[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M77M1MXE1FAJS5NPM9QQ59EX":3,"skill-same:01M77M1MXE1FAJS5NPM9QQ59EX":54},{"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":26,"commitSha":27,"skillDirectory":28,"forksCount":29,"repositoryHtmlUrl":30,"repositoryHomepageUrl":6,"ownerHtmlUrl":31,"ownerBlogUrl":32,"ownerDescription":33,"updatedAt":34,"install":35,"resources":47},"01M77M1MXE1FAJS5NPM9QQ59EX","setup",null,"Report (check, the default) or resolve (apply) the knowledge plugin's library_dir against the repository's artifact convention and its extraction prerequisites; apply install-deps provisions the extraction node deps and Chromium.","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\u002Fknowledge\u002Fskills\u002Fsetup\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\ndescription: \"Report (check, the default) or resolve (apply) the knowledge plugin's library_dir against the repository's artifact convention and its extraction prerequisites; apply install-deps provisions the extraction node deps and Chromium.\"\nargument-hint: \"[check|apply] [install-deps]\"\nuser-invocable: true\ndisable-model-invocation: true\n---\n\n## Purpose\n\nBring the knowledge plugin to a working state: confirm the effective `library_dir` against this\nrepository's artifact convention, and verify (or provision) the extraction pipelines'\nprerequisites. `library_dir` is a personal `userConfig` option that Claude Code prompts for and\nstores; this skill reports where the effective value came from and never writes it.\n\n- **Pointer**: when deciding where a `library_dir` value is stored and which settings scopes are\n  read for it, fetch\n  \u003Chttps:\u002F\u002Fcode.claude.com\u002Fdocs\u002Fen\u002Fplugins\u002Fmanifest-reference#where-values-are-stored> and\n  \u003Chttps:\u002F\u002Fcode.claude.com\u002Fdocs\u002Fen\u002Fsettings-reference#pluginconfigs> live; the option contract is\n  \u003Chttps:\u002F\u002Fcode.claude.com\u002Fdocs\u002Fen\u002Fplugins\u002Fmanifest-reference#user-configuration>.\n\nCheck-centric per the uniform setup contract (`docs\u002Fplugin-philosophy.md`\n\"Setup is explicit and repeatable\" in the marketplace repository): `check` inspects and\nreports, `apply` resolves what `check` found, and the extraction-dependency provisioning is a\ndistinct opt-in subaction. The `library_dir` option is Claude-Code-owned; this skill never\nwrites it, only reports and routes.\n\nAction routing: no argument or `check` runs the check; `apply` runs the check first, then the\n`library_dir` guidance; `apply install-deps` additionally provisions the extraction dependencies\nbelow. All actions are non-interactive when the action is given, never prompt.\n\n## `check` (read-only)\n\nReport a PASS\u002FFAIL\u002FINFO table with one remediation line per FAIL. Do not edit settings, write\nconfig, or install anything.\n\n1. **`library_dir` vs repository convention.** Read the rendered `${user_config.library_dir}`\n   value (default `.` = repository root). Inspect the consumer's `CLAUDE.md`, `AGENTS.md`,\n   `.claude\u002Frules`, and existing artifact directories for a declared knowledge\u002Fartifact\n   convention, the team source of truth. Do not infer `library_dir` from the lifecycle\n   `memory_dir`: the memory root holds lifecycle working documents, while `library_dir` owns the\n   knowledge corpus. Mapping both to `.work` would nest the video-digest pipeline's own\n   `.work\u002F\u003Cwatch-epic>\u002F...` layout as `.work\u002F.work\u002F...`. PASS when the personal value matches the\n   convention (or the portable `.` default with no distinct convention). FAIL on a mismatch\n   (remediation: Claude Code's plugin configuration prompt for `knowledge`) or a machine-absolute\n   path (not portable for repository work).\n2. **`upstream_records_dir`**. INFO. Report the directory `\u002Fknowledge:absorb-upstream` writes to\n   and its layer: `upstream_records_dir` in `\u003Chome>\u002Fknowledge.yaml` (`\u003Chome>` from the pointer\n   region of `AGENTS.md` or `CLAUDE.md`, else `docs\u002Fconventions`), else the default\n   `docs\u002Fupstream`, under the root rule and value rules of\n   `${CLAUDE_PLUGIN_ROOT}\u002Freference\u002Fconfig.md`. An invalid value is a FAIL naming the file, key and\n   value (remediation: edit the team file by hand; `apply` does not write it).\n3. **Extraction node deps**. INFO. Probe whether\n   `${CLAUDE_PLUGIN_DATA}\u002Fnode_modules\u002F@melodic\u002Fvideo-digestion` exists (the video-digest and\n   course-digest pipelines share it). Missing is INFO, not FAIL: each ingest skill self-provisions\n   on first run, and `apply install-deps` pre-provisions. Remediation: `apply install-deps`.\n4. **Playwright Chromium**. INFO. Probe whether the browsers path\n   (`PLAYWRIGHT_BROWSERS_PATH`, else `${CLAUDE_PLUGIN_DATA}\u002Fms-playwright`) holds a `chromium-*`\n   or `chromium_headless_shell-*` build (course-digest frame capture). Missing is INFO with\n   remediation `apply install-deps`.\n5. **OS-level media tools**. INFO. Probe `yt-dlp --version` (video acquisition), `ffmpeg\n   -version` (frame extraction, watch\u002Fcourse actions), and `magick -version` (ImageMagick 7,\n   contact sheets. Watch\u002Fcourse actions). Each absence is INFO with the platform install command\n   from the ingest skill's Prerequisites; this skill never installs system packages. `distill`\n   (PDF) needs none of these.\n\n## `apply` (idempotent)\n\nRun `check`, then resolve each finding. Re-running after everything passes changes nothing and\nreports \"already configured\".\n\n1. **`library_dir` mismatch. Guidance only.** `library_dir` is a personal `userConfig` scalar;\n   never hand-edit `pluginConfigs` or write Claude Code settings. Reconfigure `library_dir`\n   through Claude Code's native flow, interactively with\n   `\u002Fplugin configure knowledge@\u003Cmarketplace>` or by a headless route, as the marketplace's\n   plugin-reconfiguration convention gives them in\n   [§ The routes](..\u002F..\u002Freference\u002Fplugin-reconfiguration.md#the-routes)\n   (it owns the verified-version record). Apply the scope and failure-signal caveats in its\n   [§ Caveats every setup skill's short form carries](..\u002F..\u002Freference\u002Fplugin-reconfiguration.md#caveats-every-setup-skills-short-form-carries).\n   Read both sections and print what they give, the fallback route, its behavior on an\n   already-installed plugin and the scope to pass included, rather than only naming them, and\n   leave out the verified-version record.\n   Never uninstall to reconfigure; that section links what an uninstall deletes. Afterwards rerun\n   `check` in a **fresh session**, since a same-session `check` can still show the old value, and\n   report the observed effective value, never an unobserved change.\n\n   - **Pointer**: for the headless command's flags, how it reports a saved or refused value, and\n     when a saved value applies, fetch\n     [plugin CLI reference § plugin configure](https:\u002F\u002Fcode.claude.com\u002Fdocs\u002Fen\u002Fplugins\u002Fcli-reference#plugin-configure)\n     live.\n\n   For where `${user_config.*}` resolves, see\n   [Plugin manifest reference: Reference a saved value](https:\u002F\u002Fcode.claude.com\u002Fdocs\u002Fen\u002Fplugins\u002Fmanifest-reference#reference-a-saved-value).\n   For a root outside the project and home directories, recommend the portable value forms from the\n   README's option table (`~` prefix or `${NAME}` \u002F `%NAME%` env-var reference) instead of a literal\n   machine path, which guardrail hardcoded-path checks rightly block.\n2. **`apply install-deps`. Provision the extraction dependencies.** Only with this subaction, run\n   the shared idempotent provisioner once per extraction package (each run installs that\n   package's vendored node dependencies into `${CLAUDE_PLUGIN_DATA}`, and the course-digest run\n   additionally provisions Chromium into `${CLAUDE_PLUGIN_DATA}\u002Fms-playwright`):\n\n   ```bash\n   node \"${CLAUDE_PLUGIN_ROOT}\u002Fvendor\u002Fnode-launcher\u002Fsetup-deps.mjs\" --data-dir \"${CLAUDE_PLUGIN_DATA}\" --package \"${CLAUDE_PLUGIN_ROOT}\u002Fskills\u002Fvideo-digest\u002Fextraction\"\n   node \"${CLAUDE_PLUGIN_ROOT}\u002Fvendor\u002Fnode-launcher\u002Fsetup-deps.mjs\" --data-dir \"${CLAUDE_PLUGIN_DATA}\" --package \"${CLAUDE_PLUGIN_ROOT}\u002Fskills\u002Fcourse-digest\u002Fextraction\"\n   ```\n\n   A stored fingerprint gates reinstalls, so re-running is safe and cheap. After provisioning,\n   re-run the `check` node-deps and Chromium probes and report their actual results, never claim\n   provisioned on the script exit codes alone.\n3. **Invalid `upstream_records_dir`. Guidance only.** Name the file, key and value and the valid\n   forms from `${CLAUDE_PLUGIN_ROOT}\u002Freference\u002Fconfig.md`; never write the team file.\n4. **OS-level media tools. Guidance only.** For a missing `yt-dlp`, `ffmpeg`, or ImageMagick 7,\n   give the platform install command from the ingest skill's Prerequisites. This skill never\n   installs system packages.\n5. **Confirm.** Report the observed `library_dir`, the repository convention and any mismatch, and\n   whether extraction dependencies were provisioned or intentionally skipped. Note that\n   `\u002Fknowledge:distill` writes to its explicitly named target skill rather than this setting.\n\n## Output\n\nReport the observed personal value, the repository convention, any mismatch, the state of each\nprerequisite, and the exact next action (`\u002Fplugin configure knowledge` for `library_dir`,\nor `apply install-deps` for provisioning). A `library_dir` change takes effect in a fresh session,\nnot this one. Do not claim it this session.\n\n## Boundaries\n\n- Do not run an ingestion pipeline. Provisioning dependencies is not the same as running one.\n- Do not write the plugin cache, Claude Code user settings, or `pluginConfigs`.\n- Do not invent organization-specific paths or environment-variable prefixes.\n","## Purpose\n\nBring the knowledge plugin to a working state: confirm the effective `library_dir` against this\nrepository's artifact convention, and verify (or provision) the extraction pipelines'\nprerequisites. `library_dir` is a personal `userConfig` option that Claude Code prompts for and\nstores; this skill reports where the effective value came from and never writes it.\n\n- **Pointer**: when deciding where a `library_dir` value is stored and which settings scopes are\n  read for it, fetch\n  \u003Chttps:\u002F\u002Fcode.claude.com\u002Fdocs\u002Fen\u002Fplugins\u002Fmanifest-reference#where-values-are-stored> and\n  \u003Chttps:\u002F\u002Fcode.claude.com\u002Fdocs\u002Fen\u002Fsettings-reference#pluginconfigs> live; the option contract is\n  \u003Chttps:\u002F\u002Fcode.claude.com\u002Fdocs\u002Fen\u002Fplugins\u002Fmanifest-reference#user-configuration>.\n\nCheck-centric per the uniform setup contract (`docs\u002Fplugin-philosophy.md`\n\"Setup is explicit and repeatable\" in the marketplace repository): `check` inspects and\nreports, `apply` resolves what `check` found, and the extraction-dependency provisioning is a\ndistinct opt-in subaction. The `library_dir` option is Claude-Code-owned; this skill never\nwrites it, only reports and routes.\n\nAction routing: no argument or `check` runs the check; `apply` runs the check first, then the\n`library_dir` guidance; `apply install-deps` additionally provisions the extraction dependencies\nbelow. All actions are non-interactive when the action is given, never prompt.\n\n## `check` (read-only)\n\nReport a PASS\u002FFAIL\u002FINFO table with one remediation line per FAIL. Do not edit settings, write\nconfig, or install anything.\n\n1. **`library_dir` vs repository convention.** Read the rendered `${user_config.library_dir}`\n   value (default `.` = repository root). Inspect the consumer's `CLAUDE.md`, `AGENTS.md`,\n   `.claude\u002Frules`, and existing artifact directories for a declared knowledge\u002Fartifact\n   convention, the team source of truth. Do not infer `library_dir` from the lifecycle\n   `memory_dir`: the memory root holds lifecycle working documents, while `library_dir` owns the\n   knowledge corpus. Mapping both to `.work` would nest the video-digest pipeline's own\n   `.work\u002F\u003Cwatch-epic>\u002F...` layout as `.work\u002F.work\u002F...`. PASS when the personal value matches the\n   convention (or the portable `.` default with no distinct convention). FAIL on a mismatch\n   (remediation: Claude Code's plugin configuration prompt for `knowledge`) or a machine-absolute\n   path (not portable for repository work).\n2. **`upstream_records_dir`**. INFO. Report the directory `\u002Fknowledge:absorb-upstream` writes to\n   and its layer: `upstream_records_dir` in `\u003Chome>\u002Fknowledge.yaml` (`\u003Chome>` from the pointer\n   region of `AGENTS.md` or `CLAUDE.md`, else `docs\u002Fconventions`), else the default\n   `docs\u002Fupstream`, under the root rule and value rules of\n   `${CLAUDE_PLUGIN_ROOT}\u002Freference\u002Fconfig.md`. An invalid value is a FAIL naming the file, key and\n   value (remediation: edit the team file by hand; `apply` does not write it).\n3. **Extraction node deps**. INFO. Probe whether\n   `${CLAUDE_PLUGIN_DATA}\u002Fnode_modules\u002F@melodic\u002Fvideo-digestion` exists (the video-digest and\n   course-digest pipelines share it). Missing is INFO, not FAIL: each ingest skill self-provisions\n   on first run, and `apply install-deps` pre-provisions. Remediation: `apply install-deps`.\n4. **Playwright Chromium**. INFO. Probe whether the browsers path\n   (`PLAYWRIGHT_BROWSERS_PATH`, else `${CLAUDE_PLUGIN_DATA}\u002Fms-playwright`) holds a `chromium-*`\n   or `chromium_headless_shell-*` build (course-digest frame capture). Missing is INFO with\n   remediation `apply install-deps`.\n5. **OS-level media tools**. INFO. Probe `yt-dlp --version` (video acquisition), `ffmpeg\n   -version` (frame extraction, watch\u002Fcourse actions), and `magick -version` (ImageMagick 7,\n   contact sheets. Watch\u002Fcourse actions). Each absence is INFO with the platform install command\n   from the ingest skill's Prerequisites; this skill never installs system packages. `distill`\n   (PDF) needs none of these.\n\n## `apply` (idempotent)\n\nRun `check`, then resolve each finding. Re-running after everything passes changes nothing and\nreports \"already configured\".\n\n1. **`library_dir` mismatch. Guidance only.** `library_dir` is a personal `userConfig` scalar;\n   never hand-edit `pluginConfigs` or write Claude Code settings. Reconfigure `library_dir`\n   through Claude Code's native flow, interactively with\n   `\u002Fplugin configure knowledge@\u003Cmarketplace>` or by a headless route, as the marketplace's\n   plugin-reconfiguration convention gives them in\n   [§ The routes](..\u002F..\u002Freference\u002Fplugin-reconfiguration.md#the-routes)\n   (it owns the verified-version record). Apply the scope and failure-signal caveats in its\n   [§ Caveats every setup skill's short form carries](..\u002F..\u002Freference\u002Fplugin-reconfiguration.md#caveats-every-setup-skills-short-form-carries).\n   Read both sections and print what they give, the fallback route, its behavior on an\n   already-installed plugin and the scope to pass included, rather than only naming them, and\n   leave out the verified-version record.\n   Never uninstall to reconfigure; that section links what an uninstall deletes. Afterwards rerun\n   `check` in a **fresh session**, since a same-session `check` can still show the old value, and\n   report the observed effective value, never an unobserved change.\n\n   - **Pointer**: for the headless command's flags, how it reports a saved or refused value, and\n     when a saved value applies, fetch\n     [plugin CLI reference § plugin configure](https:\u002F\u002Fcode.claude.com\u002Fdocs\u002Fen\u002Fplugins\u002Fcli-reference#plugin-configure)\n     live.\n\n   For where `${user_config.*}` resolves, see\n   [Plugin manifest reference: Reference a saved value](https:\u002F\u002Fcode.claude.com\u002Fdocs\u002Fen\u002Fplugins\u002Fmanifest-reference#reference-a-saved-value).\n   For a root outside the project and home directories, recommend the portable value forms from the\n   README's option table (`~` prefix or `${NAME}` \u002F `%NAME%` env-var reference) instead of a literal\n   machine path, which guardrail hardcoded-path checks rightly block.\n2. **`apply install-deps`. Provision the extraction dependencies.** Only with this subaction, run\n   the shared idempotent provisioner once per extraction package (each run installs that\n   package's vendored node dependencies into `${CLAUDE_PLUGIN_DATA}`, and the course-digest run\n   additionally provisions Chromium into `${CLAUDE_PLUGIN_DATA}\u002Fms-playwright`):\n\n   ```bash\n   node \"${CLAUDE_PLUGIN_ROOT}\u002Fvendor\u002Fnode-launcher\u002Fsetup-deps.mjs\" --data-dir \"${CLAUDE_PLUGIN_DATA}\" --package \"${CLAUDE_PLUGIN_ROOT}\u002Fskills\u002Fvideo-digest\u002Fextraction\"\n   node \"${CLAUDE_PLUGIN_ROOT}\u002Fvendor\u002Fnode-launcher\u002Fsetup-deps.mjs\" --data-dir \"${CLAUDE_PLUGIN_DATA}\" --package \"${CLAUDE_PLUGIN_ROOT}\u002Fskills\u002Fcourse-digest\u002Fextraction\"\n   ```\n\n   A stored fingerprint gates reinstalls, so re-running is safe and cheap. After provisioning,\n   re-run the `check` node-deps and Chromium probes and report their actual results, never claim\n   provisioned on the script exit codes alone.\n3. **Invalid `upstream_records_dir`. Guidance only.** Name the file, key and value and the valid\n   forms from `${CLAUDE_PLUGIN_ROOT}\u002Freference\u002Fconfig.md`; never write the team file.\n4. **OS-level media tools. Guidance only.** For a missing `yt-dlp`, `ffmpeg`, or ImageMagick 7,\n   give the platform install command from the ingest skill's Prerequisites. This skill never\n   installs system packages.\n5. **Confirm.** Report the observed `library_dir`, the repository convention and any mismatch, and\n   whether extraction dependencies were provisioned or intentionally skipped. Note that\n   `\u002Fknowledge:distill` writes to its explicitly named target skill rather than this setting.\n\n## Output\n\nReport the observed personal value, the repository convention, any mismatch, the state of each\nprerequisite, and the exact next action (`\u002Fplugin configure knowledge` for `library_dir`,\nor `apply install-deps` for provisioning). A `library_dir` change takes effect in a fresh session,\nnot this one. Do not claim it this session.\n\n## Boundaries\n\n- Do not run an ingestion pipeline. Provisioning dependencies is not the same as running one.\n- Do not write the plugin cache, Claude Code user settings, or `pluginConfigs`.\n- Do not invent organization-specific paths or environment-variable prefixes.\n",{"description":7,"argument-hint":24,"user-invocable":25,"disable-model-invocation":25},"[check|apply] [install-deps]",true,"main","d0e68c3f36b92a1d6381f0ba0060d7a0b8b886c5","plugins\u002Fknowledge\u002Fskills\u002Fsetup",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":36,"prompt":46,"zipAvailable":25},[37,40,43],{"tool":38,"command":39},"npx","npx skills add melodic-software\u002Fclaude-code-plugins --skill setup",{"tool":41,"command":42},"bunx","bunx skills add melodic-software\u002Fclaude-code-plugins --skill setup",{"tool":44,"command":45},"pnpm","pnpm dlx skills add melodic-software\u002Fclaude-code-plugins --skill setup","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fmelodic-software\u002Fclaude-code-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fknowledge\u002Fskills\u002Fsetup\u002FSKILL.md",[48],{"path":49,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":52,"sourceHtmlUrl":53},"evals\u002Fevals.json","REFERENCE","参考文档",3355,"https:\u002F\u002Fgithub.com\u002Fmelodic-software\u002Fclaude-code-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fknowledge\u002Fskills\u002Fsetup\u002Fevals\u002Fevals.json",[55,62,69,76,81,88],{"skillNo":56,"name":57,"nameZh":6,"description":58,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":59,"categories":60,"keywords":61,"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":63,"name":64,"nameZh":6,"description":65,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":66,"categories":67,"keywords":68,"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":70,"name":71,"nameZh":6,"description":72,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":75,"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":77,"name":71,"nameZh":6,"description":72,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":80,"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":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"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":89,"name":90,"nameZh":6,"description":91,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":92,"categories":93,"keywords":94,"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",[],[]]