[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M77MABMR3MJKBT592N08ENWD":3,"skill-same:01M77MABMR3MJKBT592N08ENWD":57},{"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},"01M77MABMR3MJKBT592N08ENWD","use",null,"Reach Anthropic's first-party playground capability in one step: verify the upstream playground plugin is installed, invoke its skill for interactive single-file HTML explorers (controls beside a live preview, output is a prompt to paste back), or emit the exact install commands when it is absent. Use when: 'make me a playground', 'interactive explorer for X', 'install the playground plugin', 'critique this document with approve\u002Freject controls', or any ask to tune a parameter space visually and see the result (sliders, balancing, exploring parameters). Also carries field-tested prompt recipes, delivery guidance for cloud and remote sessions where a local browser cannot open, and known-limitation notes. This wrapper generates nothing itself; the upstream skill owns generation. Not for choosing a visual form for conversation content (a visualization capability owns that) or for throwaway variations of the project's own UI (a prototyping capability owns that).","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\u002Fplaygrounds\u002Fskills\u002Fuse\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\ndescription: \"Reach Anthropic's first-party playground capability in one step: verify the upstream playground plugin is installed, invoke its skill for interactive single-file HTML explorers (controls beside a live preview, output is a prompt to paste back), or emit the exact install commands when it is absent. Use when: 'make me a playground', 'interactive explorer for X', 'install the playground plugin', 'critique this document with approve\u002Freject controls', or any ask to tune a parameter space visually and see the result (sliders, balancing, exploring parameters). Also carries field-tested prompt recipes, delivery guidance for cloud and remote sessions where a local browser cannot open, and known-limitation notes. This wrapper generates nothing itself; the upstream skill owns generation. Not for choosing a visual form for conversation content (a visualization capability owns that) or for throwaway variations of the project's own UI (a prototyping capability owns that).\"\nargument-hint: \"[what to explore]\"\nuser-invocable: true\ndisable-model-invocation: false\nmetadata:\n  workflow-stage: anytime\n  summary: Route playground requests to the first-party plugin, or install it, with recipes and guidance\n---\n\n# Use playgrounds\n\n## Purpose\n\nConnect a playground-shaped request (an interactive parameter space the user wants to\nmanipulate visually, with the result flowing back as a prompt) to the maintained\nfirst-party implementation: the `playground` skill from the `playground` plugin on the\n`claude-plugins-official` marketplace. This skill routes, installs, and advises. It\nnever builds a playground itself.\n\n## Step 1: Presence check (provenance, not prose)\n\nDetermine whether the upstream plugin is installed by its identity, not its wording:\n\n- Run `claude plugin list` and look for the `playground` plugin sourced from\n  `claude-plugins-official`. That marketplace-qualified install record is the\n  authoritative signal.\n- Where the CLI is unavailable to the session, fall back to the session's skill\n  listing: a bare `playground` skill whose description says it creates interactive\n  HTML playgrounds. Treat the description comparison as ADVISORY only; upstream may\n  reword it at any time. Never conclude \"absent\" from wording alone when the name is\n  present.\n- A local skill can shadow the upstream name. When the listed `playground` skill's\n  description clearly describes something other than an interactive-explorer builder,\n  say a shadow is likely, then let provenance decide: with the install record\n  confirming `playground@claude-plugins-official`, warn about the shadow and invoke\n  the namespaced `playground:playground` form; with no install record confirming it,\n  take the install\u002Fguidance path, and never invoke the shadowing skill.\n\nHow a plugin skill's namespaced name and a same-named local skill resolve is\nClaude Code's to define; this skill always addresses the upstream skill by its\nnamespaced form.\n\n- **Pointer**: when a shadow is suspected or the bare name resolves unexpectedly,\n  fetch [Skills: Resolve skills that share a name](https:\u002F\u002Fcode.claude.com\u002Fdocs\u002Fen\u002Fskills#resolve-skills-that-share-a-name)\n  live.\n\n## Step 2: Present, so invoke\n\nWhen the upstream skill is present, invoke it via the Skill tool with the user's\nbrief as arguments, using the namespaced form `playground:playground`\n([Step 1](#step-1-presence-check-provenance-not-prose)'s pointer covers why). Pass the request\nas stated; the upstream skill owns template choice and generation. When the user names\nstyles to leave out (italic accent words, pill-shaped buttons), carry that list in the\nbrief; when they dislike a choice in the generated page, add it to the list and invoke\nagain. A general \"make it look less generic\" only swaps one default for another. If\nthe invocation is refused, do not retry blind: tell the user the skill is installed but this session\ncould not invoke it, and suggest they run it themselves by asking for a playground in\ntheir own words.\n\n## Step 3: Absent, so uplift\n\nThis plugin declares the upstream dependency in its manifest, so where Claude Code\nresolves plugin dependencies it handles the install itself. In contexts where\nresolution does not run (a synced or cloud session, a manual setup), emit the\ncommands directly:\n\n```shell\n\u002Fplugin marketplace add anthropics\u002Fclaude-plugins-official\n\u002Fplugin install playground@claude-plugins-official\n```\n\nScope guidance: `user` scope makes the capability available everywhere; `project`\nscope pins it to one repository. Include the marketplace-add step only when the\ninstall command reports the marketplace is unknown. If the install is blocked by\norganization policy, say so plainly and stop; there is no workaround to offer.\n\n- **Pointer**: when an install did not resolve the dependency, or reports why it\n  could not, fetch [Plugin dependencies: How dependencies behave for your users](https:\u002F\u002Fcode.claude.com\u002Fdocs\u002Fen\u002Fplugins\u002Fdependencies#how-dependencies-behave-for-your-users)\n  and [Install plugins: Plugins with dependencies](https:\u002F\u002Fcode.claude.com\u002Fdocs\u002Fen\u002Fplugins\u002Finstall#plugins-with-dependencies)\n  live.\n\n## Step 4: Delivery, especially off the desktop\n\nHow the upstream skill writes and opens its HTML file is that skill's to define.\nFeature-detect the delivery path instead of assuming its opening step reaches the\nuser:\n\n1. A desktop session with a local browser: let the upstream flow open the file.\n2. A session that can publish an Artifact: offer to publish the generated HTML so the\n   user gets a link. State that the page runs under the artifact sandbox, and confirm\n   the copy-prompt button works there before promising the round trip.\n3. A session with a file-send surface (remote control, managed cloud): send the HTML\n   file to the user to open locally.\n4. None of the above: report the file's absolute path and say how to open it.\n\nDegrade visibly at every tier; never name a delivery surface as guaranteed.\n\n- **Pointer**: when deciding whether the upstream flow can open the file in this\n  session, fetch [the playground skill § How to use this skill](https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fclaude-plugins-official\u002Fblob\u002Fmain\u002Fplugins\u002Fplayground\u002Fskills\u002Fplayground\u002FSKILL.md#how-to-use-this-skill)\n  live.\n\n## Recipes (field-tested)\n\nFrom the plugin author's published examples, verbatim shapes to adapt:\n\n- \"Use the playground skill to create a playground that helps me explore new layout\n  changes to the AskUserQuestion Tool\"\n- \"Use the playground skill to review my SKILL.md and give me inline suggestions I\n  can approve, reject or comment\"\n- \"Use the playground skill to tweak my intro screen to be more interesting and\n  delightful\"\n- \"Use the playground skill to show how this email agent codebase works and let me\n  comment on particular nodes in the architecture to ask questions, make edits, etc\"\n- \"Use the playground skill to help me balance the 'Inferno' hero's deck\"\n\nRepo-native recipe for this marketplace: \"Use the playground skill to review\nplugins\u002F\u003Cname>\u002Fskills\u002F\u003Cskill>\u002FSKILL.md and give me inline suggestions I can approve,\nreject or comment\" turns skill-file review into an interactive pass.\n\n## Known limitations\n\nConsumer guidance for the generated playgrounds lives in\n[`context\u002Fconsumer-notes.md`](context\u002Fconsumer-notes.md); read it before relying on a\ngenerated playground for anything beyond personal exploration.\n\n## Gotchas\n\n- A listed `playground` skill name proves presence of A skill, not THE skill, which\n  is why Step 1 judges by install record and treats wording as advisory.\n- The copy-prompt button is the product; a sandboxed page (an Artifact) can restrict\n  clipboard access, so confirm the round trip once before a long exploration.\n- A summarizing fetch of the upstream marketplace can misreport its contents;\n  verify upstream facts against raw files or the install record, never a summary.\n\n## Boundary\n\n- Choosing the best visual FORM for conversation content is the visualization\n  capability's job; this skill fires only when the user wants an interactive,\n  manipulable explorer whose output returns as a prompt.\n- Throwaway visual variations of your own project's UI are the prototyping\n  capability's job; a playground explores a parameter space, not your codebase's\n  routes.\n- Generation, templates, and the playground page's own design belong to the upstream\n  skill; nothing here overrides them.\n","# Use playgrounds\n\n## Purpose\n\nConnect a playground-shaped request (an interactive parameter space the user wants to\nmanipulate visually, with the result flowing back as a prompt) to the maintained\nfirst-party implementation: the `playground` skill from the `playground` plugin on the\n`claude-plugins-official` marketplace. This skill routes, installs, and advises. It\nnever builds a playground itself.\n\n## Step 1: Presence check (provenance, not prose)\n\nDetermine whether the upstream plugin is installed by its identity, not its wording:\n\n- Run `claude plugin list` and look for the `playground` plugin sourced from\n  `claude-plugins-official`. That marketplace-qualified install record is the\n  authoritative signal.\n- Where the CLI is unavailable to the session, fall back to the session's skill\n  listing: a bare `playground` skill whose description says it creates interactive\n  HTML playgrounds. Treat the description comparison as ADVISORY only; upstream may\n  reword it at any time. Never conclude \"absent\" from wording alone when the name is\n  present.\n- A local skill can shadow the upstream name. When the listed `playground` skill's\n  description clearly describes something other than an interactive-explorer builder,\n  say a shadow is likely, then let provenance decide: with the install record\n  confirming `playground@claude-plugins-official`, warn about the shadow and invoke\n  the namespaced `playground:playground` form; with no install record confirming it,\n  take the install\u002Fguidance path, and never invoke the shadowing skill.\n\nHow a plugin skill's namespaced name and a same-named local skill resolve is\nClaude Code's to define; this skill always addresses the upstream skill by its\nnamespaced form.\n\n- **Pointer**: when a shadow is suspected or the bare name resolves unexpectedly,\n  fetch [Skills: Resolve skills that share a name](https:\u002F\u002Fcode.claude.com\u002Fdocs\u002Fen\u002Fskills#resolve-skills-that-share-a-name)\n  live.\n\n## Step 2: Present, so invoke\n\nWhen the upstream skill is present, invoke it via the Skill tool with the user's\nbrief as arguments, using the namespaced form `playground:playground`\n([Step 1](#step-1-presence-check-provenance-not-prose)'s pointer covers why). Pass the request\nas stated; the upstream skill owns template choice and generation. When the user names\nstyles to leave out (italic accent words, pill-shaped buttons), carry that list in the\nbrief; when they dislike a choice in the generated page, add it to the list and invoke\nagain. A general \"make it look less generic\" only swaps one default for another. If\nthe invocation is refused, do not retry blind: tell the user the skill is installed but this session\ncould not invoke it, and suggest they run it themselves by asking for a playground in\ntheir own words.\n\n## Step 3: Absent, so uplift\n\nThis plugin declares the upstream dependency in its manifest, so where Claude Code\nresolves plugin dependencies it handles the install itself. In contexts where\nresolution does not run (a synced or cloud session, a manual setup), emit the\ncommands directly:\n\n```shell\n\u002Fplugin marketplace add anthropics\u002Fclaude-plugins-official\n\u002Fplugin install playground@claude-plugins-official\n```\n\nScope guidance: `user` scope makes the capability available everywhere; `project`\nscope pins it to one repository. Include the marketplace-add step only when the\ninstall command reports the marketplace is unknown. If the install is blocked by\norganization policy, say so plainly and stop; there is no workaround to offer.\n\n- **Pointer**: when an install did not resolve the dependency, or reports why it\n  could not, fetch [Plugin dependencies: How dependencies behave for your users](https:\u002F\u002Fcode.claude.com\u002Fdocs\u002Fen\u002Fplugins\u002Fdependencies#how-dependencies-behave-for-your-users)\n  and [Install plugins: Plugins with dependencies](https:\u002F\u002Fcode.claude.com\u002Fdocs\u002Fen\u002Fplugins\u002Finstall#plugins-with-dependencies)\n  live.\n\n## Step 4: Delivery, especially off the desktop\n\nHow the upstream skill writes and opens its HTML file is that skill's to define.\nFeature-detect the delivery path instead of assuming its opening step reaches the\nuser:\n\n1. A desktop session with a local browser: let the upstream flow open the file.\n2. A session that can publish an Artifact: offer to publish the generated HTML so the\n   user gets a link. State that the page runs under the artifact sandbox, and confirm\n   the copy-prompt button works there before promising the round trip.\n3. A session with a file-send surface (remote control, managed cloud): send the HTML\n   file to the user to open locally.\n4. None of the above: report the file's absolute path and say how to open it.\n\nDegrade visibly at every tier; never name a delivery surface as guaranteed.\n\n- **Pointer**: when deciding whether the upstream flow can open the file in this\n  session, fetch [the playground skill § How to use this skill](https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fclaude-plugins-official\u002Fblob\u002Fmain\u002Fplugins\u002Fplayground\u002Fskills\u002Fplayground\u002FSKILL.md#how-to-use-this-skill)\n  live.\n\n## Recipes (field-tested)\n\nFrom the plugin author's published examples, verbatim shapes to adapt:\n\n- \"Use the playground skill to create a playground that helps me explore new layout\n  changes to the AskUserQuestion Tool\"\n- \"Use the playground skill to review my SKILL.md and give me inline suggestions I\n  can approve, reject or comment\"\n- \"Use the playground skill to tweak my intro screen to be more interesting and\n  delightful\"\n- \"Use the playground skill to show how this email agent codebase works and let me\n  comment on particular nodes in the architecture to ask questions, make edits, etc\"\n- \"Use the playground skill to help me balance the 'Inferno' hero's deck\"\n\nRepo-native recipe for this marketplace: \"Use the playground skill to review\nplugins\u002F\u003Cname>\u002Fskills\u002F\u003Cskill>\u002FSKILL.md and give me inline suggestions I can approve,\nreject or comment\" turns skill-file review into an interactive pass.\n\n## Known limitations\n\nConsumer guidance for the generated playgrounds lives in\n[`context\u002Fconsumer-notes.md`](context\u002Fconsumer-notes.md); read it before relying on a\ngenerated playground for anything beyond personal exploration.\n\n## Gotchas\n\n- A listed `playground` skill name proves presence of A skill, not THE skill, which\n  is why Step 1 judges by install record and treats wording as advisory.\n- The copy-prompt button is the product; a sandboxed page (an Artifact) can restrict\n  clipboard access, so confirm the round trip once before a long exploration.\n- A summarizing fetch of the upstream marketplace can misreport its contents;\n  verify upstream facts against raw files or the install record, never a summary.\n\n## Boundary\n\n- Choosing the best visual FORM for conversation content is the visualization\n  capability's job; this skill fires only when the user wants an interactive,\n  manipulable explorer whose output returns as a prompt.\n- Throwaway visual variations of your own project's UI are the prototyping\n  capability's job; a playground explores a parameter space, not your codebase's\n  routes.\n- Generation, templates, and the playground page's own design belong to the upstream\n  skill; nothing here overrides them.\n",{"metadata":24,"description":7,"argument-hint":27,"user-invocable":28,"disable-model-invocation":20},{"summary":25,"workflow-stage":26},"Route playground requests to the first-party plugin, or install it, with recipes and guidance","anytime","[what to explore]",true,"main","d0e68c3f36b92a1d6381f0ba0060d7a0b8b886c5","plugins\u002Fplaygrounds\u002Fskills\u002Fuse",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 use",{"tool":44,"command":45},"bunx","bunx skills add melodic-software\u002Fclaude-code-plugins --skill use",{"tool":47,"command":48},"pnpm","pnpm dlx skills add melodic-software\u002Fclaude-code-plugins --skill use","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fmelodic-software\u002Fclaude-code-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fplaygrounds\u002Fskills\u002Fuse\u002FSKILL.md",[51],{"path":52,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":55,"sourceHtmlUrl":56},"context\u002Fconsumer-notes.md","REFERENCE","参考文档",1853,"https:\u002F\u002Fgithub.com\u002Fmelodic-software\u002Fclaude-code-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fplaygrounds\u002Fskills\u002Fuse\u002Fcontext\u002Fconsumer-notes.md",[58,65,72,79,84,91],{"skillNo":59,"name":60,"nameZh":6,"description":61,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":62,"categories":63,"keywords":64,"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":66,"name":67,"nameZh":6,"description":68,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":69,"categories":70,"keywords":71,"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":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"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":80,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":81,"categories":82,"keywords":83,"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":85,"name":86,"nameZh":6,"description":87,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":88,"categories":89,"keywords":90,"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":92,"name":93,"nameZh":6,"description":94,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":95,"categories":96,"keywords":97,"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",[],[]]