpt has `pw50` 8, so neither is checked.\n- A strictly regular timing fails `offstep`: hold a few drawings for 2 or 4 frames.\n- `soft` needs a soften pass after drawing, since a two-tone canvas render has almost no edge ramp.\n  Chromium's `ctx.filter = 'blur()'` does nothing below a floor\n  (`${CLAUDE_PLUGIN_ROOT}\u002Fskills\u002Frotoscope\u002Freference\u002Fmethod.md`, Rendering, holds the dated\n  record); soften in JS instead.\n",{"metadata":24,"description":7,"argument-hint":27,"user-invocable":28,"disable-model-invocation":20},{"summary":25,"workflow-stage":26},"Measure a traced clip into a style pack and check new scenes against it","implement","\u003Crotoscope work dir> \u003Cpack dir> [--cuts T,T,..] [--credit TEXT] [--negative SUMMARY.json ...]",true,"main","d0e68c3f36b92a1d6381f0ba0060d7a0b8b886c5","plugins\u002Fanimation\u002Fskills\u002Flearn-style",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 learn-style",{"tool":44,"command":45},"bunx","bunx skills add melodic-software\u002Fclaude-code-plugins --skill learn-style",{"tool":47,"command":48},"pnpm","pnpm dlx skills add melodic-software\u002Fclaude-code-plugins --skill learn-style","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fmelodic-software\u002Fclaude-code-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fanimation\u002Fskills\u002Flearn-style\u002FSKILL.md",[51,57,63],{"path":52,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":55,"sourceHtmlUrl":56},"reference\u002Fstatistics.md","REFERENCE","参考文档",22925,"https:\u002F\u002Fgithub.com\u002Fmelodic-software\u002Fclaude-code-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fanimation\u002Fskills\u002Flearn-style\u002Freference\u002Fstatistics.md",{"path":58,"resourceType":59,"resourceTypeDesc":60,"sizeBytes":61,"sourceHtmlUrl":62},"scripts\u002Fcontrols.py","SCRIPT","脚本",11953,"https:\u002F\u002Fgithub.com\u002Fmelodic-software\u002Fclaude-code-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fanimation\u002Fskills\u002Flearn-style\u002Fscripts\u002Fcontrols.py",{"path":64,"resourceType":59,"resourceTypeDesc":60,"sizeBytes":65,"sourceHtmlUrl":66},"scripts\u002Flearn.py",14366,"https:\u002F\u002Fgithub.com\u002Fmelodic-software\u002Fclaude-code-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fanimation\u002Fskills\u002Flearn-style\u002Fscripts\u002Flearn.py",[68,75,82,89,94,101],{"skillNo":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":74,"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":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"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":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"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":90,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":91,"categories":92,"keywords":93,"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":95,"name":96,"nameZh":6,"description":97,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":98,"categories":99,"keywords":100,"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":102,"name":103,"nameZh":6,"description":104,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":105,"categories":106,"keywords":107,"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",[],[]]