[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M77MWH6GCKNAVNEEVFDYYWR0":3,"skill-same:01M77MWH6GCKNAVNEEVFDYYWR0":48},{"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},"01M77MWH6GCKNAVNEEVFDYYWR0","setup",null,"Report (check, the default) or write (apply) this repository's tracked .claude\u002Fecosystems\u002FECOSYSTEM.yaml build, test and lint commands, which \u002Ftoolchain:check and \u002Ftoolchain:lint resolve first. Re-runnable.","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\u002Ftoolchain\u002Fskills\u002Fsetup\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\ndescription: \"Report (check, the default) or write (apply) this repository's tracked .claude\u002Fecosystems\u002FECOSYSTEM.yaml build, test and lint commands, which \u002Ftoolchain:check and \u002Ftoolchain:lint resolve first. Re-runnable.\"\nargument-hint: \"[check|apply] [\u003Cecosystem>]\"\nuser-invocable: true\ndisable-model-invocation: true\n---\n\n## Purpose\n\nInspect and configure the consuming repo's tracked ecosystem command surface per the uniform setup\ncontract (`docs\u002Fplugin-philosophy.md` \"Setup is explicit and repeatable\" in the marketplace\nrepository): `check` reports what is configured, `apply` writes it. The tracked files at\n`.claude\u002Fecosystems\u002F\u003Cecosystem>.yaml` let `\u002Ftoolchain:check` and `\u002Ftoolchain:lint` resolve commands\ndeterministically from rung 1 of the ladder\n([`${CLAUDE_PLUGIN_ROOT}\u002Freference\u002Fresolution-ladder.md`](${CLAUDE_PLUGIN_ROOT}\u002Freference\u002Fresolution-ladder.md))\ninstead of inferring or falling back to bundled defaults every run. This skill is the ladder's\n**writer** for rungs 2 and 3 (infer-and-persist, ask-and-persist).\n\nIdempotent: re-running reads the existing files and offers updates rather than overwriting blind. The\nplugin ships working bundled portable defaults (rung 4), so an unconfigured ecosystem is **INFO** (the\ndefault resolves), never FAIL.\n\nAction routing: no argument or `check` runs the check; `apply` runs the check first, then writes.\n`apply \u003Cecosystem>` scopes the whole run to that one ecosystem; when a named ecosystem's inference is\nunambiguous it is written non-interactively, otherwise (or with no ecosystem argument in an\ninteractive session) the interview below runs.\n\n### Resolve repo root\n\n```bash\nREPO_ROOT=$(git rev-parse --show-toplevel)\n```\n\nRead and write only inside `$REPO_ROOT\u002F.claude\u002F`, never the plugin directory or the plugin data\ndirectory; configuration lives in the consumer's tracked files.\n\n## `check` (read-only)\n\nThe bundled portable defaults and the contract schema are the single source of truth for the file\nshape (`${CLAUDE_PLUGIN_ROOT}\u002Freference\u002Fecosystems\u002F`, `ecosystem.schema.json`). **Read the ladder\nfirst**, then report a PASS\u002FFAIL\u002FINFO table; modify nothing.\n\n1. **Configured ecosystems.** For each `$REPO_ROOT\u002F.claude\u002Fecosystems\u002F\u003Cecosystem>.yaml` present,\n   report the ecosystem and its resolved command surface\n   (`build-cmd`\u002F`test-cmd`\u002F`check-cmd`\u002F`fix-cmd`\u002F`code-fix-cmd`). Validate each against the contract's\n   `ecosystem.schema.json`. **FAIL** a schema-invalid file (with the validation error in the\n   remediation line), an ecosystem file excluded by `.gitignore` (`git check-ignore -v` matches;\n   teammates would never receive it. Report the matching rule), or an un-ignored but untracked file\n   (`git ls-files --error-unmatch` exits non-zero; report \"commit it to share with the team\").\n   Otherwise PASS. If `$ARGUMENTS` names one ecosystem, scope\n   the report to just that file.\n2. **Unconfigured ecosystems.** INFO: detect which ecosystems the repo has that are *not* yet\n   configured (see the inference signals under `apply`), and note that `\u002Ftoolchain:check` \u002F\n   `\u002Ftoolchain:lint` resolve those through inference then the bundled portable defaults. The\n   remediation is `apply` to persist a command surface.\n\n## `apply` (idempotent)\n\nRun `check` first. Then write the accepted ecosystem files. After each write, re-run the `check`\nprobe pair for that path rather than trusting the write: `git check-ignore -v` reports no match,\nand `git ls-files --error-unmatch` distinguishes tracked from written-but-untracked (the\nguaranteed state right after a fresh write, so report \"written but untracked: commit it\", never\nsuccess).\n\n### 1. Read existing config first\n\nFor each `$REPO_ROOT\u002F.claude\u002Fecosystems\u002F\u003Cecosystem>.yaml` that already exists, load it and present a\nshort summary. The interview proposes changes against that baseline; nothing is dropped without the\nuser confirming. If `$ARGUMENTS` names one ecosystem, scope the whole run to just that file.\n\n### 2. Infer candidates from the repo before asking\n\nDetect which ecosystems apply from what actually exists, and draft each one's command surface. Seed\nthe draft from the bundled portable default at\n[`${CLAUDE_PLUGIN_ROOT}\u002Freference\u002Fecosystems\u002F\u003Cecosystem>.yaml`](${CLAUDE_PLUGIN_ROOT}\u002Freference\u002Fecosystems\u002F),\nthen specialize it to the repo:\n\n- **dotnet**. `*.slnx`\u002F`*.sln`\u002F`*.csproj` present. Resolve the `anchor` (solution file at root, else\n  nearest project). Note any repo-specific trap in `notes` (e.g. the xUnit v3 `--nologo` pin).\n- **python**. `pyproject.toml`\u002F`uv.lock`. Prefer `uv run …` when `uv.lock` exists, else plain\n  `ruff`\u002F`pytest`. Set `project-discovery` to the `pyproject.toml` roots.\n- **typescript**. `package.json`\u002F`tsconfig*.json`. Read the `scripts` block for the real `test-cmd`;\n  pick `check-cmd`\u002F`fix-cmd` (format-only) and `code-fix-cmd` (semantic lint autofixes) from the\n  configured linter (`biome.json` → Biome format vs check --write; eslint config → ESLint).\n- **bash** \u002F **powershell**. Shell\u002FPowerShell files present; keep the bundled check\u002Ffix commands\n  unless the repo documents its own.\n- **markdown**, a markdownlint config present.\n- **yaml**. `.github\u002Fworkflows\u002F` present (lint-only surface. `\u002Ftoolchain:lint` runs it,\n  `\u002Ftoolchain:check` does not).\n- **cross-cutting**. Repo-root config for `typos`\u002F`gitleaks`\u002F`editorconfig-checker`\u002F`lychee-offline` present (lint-only).\n\nRepo-specific CI-parity gates beyond plain build\u002Ftest\u002Flint (lockfile drift, generated-artifact\nfreshness, schema regeneration) belong in the ecosystem file's `gates` array. Draft one when the\nrepo's CI runs such a check. For an ecosystem with `project-discovery`, a gate that is repo-wide\nrather than per-project (protobuf generation, schema freshness. Checks something that exists once,\nnot once per discovered project root) needs `run-from: repo-root` on the drafted gate; omitting it\ndefaults to per-project execution, which redundantly re-runs the check in every root or fails in\nroots lacking its config. Ask which shape applies when the CI check's own scope is ambiguous from its\ncommand alone.\n\n### 3. Interview or write non-interactively\n\nWhen `apply \u003Cecosystem>` names one ecosystem and its inference is unambiguous, write the drafted\ncommand surface non-interactively. Otherwise interview, one decision at a time: present each inferred\necosystem's drafted command surface with a recommendation; let the user accept, edit, or skip it. When\ninference is ambiguous (multiple test runners, no configured linter), ask for the command rather than\nguessing. Offer any ecosystem the repo has that inference missed.\n\n### 4. Write the files\n\nMaterialize one `$REPO_ROOT\u002F.claude\u002Fecosystems\u002F\u003Cecosystem>.yaml` per accepted ecosystem, conforming to\nthe contract's `ecosystem.schema.json`. Each file carries a one-line header comment citing the\ncontract, `globs` (required), the four command keys (`null` where a phase does not apply), and the\noptional keys that apply (`anchor`, `project-discovery`, `opt-in`, `install-hint`, `gates`, `notes`).\nConfirm each file is tracked, not ignored.\n\nRecommend the consumer validate these in their own gate, a `check-jsonschema` hook or CI lane against\nthe contract schema catches typos the tolerant reader would otherwise ignore.\n\n### 5. Offer the personal override convention\n\nPersonal per-key overrides go in `.claude\u002Fecosystems\u002F\u003Cecosystem>.local.yaml`; a user-global base at\n`~\u002F.claude\u002Fecosystems\u002F\u003Cecosystem>.yaml` is also honored. Layers resolve\nuser-global → team → personal override, additively per key. Recommend the consumer add the recursive\n`.claude\u002F**\u002F*.local.*` line to `.gitignore` if not already covered.\n\n## Output\n\nTracked `.claude\u002Fecosystems\u002F*.yaml` files in the consuming repo, and a one-paragraph summary of what\nwas written and how to re-run this setup to reconfigure. `check` alone reports the effective\nconfiguration and changes nothing.\n\n## What this skill does NOT do\n\n- Run build\u002Ftest\u002Flint. That is `\u002Ftoolchain:check` and `\u002Ftoolchain:lint`.\n- Write machine-local state. Configuration lives in the consumer's tracked files, never in the plugin\n  directory or the plugin data directory.\n- Write the plugin cache, Claude Code user settings, or `pluginConfigs`.\n- Ship or edit the bundled portable defaults. Those are the plugin's rung-4 fallback, never written\n  into a consumer repo except as the seed for a file this interview produces.\n","## Purpose\n\nInspect and configure the consuming repo's tracked ecosystem command surface per the uniform setup\ncontract (`docs\u002Fplugin-philosophy.md` \"Setup is explicit and repeatable\" in the marketplace\nrepository): `check` reports what is configured, `apply` writes it. The tracked files at\n`.claude\u002Fecosystems\u002F\u003Cecosystem>.yaml` let `\u002Ftoolchain:check` and `\u002Ftoolchain:lint` resolve commands\ndeterministically from rung 1 of the ladder\n([`${CLAUDE_PLUGIN_ROOT}\u002Freference\u002Fresolution-ladder.md`](${CLAUDE_PLUGIN_ROOT}\u002Freference\u002Fresolution-ladder.md))\ninstead of inferring or falling back to bundled defaults every run. This skill is the ladder's\n**writer** for rungs 2 and 3 (infer-and-persist, ask-and-persist).\n\nIdempotent: re-running reads the existing files and offers updates rather than overwriting blind. The\nplugin ships working bundled portable defaults (rung 4), so an unconfigured ecosystem is **INFO** (the\ndefault resolves), never FAIL.\n\nAction routing: no argument or `check` runs the check; `apply` runs the check first, then writes.\n`apply \u003Cecosystem>` scopes the whole run to that one ecosystem; when a named ecosystem's inference is\nunambiguous it is written non-interactively, otherwise (or with no ecosystem argument in an\ninteractive session) the interview below runs.\n\n### Resolve repo root\n\n```bash\nREPO_ROOT=$(git rev-parse --show-toplevel)\n```\n\nRead and write only inside `$REPO_ROOT\u002F.claude\u002F`, never the plugin directory or the plugin data\ndirectory; configuration lives in the consumer's tracked files.\n\n## `check` (read-only)\n\nThe bundled portable defaults and the contract schema are the single source of truth for the file\nshape (`${CLAUDE_PLUGIN_ROOT}\u002Freference\u002Fecosystems\u002F`, `ecosystem.schema.json`). **Read the ladder\nfirst**, then report a PASS\u002FFAIL\u002FINFO table; modify nothing.\n\n1. **Configured ecosystems.** For each `$REPO_ROOT\u002F.claude\u002Fecosystems\u002F\u003Cecosystem>.yaml` present,\n   report the ecosystem and its resolved command surface\n   (`build-cmd`\u002F`test-cmd`\u002F`check-cmd`\u002F`fix-cmd`\u002F`code-fix-cmd`). Validate each against the contract's\n   `ecosystem.schema.json`. **FAIL** a schema-invalid file (with the validation error in the\n   remediation line), an ecosystem file excluded by `.gitignore` (`git check-ignore -v` matches;\n   teammates would never receive it. Report the matching rule), or an un-ignored but untracked file\n   (`git ls-files --error-unmatch` exits non-zero; report \"commit it to share with the team\").\n   Otherwise PASS. If `$ARGUMENTS` names one ecosystem, scope\n   the report to just that file.\n2. **Unconfigured ecosystems.** INFO: detect which ecosystems the repo has that are *not* yet\n   configured (see the inference signals under `apply`), and note that `\u002Ftoolchain:check` \u002F\n   `\u002Ftoolchain:lint` resolve those through inference then the bundled portable defaults. The\n   remediation is `apply` to persist a command surface.\n\n## `apply` (idempotent)\n\nRun `check` first. Then write the accepted ecosystem files. After each write, re-run the `check`\nprobe pair for that path rather than trusting the write: `git check-ignore -v` reports no match,\nand `git ls-files --error-unmatch` distinguishes tracked from written-but-untracked (the\nguaranteed state right after a fresh write, so report \"written but untracked: commit it\", never\nsuccess).\n\n### 1. Read existing config first\n\nFor each `$REPO_ROOT\u002F.claude\u002Fecosystems\u002F\u003Cecosystem>.yaml` that already exists, load it and present a\nshort summary. The interview proposes changes against that baseline; nothing is dropped without the\nuser confirming. If `$ARGUMENTS` names one ecosystem, scope the whole run to just that file.\n\n### 2. Infer candidates from the repo before asking\n\nDetect which ecosystems apply from what actually exists, and draft each one's command surface. Seed\nthe draft from the bundled portable default at\n[`${CLAUDE_PLUGIN_ROOT}\u002Freference\u002Fecosystems\u002F\u003Cecosystem>.yaml`](${CLAUDE_PLUGIN_ROOT}\u002Freference\u002Fecosystems\u002F),\nthen specialize it to the repo:\n\n- **dotnet**. `*.slnx`\u002F`*.sln`\u002F`*.csproj` present. Resolve the `anchor` (solution file at root, else\n  nearest project). Note any repo-specific trap in `notes` (e.g. the xUnit v3 `--nologo` pin).\n- **python**. `pyproject.toml`\u002F`uv.lock`. Prefer `uv run …` when `uv.lock` exists, else plain\n  `ruff`\u002F`pytest`. Set `project-discovery` to the `pyproject.toml` roots.\n- **typescript**. `package.json`\u002F`tsconfig*.json`. Read the `scripts` block for the real `test-cmd`;\n  pick `check-cmd`\u002F`fix-cmd` (format-only) and `code-fix-cmd` (semantic lint autofixes) from the\n  configured linter (`biome.json` → Biome format vs check --write; eslint config → ESLint).\n- **bash** \u002F **powershell**. Shell\u002FPowerShell files present; keep the bundled check\u002Ffix commands\n  unless the repo documents its own.\n- **markdown**, a markdownlint config present.\n- **yaml**. `.github\u002Fworkflows\u002F` present (lint-only surface. `\u002Ftoolchain:lint` runs it,\n  `\u002Ftoolchain:check` does not).\n- **cross-cutting**. Repo-root config for `typos`\u002F`gitleaks`\u002F`editorconfig-checker`\u002F`lychee-offline` present (lint-only).\n\nRepo-specific CI-parity gates beyond plain build\u002Ftest\u002Flint (lockfile drift, generated-artifact\nfreshness, schema regeneration) belong in the ecosystem file's `gates` array. Draft one when the\nrepo's CI runs such a check. For an ecosystem with `project-discovery`, a gate that is repo-wide\nrather than per-project (protobuf generation, schema freshness. Checks something that exists once,\nnot once per discovered project root) needs `run-from: repo-root` on the drafted gate; omitting it\ndefaults to per-project execution, which redundantly re-runs the check in every root or fails in\nroots lacking its config. Ask which shape applies when the CI check's own scope is ambiguous from its\ncommand alone.\n\n### 3. Interview or write non-interactively\n\nWhen `apply \u003Cecosystem>` names one ecosystem and its inference is unambiguous, write the drafted\ncommand surface non-interactively. Otherwise interview, one decision at a time: present each inferred\necosystem's drafted command surface with a recommendation; let the user accept, edit, or skip it. When\ninference is ambiguous (multiple test runners, no configured linter), ask for the command rather than\nguessing. Offer any ecosystem the repo has that inference missed.\n\n### 4. Write the files\n\nMaterialize one `$REPO_ROOT\u002F.claude\u002Fecosystems\u002F\u003Cecosystem>.yaml` per accepted ecosystem, conforming to\nthe contract's `ecosystem.schema.json`. Each file carries a one-line header comment citing the\ncontract, `globs` (required), the four command keys (`null` where a phase does not apply), and the\noptional keys that apply (`anchor`, `project-discovery`, `opt-in`, `install-hint`, `gates`, `notes`).\nConfirm each file is tracked, not ignored.\n\nRecommend the consumer validate these in their own gate, a `check-jsonschema` hook or CI lane against\nthe contract schema catches typos the tolerant reader would otherwise ignore.\n\n### 5. Offer the personal override convention\n\nPersonal per-key overrides go in `.claude\u002Fecosystems\u002F\u003Cecosystem>.local.yaml`; a user-global base at\n`~\u002F.claude\u002Fecosystems\u002F\u003Cecosystem>.yaml` is also honored. Layers resolve\nuser-global → team → personal override, additively per key. Recommend the consumer add the recursive\n`.claude\u002F**\u002F*.local.*` line to `.gitignore` if not already covered.\n\n## Output\n\nTracked `.claude\u002Fecosystems\u002F*.yaml` files in the consuming repo, and a one-paragraph summary of what\nwas written and how to re-run this setup to reconfigure. `check` alone reports the effective\nconfiguration and changes nothing.\n\n## What this skill does NOT do\n\n- Run build\u002Ftest\u002Flint. That is `\u002Ftoolchain:check` and `\u002Ftoolchain:lint`.\n- Write machine-local state. Configuration lives in the consumer's tracked files, never in the plugin\n  directory or the plugin data directory.\n- Write the plugin cache, Claude Code user settings, or `pluginConfigs`.\n- Ship or edit the bundled portable defaults. Those are the plugin's rung-4 fallback, never written\n  into a consumer repo except as the seed for a file this interview produces.\n",{"description":7,"argument-hint":24,"user-invocable":25,"disable-model-invocation":25},"[check|apply] [\u003Cecosystem>]",true,"main","d0e68c3f36b92a1d6381f0ba0060d7a0b8b886c5","plugins\u002Ftoolchain\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\u002Ftoolchain\u002Fskills\u002Fsetup\u002FSKILL.md",[],[49,56,63,70,75,82],{"skillNo":50,"name":51,"nameZh":6,"description":52,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":53,"categories":54,"keywords":55,"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":57,"name":58,"nameZh":6,"description":59,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":60,"categories":61,"keywords":62,"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":64,"name":65,"nameZh":6,"description":66,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":67,"categories":68,"keywords":69,"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":71,"name":65,"nameZh":6,"description":66,"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},"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":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},"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":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},"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",[],[]]