[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7AFNWMFYB3PWST7BWMZSZFX":3,"skill-same:01M7AFNWMFYB3PWST7BWMZSZFX":49},{"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":28,"commitSha":29,"skillDirectory":30,"forksCount":31,"repositoryHtmlUrl":32,"repositoryHomepageUrl":32,"ownerHtmlUrl":33,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":34,"install":35,"resources":48},"01M7AFNWMFYB3PWST7BWMZSZFX","trove-explain",null,"Explain code, architecture, or data flow at the appropriate level for the audience. Use when someone needs to understand unfamiliar code, a module, or system design.","bravew\u002Ftrove","bravew","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F10855844?v=4","01M7ACJ91JZSQYHT81XPVYR7VA","Yong","01M7AFERNR92HDPGNGP5QA16DM",10,"MIT","https:\u002F\u002Fgithub.com\u002Fbravew\u002Ftrove\u002Fblob\u002Fmain\u002Fplugins\u002Ftrove-dev\u002Fskills\u002Ftrove-explain\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: trove-explain\ndescription: \"Explain code, architecture, or data flow at the appropriate level for the audience. Use when someone needs to understand unfamiliar code, a module, or system design.\"\nwhen_to_use: \"explain this code; what does this do; walk me through\"\nmetadata:\n  trove-category: engineering\n  trove-category-label: Engineering\n---\n\u003C!-- AUTO-GENERATED from SKILL.md.tmpl — do not edit directly -->\n\u003C!-- Regenerate: bun run build:skills -->\n\n## Session Init\n\nThis skill ships Trove conventions. Prefer existing project patterns over generic best practices when they conflict.\n\n# Code Explanation Skill\n\n## Complexity gate\n\nSize the effort to the subsystem before diving in:\n\n- **Simple** (one module, one flow): explain it in a single pass.\n- **Complex** (multiple subsystems, unclear ownership): fan out 2-4 bounded, read-only sub-agents to map distinct areas in parallel, then synthesize their findings into one mental model. Use the delegated-exploration phrasing in [docs\u002Forchestration.md](..\u002F..\u002Fdocs\u002Forchestration.md); fan out only when the subsystem warrants it (parallel agents cost linearly).\n\nRead the actual code. Do not guess behavior from file or symbol names — the name lies often enough that a guess is the most common explanation failure.\n\n## Approach\n\nWhen explaining code or architecture:\n\n1. **Start with the \"why\"** — what problem does this solve?\n2. **Show the big picture** — how does it fit in the larger system?\n3. **Walk through the flow** — trace data from entry to exit\n4. **Highlight the non-obvious** — gotchas, trade-offs, design decisions\n\n## Explanation Levels\n\nAdapt your explanation depth to the audience:\n\n| Level | Audience | Focus |\n|-------|----------|-------|\n| **High** | PM, Designer | What it does, user impact |\n| **Mid** | New developer | How it works, key patterns |\n| **Deep** | Experienced dev | Why decisions were made, edge cases |\n\n## Output Format\n\n```markdown\n## What This Does\nOne-paragraph summary of purpose and behavior.\n\n## Architecture\nHow components connect (use diagrams when helpful).\n\n## Key Flow\nStep-by-step trace through the main path.\n\n## Design Decisions\nWhy it's built this way (trade-offs, alternatives considered).\n\n## Gotchas\nThings that might surprise you or cause bugs.\n```\n\n## Critique mode (optional)\n\nWhen asked to critique (not just explain) the architecture, explain first, then surface findings and sort each into: **Act on** (real problem, worth fixing now), **Consider** (worth weighing), **Noted** (minor), **Dismissed** (raised and rejected, with the reason). Keep it lightweight; the heavyweight adversarial pass is `trove-review`'s deep mode.\n\n## Best Practices\n\n- Use code snippets to illustrate, but annotate them\n- Prefer diagrams (ASCII or mermaid) for architecture\n- Link to related code files when referencing them\n- Keep explanations under 500 words unless requested otherwise\n","\u003C!-- AUTO-GENERATED from SKILL.md.tmpl — do not edit directly -->\n\u003C!-- Regenerate: bun run build:skills -->\n\n## Session Init\n\nThis skill ships Trove conventions. Prefer existing project patterns over generic best practices when they conflict.\n\n# Code Explanation Skill\n\n## Complexity gate\n\nSize the effort to the subsystem before diving in:\n\n- **Simple** (one module, one flow): explain it in a single pass.\n- **Complex** (multiple subsystems, unclear ownership): fan out 2-4 bounded, read-only sub-agents to map distinct areas in parallel, then synthesize their findings into one mental model. Use the delegated-exploration phrasing in [docs\u002Forchestration.md](..\u002F..\u002Fdocs\u002Forchestration.md); fan out only when the subsystem warrants it (parallel agents cost linearly).\n\nRead the actual code. Do not guess behavior from file or symbol names — the name lies often enough that a guess is the most common explanation failure.\n\n## Approach\n\nWhen explaining code or architecture:\n\n1. **Start with the \"why\"** — what problem does this solve?\n2. **Show the big picture** — how does it fit in the larger system?\n3. **Walk through the flow** — trace data from entry to exit\n4. **Highlight the non-obvious** — gotchas, trade-offs, design decisions\n\n## Explanation Levels\n\nAdapt your explanation depth to the audience:\n\n| Level | Audience | Focus |\n|-------|----------|-------|\n| **High** | PM, Designer | What it does, user impact |\n| **Mid** | New developer | How it works, key patterns |\n| **Deep** | Experienced dev | Why decisions were made, edge cases |\n\n## Output Format\n\n```markdown\n## What This Does\nOne-paragraph summary of purpose and behavior.\n\n## Architecture\nHow components connect (use diagrams when helpful).\n\n## Key Flow\nStep-by-step trace through the main path.\n\n## Design Decisions\nWhy it's built this way (trade-offs, alternatives considered).\n\n## Gotchas\nThings that might surprise you or cause bugs.\n```\n\n## Critique mode (optional)\n\nWhen asked to critique (not just explain) the architecture, explain first, then surface findings and sort each into: **Act on** (real problem, worth fixing now), **Consider** (worth weighing), **Noted** (minor), **Dismissed** (raised and rejected, with the reason). Keep it lightweight; the heavyweight adversarial pass is `trove-review`'s deep mode.\n\n## Best Practices\n\n- Use code snippets to illustrate, but annotate them\n- Prefer diagrams (ASCII or mermaid) for architecture\n- Link to related code files when referencing them\n- Keep explanations under 500 words unless requested otherwise\n",{"name":5,"metadata":24,"description":7,"when_to_use":27},{"trove-category":25,"trove-category-label":26},"engineering","Engineering","explain this code; what does this do; walk me through","main","f88db1f1cf0e0703dd962051ebc142db961d7799","plugins\u002Ftrove-dev\u002Fskills\u002Ftrove-explain",1,"https:\u002F\u002Fgithub.com\u002Fbravew\u002Ftrove","https:\u002F\u002Fgithub.com\u002Fbravew","2026-11-12 07:56:32",{"source":8,"skillName":5,"commands":36,"prompt":46,"zipAvailable":47},[37,40,43],{"tool":38,"command":39},"npx","npx skills add bravew\u002Ftrove --skill trove-explain",{"tool":41,"command":42},"bunx","bunx skills add bravew\u002Ftrove --skill trove-explain",{"tool":44,"command":45},"pnpm","pnpm dlx skills add bravew\u002Ftrove --skill trove-explain","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fbravew\u002Ftrove\u002Fblob\u002Fmain\u002Fplugins\u002Ftrove-dev\u002Fskills\u002Ftrove-explain\u002FSKILL.md",true,[],[50,57,64,71,78,85],{"skillNo":51,"name":52,"nameZh":6,"description":53,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":54,"categories":55,"keywords":56,"publishedAt":19},"01M7AGJDHTQAS1VK6P7VJAV79G","using-trove","Skill discipline anchor for the Trove marketplace. Loaded once per session; routes the agent to the right trove-* skill before code, planning, review, or git actions.","https:\u002F\u002Fgithub.com\u002Fbravew\u002Ftrove\u002Fblob\u002Fmain\u002Fskills\u002Fworkflow\u002Fusing-trove\u002FSKILL.md",[],[],{"skillNo":58,"name":59,"nameZh":6,"description":60,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":61,"categories":62,"keywords":63,"publishedAt":19},"01M7AGJAS4V4TXE6TV6F839BGZ","trove-write-skill","Skill authoring workflow. Use when creating or updating a Codex or Trove skill, including rubrics, tasks, metadata, and validation.","https:\u002F\u002Fgithub.com\u002Fbravew\u002Ftrove\u002Fblob\u002Fmain\u002Fskills\u002Fworkflow\u002Ftrove-write-skill\u002FSKILL.md",[],[],{"skillNo":65,"name":66,"nameZh":6,"description":67,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":68,"categories":69,"keywords":70,"publishedAt":19},"01M7AGJ87K41ZAC8DDBAV17QFW","trove-worktree","Git worktree workflow for spikes, risky experiments, and broad refactors that should not disturb the user's current branch.","https:\u002F\u002Fgithub.com\u002Fbravew\u002Ftrove\u002Fblob\u002Fmain\u002Fskills\u002Fworkflow\u002Ftrove-worktree\u002FSKILL.md",[],[],{"skillNo":72,"name":73,"nameZh":6,"description":74,"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},"01M7AGJ32V58VYBFYMS9EMHRY4","trove-why","Reconstruct design rationale and decision history from evidence — source control, issue tracker (Linear), docs (Notion), chat (Slack), error tracking (Sentry) — with calibrated confidence. Use for \"why does X work this way\", \"why did we pick Y\", regressions, and postmortems. Use trove-explain for how it works now.","https:\u002F\u002Fgithub.com\u002Fbravew\u002Ftrove\u002Fblob\u002Fmain\u002Fskills\u002Fworkflow\u002Ftrove-why\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},"01M7AGJ0FHJSRR8MMXC3V8XNHF","trove-verify","Completion verification workflow. Use before claiming done, fixed, complete, ready, or shipped.","https:\u002F\u002Fgithub.com\u002Fbravew\u002Ftrove\u002Fblob\u002Fmain\u002Fskills\u002Fworkflow\u002Ftrove-verify\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},"01M7AGHWV4B9SDS60RH5W0B0K5","trove-unslop","Cut AI tells from writing — PR descriptions, release notes, specs, commit bodies, and replies. Use before finalizing prose, or when the user asks to clean up, de-slop, or make text sound human.","https:\u002F\u002Fgithub.com\u002Fbravew\u002Ftrove\u002Fblob\u002Fmain\u002Fskills\u002Fworkflow\u002Ftrove-unslop\u002FSKILL.md",[],[]]