[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M77M7DP27G8FMF3PR8CY877J":3,"skill-same:01M77M7DP27G8FMF3PR8CY877J":81},{"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},"01M77M7DP27G8FMF3PR8CY877J","brainstorm",null,"Diverge before scoping: turn a rough engineering\u002Fproduct problem into codebase-grounded candidate approaches, cheapest→most ambitious, capture which resonate, and hand off scoped. Use when: 'brainstorm', 'what are my options', 'places we could intervene', 'how could we approach X', 'ideas for this', 'explore some approaches', 'what could we do here', or any rough technical problem with no locked scope; skip when scope is already locked or the options are visual variations.","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\u002Fplanning\u002Fskills\u002Fbrainstorm\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\ndescription: \"Diverge before scoping: turn a rough engineering\u002Fproduct problem into codebase-grounded candidate approaches, cheapest→most ambitious, capture which resonate, and hand off scoped. Use when: 'brainstorm', 'what are my options', 'places we could intervene', 'how could we approach X', 'ideas for this', 'explore some approaches', 'what could we do here', or any rough technical problem with no locked scope; skip when scope is already locked or the options are visual variations.\"\nargument-hint: \"\u003Crough-problem>\"\nuser-invocable: true\ndisable-model-invocation: false\nmetadata:\n  workflow-stage: prd\n  summary: Diverge into codebase-grounded candidate approaches before scoping\n---\n\n**Arguments.** `\u003Crough-problem>`. e.g., \u002Fplanning:brainstorm users churn after onboarding\n\n## Purpose\n\nThe divergence step before any scoping: unknown-knowns (criteria the user only recognizes when seen)\nsurface cheapest at candidate-list time. Finding one mid-implementation costs a re-plan. A\ncheapest→most-ambitious spread also calibrates scope: neither too narrow (missed the high-value\napproach) nor too wide (ambition the problem doesn't need). It is also where a half-formed idea\ngoes: the run settles the problem and the user's intent, and hands both forward.\n\nOpening a fresh session on a rough problem with a brainstorm is a citable practice, not a detour:\nthe cheapest→ambitious spread is the cheapest artifact that surfaces criteria the user only\nrecognizes when seen (rationale and sources: `docs\u002Ffinding-your-unknowns.md` in the marketplace\nrepository).\n\nDistinct neighbors: `\u002Fplanning:design` Phase 1 decomposes the problem space WITHIN a design task\nalready chosen; a proactive architecture-friction scan (e.g. `\u002Farchitecture:improve`, if enabled)\nhunts on its own lanes; a UI-variation prototyper (e.g. `\u002Fprototype:explore-directions`, if\nenabled) builds visual variations of a chosen direction. This skill is the general, problem-shaped\nentry upstream of all three. One request to raise or deepen, not options to compare, is\n`\u002Fdiscipline:be-ambitious` (if enabled; the user types it). Creative-domain ideation owned by a domain skill (e.g. songwriting\nbrainstorms → `\u002Fsongwriting:workflow`, if enabled) stays with that skill.\n\n## Task\n\nRough problem: $ARGUMENTS (if empty, infer from conversation; if nothing rough is open, say so and\nstop).\n\nThe run follows\n[`${CLAUDE_PLUGIN_ROOT}\u002Fcontext\u002Fproblem-framing.md`](..\u002F..\u002Fcontext\u002Fproblem-framing.md) \"Idea-stage\nrequests\". Its `time_units` user layer is `${user_config.time_units}` (unexpanded means unset).\n\n1. **Intake: problem and intent.** Read the Brief's `### Problem` when one exists; otherwise state\n   the problem in one line with no solution in it, its evidence rated per \"Evidence rating\". In one\n   message, skipping any question the request already answers, ask:\n   - Is that the problem? (yes, or a correction; a correction restates again)\n   - Why does it matter to you, and where do you want this to head? Keep both in the user's words.\n   - What ideas do you already have, however rough? Ask before showing any candidate, so the user\n     stays the author of the direction: ideas the agent writes for the user lower the user's\n     ownership of them. Keep the user's wording for their ideas.\n\n   A solution the user named is one of their ideas; one question may ask whether to rethink it or\n   keep it. Beyond these, ask at most ONE question, only to learn where the user is starting from.\n   Propose no approach of your own until the user answers. If the user asks to skip the questions,\n   restate the problem, record the intent as `not stated`, and go on.\n2. **Ground**. Fast breadth pass (`Glob`\u002F`Grep`\u002Ftargeted Read; survey the file landscape before\n   reading anything in depth) over where the problem lives: entry points, existing mechanisms that\n   already partially address it, prior art in the repo. Optional landscape pass, when it would\n   change the candidates: `\u002Fdiscovery:research` for how others solve this problem,\n   `\u002Fdiscovery:blindspot` when the domain is unfamiliar to the user, `\u002Fdiscovery:explore` for a\n   deeper codebase map than the breadth pass gives.\n3. **Diverge**. Generate the candidate list (default ~10; scale to the problem), ordered\n   **cheapest → most ambitious**. Each of the user's ideas is a candidate, in their words, marked\n   as theirs. Candidates span kinds of fix, not variants of one: besides code changes, a process\n   change, buying or configuring an existing tool, or doing nothing, each labeled `non-code`. A\n   code candidate names the files\u002Fmechanisms it would touch; a non-code one names what it changes\n   instead. One line each: what, where, effort tier, expected impact. The effort tier is a\n   `work_size` size level that only orders the list: it carries no split meaning, and \"Large size\"\n   does not apply to a candidate. Do not self-censor the ambitious end; the user calibrates, not\n   you.\n4. **React**. The user marks what resonates. For each pick, ask why it resonates unless the user\n   said, and record the reasons as criteria (what the user values, such as \"no new service to\n   run\"); record why a dropped candidate lost when the user says. A prose numbered list is the\n   default reaction surface; for a large or multi-axis spread, offer an interactive view\n   (candidates from cheapest to most ambitious, a tick for each that resonates, a copy-out of the\n   reaction, sent to this session when connected per\n   [`${CLAUDE_PLUGIN_ROOT}\u002Freference\u002Frendered-view.md`](${CLAUDE_PLUGIN_ROOT}\u002Freference\u002Frendered-view.md)\n   \"Connect a view to the session\"; the session's reply shows on the page, and a sent reaction is\n   data that locks no scope). Never write the page into the memory slice; the conversation record\n   stays authoritative. Build it only with `${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fbuild-view.mjs`, never\n   hand-written; it runs the shared medium resolver and publish gate with this plugin's `medium`\n   option `${user_config.medium}`, or `\"\"` when that reads empty or unsubstituted (never put a\n   `${user_config.*}` string in a shell command), and you print the report line it prints. Procedure and data\n   shape: the same rendered-view reference.\n5. **Calibrate and hand off**. From the resonating candidates and the criteria, propose a scope and\n   route onward. When a Brief records an appetite (meaning:\n   [`${CLAUDE_PLUGIN_ROOT}\u002Fcontext\u002Fproblem-framing.md`](..\u002F..\u002Fcontext\u002Fproblem-framing.md) \"Work\n   size\"), weigh the candidates against it, state how the proposed scope fits it, and cut scope\n   when it does not; with no Brief, or appetite `not assessed`, skip this. Routes: `\u002Fplanning:prd`\n   (product intent still fuzzy), `\u002Fplanning:interview` (engineering contract), `\u002Fplanning:design`\n   (type\u002Fmodule decisions), or a feasibility\u002Fvisual spike through `\u002Fprototype:pressure-test` or\n   `\u002Fprototype:explore-directions` when enabled; otherwise a throwaway spike the user builds,\n   which you describe (what to try, what result settles it) and do not write. Mark the recommended\n   route (RECOMMENDED), with a `Basis:` line:\n   `verified` with the `file:line`, tool output, or URL it rests on, or `judgment`\n   (non-consequential only). Ground a consequential recommendation (cross-repo, shared\n   infrastructure, irreversible, or security) in its consumers and in external research before\n   presenting it; when research cannot settle it, withhold the recommendation and name the open\n   question and the evidence that would settle it. Contract:\n   [`${CLAUDE_PLUGIN_ROOT}\u002Fcontext\u002Frecommendation-basis.md`](..\u002F..\u002Fcontext\u002Frecommendation-basis.md).\n   On a route to `\u002Fplanning:interview`, `\u002Fplanning:prd` or `\u002Fplanning:design`, write the handoff\n   block (Output) and name its path in the route.\n\n## Output\n\nOn a route to `\u002Fplanning:interview`, `\u002Fplanning:prd` or `\u002Fplanning:design`, write\n`\u003Cmemory_dir>\u002F\u003Ctopic-slug>\u002Fbrainstorm.md` (default `.work\u002F`; the existing slice for the effort, else\na slug from the problem; placement per\n[`${CLAUDE_PLUGIN_ROOT}\u002Freference\u002Fartifact-protocol.md`](${CLAUDE_PLUGIN_ROOT}\u002Freference\u002Fartifact-protocol.md))\nholding this block, every field filled or `not stated`:\n\n```markdown\n## Handoff\n\n- Problem: \u003Cthe confirmed one-line problem, evidence rated>\n- Intent (why, in the user's words): \u003Cthe user's words>\n- Vision (where this heads): \u003Cthe user's words>\n- Chosen direction: \u003Cthe resonating candidates and the proposed scope>\n- Rejected options: \u003Ceach candidate not chosen, with its reason>\n- Criteria surfaced: \u003Cwhy each chosen candidate resonated>\n```\n\nThe full candidate list and reactions go into the same file only when the user opts in. Other\nroutes write nothing.\n\n## Next\n\n- The engineering contract is next, carrying the handoff block: \u002Fplanning:interview.\n- Product intent is still fuzzy: \u002Fplanning:prd.\n- The direction is a product or feature idea to stress-test before building it: \u002Fplanning:interview product.\n- Type and module decisions, with the contract already locked: \u002Fplanning:design.\n- Unsure where this leaves the work, or arrived mid-flow: \u002Fsession-flow:workflow.\n\n## What this skill does NOT do\n\n- **Does not decide**. User reactions drive selection; the skill recommends, marked (RECOMMENDED)\n  with basis\n- **Does not lock scope or contract**. `\u002Fplanning:interview`\n- **Does not explore the design space of a chosen direction**. `\u002Fplanning:design`\n- **Does not build variations or throwaway code**. A prototyping capability\n  (`\u002Fprototype:pressure-test` \u002F `\u002Fprototype:explore-directions` when enabled)\n","**Arguments.** `\u003Crough-problem>`. e.g., \u002Fplanning:brainstorm users churn after onboarding\n\n## Purpose\n\nThe divergence step before any scoping: unknown-knowns (criteria the user only recognizes when seen)\nsurface cheapest at candidate-list time. Finding one mid-implementation costs a re-plan. A\ncheapest→most-ambitious spread also calibrates scope: neither too narrow (missed the high-value\napproach) nor too wide (ambition the problem doesn't need). It is also where a half-formed idea\ngoes: the run settles the problem and the user's intent, and hands both forward.\n\nOpening a fresh session on a rough problem with a brainstorm is a citable practice, not a detour:\nthe cheapest→ambitious spread is the cheapest artifact that surfaces criteria the user only\nrecognizes when seen (rationale and sources: `docs\u002Ffinding-your-unknowns.md` in the marketplace\nrepository).\n\nDistinct neighbors: `\u002Fplanning:design` Phase 1 decomposes the problem space WITHIN a design task\nalready chosen; a proactive architecture-friction scan (e.g. `\u002Farchitecture:improve`, if enabled)\nhunts on its own lanes; a UI-variation prototyper (e.g. `\u002Fprototype:explore-directions`, if\nenabled) builds visual variations of a chosen direction. This skill is the general, problem-shaped\nentry upstream of all three. One request to raise or deepen, not options to compare, is\n`\u002Fdiscipline:be-ambitious` (if enabled; the user types it). Creative-domain ideation owned by a domain skill (e.g. songwriting\nbrainstorms → `\u002Fsongwriting:workflow`, if enabled) stays with that skill.\n\n## Task\n\nRough problem: $ARGUMENTS (if empty, infer from conversation; if nothing rough is open, say so and\nstop).\n\nThe run follows\n[`${CLAUDE_PLUGIN_ROOT}\u002Fcontext\u002Fproblem-framing.md`](..\u002F..\u002Fcontext\u002Fproblem-framing.md) \"Idea-stage\nrequests\". Its `time_units` user layer is `${user_config.time_units}` (unexpanded means unset).\n\n1. **Intake: problem and intent.** Read the Brief's `### Problem` when one exists; otherwise state\n   the problem in one line with no solution in it, its evidence rated per \"Evidence rating\". In one\n   message, skipping any question the request already answers, ask:\n   - Is that the problem? (yes, or a correction; a correction restates again)\n   - Why does it matter to you, and where do you want this to head? Keep both in the user's words.\n   - What ideas do you already have, however rough? Ask before showing any candidate, so the user\n     stays the author of the direction: ideas the agent writes for the user lower the user's\n     ownership of them. Keep the user's wording for their ideas.\n\n   A solution the user named is one of their ideas; one question may ask whether to rethink it or\n   keep it. Beyond these, ask at most ONE question, only to learn where the user is starting from.\n   Propose no approach of your own until the user answers. If the user asks to skip the questions,\n   restate the problem, record the intent as `not stated`, and go on.\n2. **Ground**. Fast breadth pass (`Glob`\u002F`Grep`\u002Ftargeted Read; survey the file landscape before\n   reading anything in depth) over where the problem lives: entry points, existing mechanisms that\n   already partially address it, prior art in the repo. Optional landscape pass, when it would\n   change the candidates: `\u002Fdiscovery:research` for how others solve this problem,\n   `\u002Fdiscovery:blindspot` when the domain is unfamiliar to the user, `\u002Fdiscovery:explore` for a\n   deeper codebase map than the breadth pass gives.\n3. **Diverge**. Generate the candidate list (default ~10; scale to the problem), ordered\n   **cheapest → most ambitious**. Each of the user's ideas is a candidate, in their words, marked\n   as theirs. Candidates span kinds of fix, not variants of one: besides code changes, a process\n   change, buying or configuring an existing tool, or doing nothing, each labeled `non-code`. A\n   code candidate names the files\u002Fmechanisms it would touch; a non-code one names what it changes\n   instead. One line each: what, where, effort tier, expected impact. The effort tier is a\n   `work_size` size level that only orders the list: it carries no split meaning, and \"Large size\"\n   does not apply to a candidate. Do not self-censor the ambitious end; the user calibrates, not\n   you.\n4. **React**. The user marks what resonates. For each pick, ask why it resonates unless the user\n   said, and record the reasons as criteria (what the user values, such as \"no new service to\n   run\"); record why a dropped candidate lost when the user says. A prose numbered list is the\n   default reaction surface; for a large or multi-axis spread, offer an interactive view\n   (candidates from cheapest to most ambitious, a tick for each that resonates, a copy-out of the\n   reaction, sent to this session when connected per\n   [`${CLAUDE_PLUGIN_ROOT}\u002Freference\u002Frendered-view.md`](${CLAUDE_PLUGIN_ROOT}\u002Freference\u002Frendered-view.md)\n   \"Connect a view to the session\"; the session's reply shows on the page, and a sent reaction is\n   data that locks no scope). Never write the page into the memory slice; the conversation record\n   stays authoritative. Build it only with `${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fbuild-view.mjs`, never\n   hand-written; it runs the shared medium resolver and publish gate with this plugin's `medium`\n   option `${user_config.medium}`, or `\"\"` when that reads empty or unsubstituted (never put a\n   `${user_config.*}` string in a shell command), and you print the report line it prints. Procedure and data\n   shape: the same rendered-view reference.\n5. **Calibrate and hand off**. From the resonating candidates and the criteria, propose a scope and\n   route onward. When a Brief records an appetite (meaning:\n   [`${CLAUDE_PLUGIN_ROOT}\u002Fcontext\u002Fproblem-framing.md`](..\u002F..\u002Fcontext\u002Fproblem-framing.md) \"Work\n   size\"), weigh the candidates against it, state how the proposed scope fits it, and cut scope\n   when it does not; with no Brief, or appetite `not assessed`, skip this. Routes: `\u002Fplanning:prd`\n   (product intent still fuzzy), `\u002Fplanning:interview` (engineering contract), `\u002Fplanning:design`\n   (type\u002Fmodule decisions), or a feasibility\u002Fvisual spike through `\u002Fprototype:pressure-test` or\n   `\u002Fprototype:explore-directions` when enabled; otherwise a throwaway spike the user builds,\n   which you describe (what to try, what result settles it) and do not write. Mark the recommended\n   route (RECOMMENDED), with a `Basis:` line:\n   `verified` with the `file:line`, tool output, or URL it rests on, or `judgment`\n   (non-consequential only). Ground a consequential recommendation (cross-repo, shared\n   infrastructure, irreversible, or security) in its consumers and in external research before\n   presenting it; when research cannot settle it, withhold the recommendation and name the open\n   question and the evidence that would settle it. Contract:\n   [`${CLAUDE_PLUGIN_ROOT}\u002Fcontext\u002Frecommendation-basis.md`](..\u002F..\u002Fcontext\u002Frecommendation-basis.md).\n   On a route to `\u002Fplanning:interview`, `\u002Fplanning:prd` or `\u002Fplanning:design`, write the handoff\n   block (Output) and name its path in the route.\n\n## Output\n\nOn a route to `\u002Fplanning:interview`, `\u002Fplanning:prd` or `\u002Fplanning:design`, write\n`\u003Cmemory_dir>\u002F\u003Ctopic-slug>\u002Fbrainstorm.md` (default `.work\u002F`; the existing slice for the effort, else\na slug from the problem; placement per\n[`${CLAUDE_PLUGIN_ROOT}\u002Freference\u002Fartifact-protocol.md`](${CLAUDE_PLUGIN_ROOT}\u002Freference\u002Fartifact-protocol.md))\nholding this block, every field filled or `not stated`:\n\n```markdown\n## Handoff\n\n- Problem: \u003Cthe confirmed one-line problem, evidence rated>\n- Intent (why, in the user's words): \u003Cthe user's words>\n- Vision (where this heads): \u003Cthe user's words>\n- Chosen direction: \u003Cthe resonating candidates and the proposed scope>\n- Rejected options: \u003Ceach candidate not chosen, with its reason>\n- Criteria surfaced: \u003Cwhy each chosen candidate resonated>\n```\n\nThe full candidate list and reactions go into the same file only when the user opts in. Other\nroutes write nothing.\n\n## Next\n\n- The engineering contract is next, carrying the handoff block: \u002Fplanning:interview.\n- Product intent is still fuzzy: \u002Fplanning:prd.\n- The direction is a product or feature idea to stress-test before building it: \u002Fplanning:interview product.\n- Type and module decisions, with the contract already locked: \u002Fplanning:design.\n- Unsure where this leaves the work, or arrived mid-flow: \u002Fsession-flow:workflow.\n\n## What this skill does NOT do\n\n- **Does not decide**. User reactions drive selection; the skill recommends, marked (RECOMMENDED)\n  with basis\n- **Does not lock scope or contract**. `\u002Fplanning:interview`\n- **Does not explore the design space of a chosen direction**. `\u002Fplanning:design`\n- **Does not build variations or throwaway code**. A prototyping capability\n  (`\u002Fprototype:pressure-test` \u002F `\u002Fprototype:explore-directions` when enabled)\n",{"metadata":24,"description":7,"argument-hint":27,"user-invocable":28,"disable-model-invocation":20},{"summary":25,"workflow-stage":26},"Diverge into codebase-grounded candidate approaches before scoping","prd","\u003Crough-problem>",true,"main","d0e68c3f36b92a1d6381f0ba0060d7a0b8b886c5","plugins\u002Fplanning\u002Fskills\u002Fbrainstorm",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 brainstorm",{"tool":44,"command":45},"bunx","bunx skills add melodic-software\u002Fclaude-code-plugins --skill brainstorm",{"tool":47,"command":48},"pnpm","pnpm dlx skills add melodic-software\u002Fclaude-code-plugins --skill brainstorm","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fmelodic-software\u002Fclaude-code-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fplanning\u002Fskills\u002Fbrainstorm\u002FSKILL.md",[51,57,61,65,69,73,77],{"path":52,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":55,"sourceHtmlUrl":56},"evals\u002Fevals.json","REFERENCE","参考文档",9311,"https:\u002F\u002Fgithub.com\u002Fmelodic-software\u002Fclaude-code-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fplanning\u002Fskills\u002Fbrainstorm\u002Fevals\u002Fevals.json",{"path":58,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":59,"sourceHtmlUrl":60},"evals\u002Ffixtures\u002Fdisconnected-scan\u002Fapp\u002Fconfig.py.txt",80,"https:\u002F\u002Fgithub.com\u002Fmelodic-software\u002Fclaude-code-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fplanning\u002Fskills\u002Fbrainstorm\u002Fevals\u002Ffixtures\u002Fdisconnected-scan\u002Fapp\u002Fconfig.py.txt",{"path":62,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":63,"sourceHtmlUrl":64},"evals\u002Ffixtures\u002Fdisconnected-scan\u002Fapp\u002Fdigest.py.txt",127,"https:\u002F\u002Fgithub.com\u002Fmelodic-software\u002Fclaude-code-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fplanning\u002Fskills\u002Fbrainstorm\u002Fevals\u002Ffixtures\u002Fdisconnected-scan\u002Fapp\u002Fdigest.py.txt",{"path":66,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":67,"sourceHtmlUrl":68},"evals\u002Ffixtures\u002Fdisconnected-scan\u002Fapp\u002Fnotifier.py.txt",262,"https:\u002F\u002Fgithub.com\u002Fmelodic-software\u002Fclaude-code-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fplanning\u002Fskills\u002Fbrainstorm\u002Fevals\u002Ffixtures\u002Fdisconnected-scan\u002Fapp\u002Fnotifier.py.txt",{"path":70,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":71,"sourceHtmlUrl":72},"evals\u002Ffixtures\u002Fdisconnected-scan\u002Fapp\u002Fstore.py.txt",359,"https:\u002F\u002Fgithub.com\u002Fmelodic-software\u002Fclaude-code-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fplanning\u002Fskills\u002Fbrainstorm\u002Fevals\u002Ffixtures\u002Fdisconnected-scan\u002Fapp\u002Fstore.py.txt",{"path":74,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":75,"sourceHtmlUrl":76},"evals\u002Ffixtures\u002Fdisconnected-scan\u002Fdb\u002Fschema.sql.txt",274,"https:\u002F\u002Fgithub.com\u002Fmelodic-software\u002Fclaude-code-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fplanning\u002Fskills\u002Fbrainstorm\u002Fevals\u002Ffixtures\u002Fdisconnected-scan\u002Fdb\u002Fschema.sql.txt",{"path":78,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":79,"sourceHtmlUrl":80},"templates\u002Fbrainstorm-view.html",7754,"https:\u002F\u002Fgithub.com\u002Fmelodic-software\u002Fclaude-code-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fplanning\u002Fskills\u002Fbrainstorm\u002Ftemplates\u002Fbrainstorm-view.html",[82,89,96,103,108,115],{"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},"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":90,"name":91,"nameZh":6,"description":92,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":93,"categories":94,"keywords":95,"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":97,"name":98,"nameZh":6,"description":99,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":100,"categories":101,"keywords":102,"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":104,"name":98,"nameZh":6,"description":99,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":105,"categories":106,"keywords":107,"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":109,"name":110,"nameZh":6,"description":111,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":112,"categories":113,"keywords":114,"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":116,"name":117,"nameZh":6,"description":118,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":119,"categories":120,"keywords":121,"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",[],[]]