[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M77MDKFM9RY8R4J9PBK32AXM":3,"skill-same:01M77MDKFM9RY8R4J9PBK32AXM":51},{"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},"01M77MDKFM9RY8R4J9PBK32AXM","setup",null,"Verify repo-hygiene's external prerequisites on this machine and report the effective destructive-guard toggle and the scope it actually applies at. The prerequisites are `git`, which the scan, git, stash, and tree tiers and the tracked-file guarantee all rest on, `node`, which launches the destructive guard, and the optional `ghq` the fleet batch actions enumerate repositories from. Use when: 'set up repo-hygiene', 'configure repo-hygiene', 'is repo-hygiene working', 'is the destructive guard on', 'why did tree-batch find no repos', or before a first clean on a new machine. Check-only: verifies, reports, and points at each remediation; installs nothing and there is nothing setup may write here. Re-runnable and safe.","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\u002Frepo-hygiene\u002Fskills\u002Fsetup\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\ndescription: \"Verify repo-hygiene's external prerequisites on this machine and report the effective destructive-guard toggle and the scope it actually applies at. The prerequisites are `git`, which the scan, git, stash, and tree tiers and the tracked-file guarantee all rest on, `node`, which launches the destructive guard, and the optional `ghq` the fleet batch actions enumerate repositories from. Use when: 'set up repo-hygiene', 'configure repo-hygiene', 'is repo-hygiene working', 'is the destructive guard on', 'why did tree-batch find no repos', or before a first clean on a new machine. Check-only: verifies, reports, and points at each remediation; installs nothing and there is nothing setup may write here. Re-runnable and safe.\"\nargument-hint: \"[check]\"\nuser-invocable: true\ndisable-model-invocation: true\nallowed-tools:\n  - \"Bash(command -v ghq*)\"\nshell: bash\n---\n\n## Pre-computed context\n\n`check`'s `ghq` probe ran at load time. Read this row instead of re-issuing it; it shows\nthe tool's path when present, or `absent` when missing:\n\n- `ghq`: !`command -v ghq 2>\u002Fdev\u002Fnull || echo absent`\n\nA row reading `[shell command execution disabled by policy]` carries no result: run that tool's\n`command -v` probe via Bash instead.\n\n- **Pointer**: for the placeholder a skipped load-time command leaves, fetch\n  [skills § Inject dynamic context](https:\u002F\u002Fcode.claude.com\u002Fdocs\u002Fen\u002Fskills#inject-dynamic-context)\n  live.\n- **As of**: 2026-11-11\n- **Recheck trigger**: the placeholder text changes.\n\n`git` is probed in the body, not here ([gather-block convention](https:\u002F\u002Fgithub.com\u002Fmelodic-software\u002Fclaude-code-plugins\u002Fblob\u002Fmain\u002Fdocs\u002Fconventions\u002Fgather-block\u002FREADME.md#the-pre-compute-block-runs-as-one-shell-invocation),\n\"The pre-compute block runs as one shell invocation\").\n\n## Purpose\n\nCheck-only setup under the Check-only carve-out (`docs\u002Fplugin-philosophy.md` \"Setup is explicit\nand repeatable\" in the marketplace repository): this plugin's configuration contains no\nwritable artifact, so `check` inspects, reports, and points at each remediation, and no `apply` is\noffered because there is nothing it could conformingly write. The warrant is the carve-out's\nexternal-prerequisites class: `git`, which every git-touching tier of `\u002Frepo-hygiene:clean` and\nthe tracked-file safety guarantee depend on, `node`, which launches the destructive guard, and the\noptional `ghq` the fleet batch actions\nenumerate repositories from. None is visible to a native configuration prompt; each is\nverifiable only. The `clean_destructive_guard_enabled` option is a native `userConfig` toggle whose only\nstored home is the `pluginConfigs` this contract forbids setup to write.\n\nAction routing: no argument or `check` runs the check. Non-interactive, never prompts.\n\n## `check` (read-only)\n\nThe clean skill and its bundled scripts are the single source of truth for what each tier requires.\n**Read it first**, with the Read tool, by the paths the steps below name: `${CLAUDE_PLUGIN_ROOT}\u002Fskills\u002Fclean\u002FSKILL.md` first, then each script a step names. Probe what it actually does, don't recite this file.\n\nNever search the plugin directory: no Glob, Grep, `find`, `ls` or `cd` in `${CLAUDE_PLUGIN_ROOT}`, and no shell `head` or `cat` of its files. The files below are all it needs. Then read the\npre-computed `ghq` row, run each remaining probe as its own Bash call with nothing chained to it, and report a PASS\u002FFAIL\u002FINFO\ntable with one remediation line per FAIL. Do not modify anything.\n\nInstall nothing, and run no mutating tier.\n\n1. **`git` on `PATH`**. `command -v git`, and report the resolved path and version. FAIL when\n   absent, and state what is lost rather than a blanket \"the plugin is broken\":\n   - `scan` resolves the repository through git and reports `not a git repository` when it cannot;\n     the `git`, `stash`, `tree`, and `tree-batch` tiers are git operations outright.\n   - The **any git-tracked file is off-limits** guarantee is enforced against the index by the\n     shared `${CLAUDE_PLUGIN_ROOT}\u002Fskills\u002Fclean\u002Fscripts\u002Flib\u002Fclean-common.sh` (Read that file to confirm it)\n     (`git ls-files --error-unmatch`), so even the `caches` and\n     `build` tiers reach git through it, as does restoring a tracked file deleted by reparse-point\n     traversal during a `tree` clean. No tier is safe to run without git.\n2. **`ghq`** (optional). The pre-computed `ghq` row. Present: INFO, `ghq list -p` can feed\n   `tree-batch` and the other `*-batch` actions. Absent: INFO, not a defect, the batch actions still\n   take `--repo` (repeatable, glob-expanded) and `--repos-from FILE|-`; only the `ghq`-derived\n   enumeration is unavailable. Report this rather than letting an empty repo list look like a bug.\n3. **A POSIX shell for the bundled scripts**. Every tier script and the destructive guard are\n   `bash`. On Windows that means Git Bash must be present. The guard is exec form: `command` is\n   `node`, and `${CLAUDE_PLUGIN_ROOT}\u002Fhooks\u002Fexec-bash.mjs` (Read it to confirm) finds bash (on Windows `CLAUDE_CODE_GIT_BASH_PATH`, then\n   `Git\\bin\\bash.exe`, then `PATH`, never `System32\\bash.exe`; \u003C!-- portability-ok: Windows path, not a shell regex -->\n   elsewhere `PATH`, then `\u002Fbin\u002Fbash` and `\u002Fusr\u002Fbin\u002Fbash`).\n   - **Pointer**: for how an exec-form hook launches its command, fetch\n     \u003Chttps:\u002F\u002Fcode.claude.com\u002Fdocs\u002Fen\u002Fhooks#exec-form-and-shell-form> live.\n\n   Report the shell as INFO on Unix; FAIL on Windows when no Git Bash resolves, since the\n   scripts and the guard alike cannot launch.\n4. **`node` on `PATH`**. `command -v node`, and report the resolved path and version. Probe it\n   through Bash, so it works without the launcher. FAIL when absent: every hook row runs\n   `node hooks\u002Fexec-bash.mjs`, so without it the guard does not launch and is not enforced.\n\n   - **Pointer**: for whether Claude Code's install uses Node at runtime, fetch\n     \u003Chttps:\u002F\u002Fcode.claude.com\u002Fdocs\u002Fen\u002Fsetup#install-with-npm> live.\n\n5. **Destructive-guard registration and toggle**. INFO, and be precise about *where* the guard\n   lives, because the answer is the reason it is session-scoped:\n   - It registers from the frontmatter `hooks:` block in `${CLAUDE_PLUGIN_ROOT}\u002Fskills\u002Fclean\u002FSKILL.md`,\n     not from a plugin-level `hooks\u002Fhooks.json`, which this plugin does not ship. Claude Code\n     arms it once `\u002Frepo-hygiene:clean` is invoked and keeps it armed for the rest of that session,\n     so a session that never invoked the skill has no guard and nothing is wrong with that. Read that SKILL.md for the block (it runs `${CLAUDE_PLUGIN_ROOT}\u002Fskills\u002Fclean\u002Fscripts\u002Fdestructive-guard.sh`); never look for a `hooks.json` or list `hooks\u002F`.\n   - Report the effective `${user_config.clean_destructive_guard_enabled}` (an unexpanded token or\n     an empty value means the manifest default `true`). Read it from this text as rendered; never\n     echo it through Bash, where an unexpanded token is invalid shell syntax and the call is\n     refused. A change made now is observed only in a **fresh session**.\n\n     - **Pointer**: for when a saved value reaches skill content, fetch\n       [plugins manifest reference § Reference a saved value](https:\u002F\u002Fcode.claude.com\u002Fdocs\u002Fen\u002Fplugins\u002Fmanifest-reference#reference-a-saved-value)\n       live.\n   - The option is **user-scoped**: plugin option values are read from user, `--settings`, and\n     managed settings only, never from a project's `.claude\u002Fsettings.json`. So there is no\n     per-repository value of this toggle. To vary the behavior for one repository, enable or disable\n     the plugin in that project's `enabledPlugins` instead.\n\n## Remediation guidance (printed by `check`; the operator applies it)\n\nThe prerequisites are system tools and the one option lives in Claude Code's native\nplugin configuration (Check-only carve-out, external-prerequisites and native-`userConfig`\nclasses), so `check` closes by pointing at each resolution rather than writing. Re-running it\nafter everything passes changes nothing and reports \"already configured\":\n\n- **Missing `git`:** the platform's own install channel (\u003Chttps:\u002F\u002Fgit-scm.com\u002Fdownloads>). This\n  plugin never downloads a tool.\n- **Missing `ghq` and fleet actions wanted:** install it (\u003Chttps:\u002F\u002Fgithub.com\u002Fx-motemen\u002Fghq>), or\n  keep using `--repo` \u002F `--repos-from` and say so. This is a convenience, not a blocker.\n- **Missing `node`:** install Node.js (\u003Chttps:\u002F\u002Fnodejs.org\u002Fen\u002Fdownload>) and put it on `PATH`. Until\n  then the destructive guard is not enforced.\n- **Missing Git Bash on Windows:** install Git for Windows; nothing in this plugin runs without it.\n- **Toggle off (or on):** set `clean_destructive_guard_enabled` to `true` or `false` through\n  Claude Code's native flow, interactively with `\u002Fplugin configure repo-hygiene@\u003Cmarketplace>` or\n  by a headless route, as the marketplace's 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. This skill never\n  writes user settings or `pluginConfigs`. Afterwards rerun `check` in a **fresh session**, since a\n  same-session `check` can still show the old value, and report the observed effective toggle\n  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## What this skill does NOT do\n\n- Scan, clean, prune, or reset anything. Those are `\u002Frepo-hygiene:clean`'s tiers, with their own\n  dry-run-first and confirmation contract.\n- Install `git`, `ghq`, or any tool. Guidance only.\n- Write the plugin cache, Claude Code user settings, or `pluginConfigs`. Nor any other Claude Code\n  settings file.\n","## Pre-computed context\n\n`check`'s `ghq` probe ran at load time. Read this row instead of re-issuing it; it shows\nthe tool's path when present, or `absent` when missing:\n\n- `ghq`: !`command -v ghq 2>\u002Fdev\u002Fnull || echo absent`\n\nA row reading `[shell command execution disabled by policy]` carries no result: run that tool's\n`command -v` probe via Bash instead.\n\n- **Pointer**: for the placeholder a skipped load-time command leaves, fetch\n  [skills § Inject dynamic context](https:\u002F\u002Fcode.claude.com\u002Fdocs\u002Fen\u002Fskills#inject-dynamic-context)\n  live.\n- **As of**: 2026-11-11\n- **Recheck trigger**: the placeholder text changes.\n\n`git` is probed in the body, not here ([gather-block convention](https:\u002F\u002Fgithub.com\u002Fmelodic-software\u002Fclaude-code-plugins\u002Fblob\u002Fmain\u002Fdocs\u002Fconventions\u002Fgather-block\u002FREADME.md#the-pre-compute-block-runs-as-one-shell-invocation),\n\"The pre-compute block runs as one shell invocation\").\n\n## Purpose\n\nCheck-only setup under the Check-only carve-out (`docs\u002Fplugin-philosophy.md` \"Setup is explicit\nand repeatable\" in the marketplace repository): this plugin's configuration contains no\nwritable artifact, so `check` inspects, reports, and points at each remediation, and no `apply` is\noffered because there is nothing it could conformingly write. The warrant is the carve-out's\nexternal-prerequisites class: `git`, which every git-touching tier of `\u002Frepo-hygiene:clean` and\nthe tracked-file safety guarantee depend on, `node`, which launches the destructive guard, and the\noptional `ghq` the fleet batch actions\nenumerate repositories from. None is visible to a native configuration prompt; each is\nverifiable only. The `clean_destructive_guard_enabled` option is a native `userConfig` toggle whose only\nstored home is the `pluginConfigs` this contract forbids setup to write.\n\nAction routing: no argument or `check` runs the check. Non-interactive, never prompts.\n\n## `check` (read-only)\n\nThe clean skill and its bundled scripts are the single source of truth for what each tier requires.\n**Read it first**, with the Read tool, by the paths the steps below name: `${CLAUDE_PLUGIN_ROOT}\u002Fskills\u002Fclean\u002FSKILL.md` first, then each script a step names. Probe what it actually does, don't recite this file.\n\nNever search the plugin directory: no Glob, Grep, `find`, `ls` or `cd` in `${CLAUDE_PLUGIN_ROOT}`, and no shell `head` or `cat` of its files. The files below are all it needs. Then read the\npre-computed `ghq` row, run each remaining probe as its own Bash call with nothing chained to it, and report a PASS\u002FFAIL\u002FINFO\ntable with one remediation line per FAIL. Do not modify anything.\n\nInstall nothing, and run no mutating tier.\n\n1. **`git` on `PATH`**. `command -v git`, and report the resolved path and version. FAIL when\n   absent, and state what is lost rather than a blanket \"the plugin is broken\":\n   - `scan` resolves the repository through git and reports `not a git repository` when it cannot;\n     the `git`, `stash`, `tree`, and `tree-batch` tiers are git operations outright.\n   - The **any git-tracked file is off-limits** guarantee is enforced against the index by the\n     shared `${CLAUDE_PLUGIN_ROOT}\u002Fskills\u002Fclean\u002Fscripts\u002Flib\u002Fclean-common.sh` (Read that file to confirm it)\n     (`git ls-files --error-unmatch`), so even the `caches` and\n     `build` tiers reach git through it, as does restoring a tracked file deleted by reparse-point\n     traversal during a `tree` clean. No tier is safe to run without git.\n2. **`ghq`** (optional). The pre-computed `ghq` row. Present: INFO, `ghq list -p` can feed\n   `tree-batch` and the other `*-batch` actions. Absent: INFO, not a defect, the batch actions still\n   take `--repo` (repeatable, glob-expanded) and `--repos-from FILE|-`; only the `ghq`-derived\n   enumeration is unavailable. Report this rather than letting an empty repo list look like a bug.\n3. **A POSIX shell for the bundled scripts**. Every tier script and the destructive guard are\n   `bash`. On Windows that means Git Bash must be present. The guard is exec form: `command` is\n   `node`, and `${CLAUDE_PLUGIN_ROOT}\u002Fhooks\u002Fexec-bash.mjs` (Read it to confirm) finds bash (on Windows `CLAUDE_CODE_GIT_BASH_PATH`, then\n   `Git\\bin\\bash.exe`, then `PATH`, never `System32\\bash.exe`; \u003C!-- portability-ok: Windows path, not a shell regex -->\n   elsewhere `PATH`, then `\u002Fbin\u002Fbash` and `\u002Fusr\u002Fbin\u002Fbash`).\n   - **Pointer**: for how an exec-form hook launches its command, fetch\n     \u003Chttps:\u002F\u002Fcode.claude.com\u002Fdocs\u002Fen\u002Fhooks#exec-form-and-shell-form> live.\n\n   Report the shell as INFO on Unix; FAIL on Windows when no Git Bash resolves, since the\n   scripts and the guard alike cannot launch.\n4. **`node` on `PATH`**. `command -v node`, and report the resolved path and version. Probe it\n   through Bash, so it works without the launcher. FAIL when absent: every hook row runs\n   `node hooks\u002Fexec-bash.mjs`, so without it the guard does not launch and is not enforced.\n\n   - **Pointer**: for whether Claude Code's install uses Node at runtime, fetch\n     \u003Chttps:\u002F\u002Fcode.claude.com\u002Fdocs\u002Fen\u002Fsetup#install-with-npm> live.\n\n5. **Destructive-guard registration and toggle**. INFO, and be precise about *where* the guard\n   lives, because the answer is the reason it is session-scoped:\n   - It registers from the frontmatter `hooks:` block in `${CLAUDE_PLUGIN_ROOT}\u002Fskills\u002Fclean\u002FSKILL.md`,\n     not from a plugin-level `hooks\u002Fhooks.json`, which this plugin does not ship. Claude Code\n     arms it once `\u002Frepo-hygiene:clean` is invoked and keeps it armed for the rest of that session,\n     so a session that never invoked the skill has no guard and nothing is wrong with that. Read that SKILL.md for the block (it runs `${CLAUDE_PLUGIN_ROOT}\u002Fskills\u002Fclean\u002Fscripts\u002Fdestructive-guard.sh`); never look for a `hooks.json` or list `hooks\u002F`.\n   - Report the effective `${user_config.clean_destructive_guard_enabled}` (an unexpanded token or\n     an empty value means the manifest default `true`). Read it from this text as rendered; never\n     echo it through Bash, where an unexpanded token is invalid shell syntax and the call is\n     refused. A change made now is observed only in a **fresh session**.\n\n     - **Pointer**: for when a saved value reaches skill content, fetch\n       [plugins manifest reference § Reference a saved value](https:\u002F\u002Fcode.claude.com\u002Fdocs\u002Fen\u002Fplugins\u002Fmanifest-reference#reference-a-saved-value)\n       live.\n   - The option is **user-scoped**: plugin option values are read from user, `--settings`, and\n     managed settings only, never from a project's `.claude\u002Fsettings.json`. So there is no\n     per-repository value of this toggle. To vary the behavior for one repository, enable or disable\n     the plugin in that project's `enabledPlugins` instead.\n\n## Remediation guidance (printed by `check`; the operator applies it)\n\nThe prerequisites are system tools and the one option lives in Claude Code's native\nplugin configuration (Check-only carve-out, external-prerequisites and native-`userConfig`\nclasses), so `check` closes by pointing at each resolution rather than writing. Re-running it\nafter everything passes changes nothing and reports \"already configured\":\n\n- **Missing `git`:** the platform's own install channel (\u003Chttps:\u002F\u002Fgit-scm.com\u002Fdownloads>). This\n  plugin never downloads a tool.\n- **Missing `ghq` and fleet actions wanted:** install it (\u003Chttps:\u002F\u002Fgithub.com\u002Fx-motemen\u002Fghq>), or\n  keep using `--repo` \u002F `--repos-from` and say so. This is a convenience, not a blocker.\n- **Missing `node`:** install Node.js (\u003Chttps:\u002F\u002Fnodejs.org\u002Fen\u002Fdownload>) and put it on `PATH`. Until\n  then the destructive guard is not enforced.\n- **Missing Git Bash on Windows:** install Git for Windows; nothing in this plugin runs without it.\n- **Toggle off (or on):** set `clean_destructive_guard_enabled` to `true` or `false` through\n  Claude Code's native flow, interactively with `\u002Fplugin configure repo-hygiene@\u003Cmarketplace>` or\n  by a headless route, as the marketplace's 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. This skill never\n  writes user settings or `pluginConfigs`. Afterwards rerun `check` in a **fresh session**, since a\n  same-session `check` can still show the old value, and report the observed effective toggle\n  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## What this skill does NOT do\n\n- Scan, clean, prune, or reset anything. Those are `\u002Frepo-hygiene:clean`'s tiers, with their own\n  dry-run-first and confirmation contract.\n- Install `git`, `ghq`, or any tool. Guidance only.\n- Write the plugin cache, Claude Code user settings, or `pluginConfigs`. Nor any other Claude Code\n  settings file.\n",{"shell":24,"description":7,"allowed-tools":25,"argument-hint":27,"user-invocable":28,"disable-model-invocation":28},"bash",[26],"Bash(command -v ghq*)","[check]",true,"main","d0e68c3f36b92a1d6381f0ba0060d7a0b8b886c5","plugins\u002Frepo-hygiene\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":39,"prompt":49,"zipAvailable":28},[40,43,46],{"tool":41,"command":42},"npx","npx skills add melodic-software\u002Fclaude-code-plugins --skill setup",{"tool":44,"command":45},"bunx","bunx skills add melodic-software\u002Fclaude-code-plugins --skill setup",{"tool":47,"command":48},"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\u002Frepo-hygiene\u002Fskills\u002Fsetup\u002FSKILL.md",[],[52,59,66,73,78,85],{"skillNo":53,"name":54,"nameZh":6,"description":55,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":56,"categories":57,"keywords":58,"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":60,"name":61,"nameZh":6,"description":62,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":63,"categories":64,"keywords":65,"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":67,"name":68,"nameZh":6,"description":69,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":70,"categories":71,"keywords":72,"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":74,"name":68,"nameZh":6,"description":69,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":75,"categories":76,"keywords":77,"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":79,"name":80,"nameZh":6,"description":81,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":82,"categories":83,"keywords":84,"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":86,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":89,"categories":90,"keywords":91,"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",[],[]]