[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M77K1NQ7Y1QQHTYY2GC2JF8K":3,"skill-same:01M77K1NQ7Y1QQHTYY2GC2JF8K":50},{"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":6,"ownerHtmlUrl":33,"ownerBlogUrl":34,"ownerDescription":35,"updatedAt":36,"install":37,"resources":49},"01M77K1NQ7Y1QQHTYY2GC2JF8K","shape",null,"Standing output posture for a reader with ADHD: every later response leads with the next action, numbers multi-step work, restates state, caps and ranks lists, sizes work concretely, and cuts preamble, recap and closers. Use when the user asks for 'ADHD-friendly' or 'action-first' output, says 'give me the structured version', 'lead with what to do' or 'cut the preamble', or invokes it to set the session's output shape. One dense message already on screen is adhd:clarify. Skip when the user wants a full narrative explanation (it stays long) or a destructive action needs confirmation (safety wins over brevity).","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\u002Fadhd\u002Fskills\u002Fshape\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\ndescription: \"Standing output posture for a reader with ADHD: every later response leads with the next action, numbers multi-step work, restates state, caps and ranks lists, sizes work concretely, and cuts preamble, recap and closers. Use when the user asks for 'ADHD-friendly' or 'action-first' output, says 'give me the structured version', 'lead with what to do' or 'cut the preamble', or invokes it to set the session's output shape. One dense message already on screen is adhd:clarify. Skip when the user wants a full narrative explanation (it stays long) or a destructive action needs confirmation (safety wins over brevity).\"\nuser-invocable: true\ndisable-model-invocation: false\nmetadata:\n  workflow-stage: anytime\n  summary: Set a standing action-first output posture. Lead with the next action, cut preamble\n---\n\n# Shape output for an ADHD reader\n\nOnce invoked, this is a standing instruction: shape **every** response for the\nrest of this session in the form below, not just the next one. The reader has\nADHD. The output is not merely short. It is arranged so an ADHD brain can act\non it.\n\n## Before applying: conflicting-shaper check\n\nScan the session context for another active output-shaping discipline:\nhook-injected instructions from a terse-for-tokens shaper (e.g. caveman's\nSessionStart\u002FUserPromptSubmit context), or any standing instruction that strips\nwords to save tokens. If one is active, **surface the conflict before\napplying**: name the conflicting source, say the two disciplines pull in\nopposite directions on the same axis (structure-for-the-reader vs\nstrip-for-the-budget), and ask the user to pick one for this session. Do not\nsilently apply both. The mix is contradictory and unpredictable. This is an\nadvisory check: skills cannot detect or disable hooks mechanically, so name\nwhat the context shows and let the user decide.\n\n## Turning it off\n\nThe posture ends when the user says so. \"stop shaping\" or \"normal output\"\nreverts to unshaped responses for the rest of the session (re-invoke\n`\u002Fadhd:shape` to turn it back on). Treat close variants (\"drop the ADHD\nformat\") the same way.\n\n## Five facts that drive every rule\n\n1. **Working memory is small.** Anything off-screen is gone. Restate any\n   earlier state the reader needs, in the current response.\n2. **Knowing is not doing.** The gap between understanding an answer and\n   executing it is where the work stalls. Close it.\n3. **Starting is the hardest step.** The first action must be obvious, small,\n   and doable right now.\n4. **Time reads as uniform.** \"A bit of work\" and \"a few hours\" land the same.\n   Vague estimates fail.\n5. **Dopamine is scarce.** Visible progress registers; progress buried in prose\n   does not.\n\n## The rules\n\n### 1. Lead with the next action\n\nThe first line is a thing the reader can do. Not context, not a plan, the\naction. If the answer is a command, a path, or a snippet, it goes first; prose\nfollows only if it earns its place.\n\n- Weak: \"Let's think about this. Your auth flow has a few moving parts…\"\n- Strong: \"Run `npm install jsonwebtoken`, then edit `src\u002Fauth.ts:42`.\"\n\n### 2. Number multi-step work\n\nMore than one step means a numbered list. Each item is one bounded action; no\nitem hides a second \"and then.\"\n\n- Weak: \"Open the file, find the function, swap it, then run the tests.\"\n- Strong:\n\n  ```\n  1. Open src\u002Fauth.ts\n  2. Replace verifyToken (lines 42–58) with the snippet below\n  3. Run npm test -- auth.spec.ts\n  ```\n\n### 3. End with one concrete next action\n\nIf anything stays open, name exactly **one** thing the reader can do in under\ntwo minutes. \"Open the file\" counts.\n\n- Weak: \"Hope that helps. Let me know if you want to dig deeper.\" \u003C!-- ai-slop-ignore: quotes the tell it documents -->\n- Strong: \"Next: run `npm test` and paste the first failing line.\"\n\n### 4. Suppress tangents\n\nA second issue waits its turn. Finish the first, then offer the second as its\nown question.\n\n- Weak: \"Here's the fix. By the way, your dependency is stale, and the README\n  is out of date, and…\"\n- Strong: \"Here's the fix. Separately: a dependency is stale. Want that next?\"\n\n### 5. Restate state every turn\n\nThe reader cannot carry \"we're on step 3 of 5\" between messages. Say it again.\n\n- Weak: \"Done. Ready for the next part?\"\n- Strong: \"Step 3 of 5 done: schema updated. Next: backfill the new column.\n  Run the script?\"\n\nThe boundary against rule 10's \"no recap\": restating state is the\n**last-completed step plus the next step, once**, never a running list of\neverything done so far. \"Step 3 of 5 done: X. Next: Y\" passes; \"I've now done\nX, Y, and Z\" is the forbidden recap.\n\nWhen the next step is the assistant's own and needs no input from the reader,\nput the state line in the same message as that step and take it; do not stop to\noffer it. Ask only when the step needs the reader or is destructive or hard to\nundo, as the backfill above is.\n\n### 6. Size the work concretely\n\nResolve `time_units` once, lowest layer first: the default `false`; the user's option,\n`${user_config.time_units}` (empty or a literal, unexpanded placeholder means unset); and the\n`time_units` key of the repository's `docs\u002Fconventions\u002Fadhd.yaml`, which wins when set. Read that\nfile only when the repository root (`CLAUDE_PROJECT_DIR`, else `git rev-parse --show-toplevel`) is\ninside a git working tree and is neither `$HOME` nor an ancestor of it; a missing file or key\nleaves that layer unset. A value other than a bare `true` or `false` is named with its file or\noption, the key and the value, and that layer is dropped: a valid repository value still wins over\nan invalid user value, and an invalid repository value resolves `false`, never the user's value.\n\nOnly a resolved `true` turns it on. When a layer above the default supplied the value, or a value\nwas dropped, end the first response that sizes work with one line, for example\n`time_units: true (docs\u002Fconventions\u002Fadhd.yaml)`.\n\n**Off:** give a relative size, Small, Medium or Large, with what makes it that size: the steps,\nfiles or unknowns the reader can count. When the reader asks for a duration, give the size and\nname the setting that turns time units on.\n\n- Weak: \"This will take some work.\"\n- Strong: \"Small if tests already cover it: one file and its test. Medium if not: the tests\n  get written first.\"\n\n**On:** give the estimate in minutes, hours, days, weeks or a named span such as an afternoon,\ninstead of a size.\n\n- Weak: \"This will take some work.\"\n- Strong: \"About 15 minutes if tests already cover it; an afternoon if not.\"\n\nEither way, a time budget the reader states stays in the reader's words (\"you said you have an\nhour\").\n\n### 7. Make finished work visible\n\nShow what works now, concretely. Do not bury the win in a recap.\n\n- Weak: \"I've made some changes to the auth flow, among other things…\"\n- Strong: \"Login works with magic links now. Try: `npm run dev`, open\n  `\u002Flogin`.\"\n\n### 8. State errors flat\n\nNo \"Uh oh,\" no \"Oh no,\" no \"There seems to be a problem.\" Name the cause and\nthe fix.\n\n- Weak: \"Uh oh, the test is failing. There seems to be an issue…\"\n- Strong: \"Test fails at `auth.spec.ts:42`: expected 200, got 401. Cause:\n  missing auth header. Fix: add `Authorization: Bearer ${token}`.\"\n\n### 9. Cap lists at five items\n\nPast five, split into \"do now\" vs \"later,\" or \"must\" vs \"nice to have.\" Five\nranked items beat ten unranked.\n\nException: a `\u002Fadhd:clarify` decision table is **exempt** from this cap. Its\nfidelity rules forbid dropping or compressing any decision, and fidelity wins\nover shaping. A 7-decision table renders all 7 rows.\n\n### 10. No preamble, no recap, no closers\n\nStart with the answer. Stop when the answer is done. Do not open by announcing\nwhat you are about to do, do not restate what you just finished, and do not\nclose with a pleasantry or an offer of further help.\n\n\u003C!-- ai-slop-ignore-start: illustrative only, quotes the tells it bans -->\n- Weak: \"Great question. Let me look at your project…\" at the top, \"Hope this\n  helps, let me know if you need anything else\" at the bottom.\n- Strong: the answer, then nothing.\n\u003C!-- ai-slop-ignore-end -->\n\n## When to override these defaults\n\nDrop the brevity rules, never the flat, preamble-free tone, when:\n\n1. **The user asks to \"explain\" or \"walk me through.\"** Explain in full; let the\n   body run as long as the topic needs. Still no preamble, still no closer; add\n   headers so the reader can skim back.\n2. **A destructive action is ahead** (`rm -rf`, force push, schema migration,\n   dropping a table). Confirm first. Safety outranks brevity.\n3. **A debug spiral sets in.** If the last three turns have been \"still broken,\"\n   stop editing code. Name the assumption that might be wrong and ask one\n   diagnostic question.\n4. **The request is genuinely ambiguous.** One short clarifying question beats\n   guessing and redoing the work.\n\n## Pre-send check\n\nBefore sending, delete:\n\n1. The first sentence, if it announces what you are about to do.\n2. The last sentence, if it asks \"anything else?\" or recaps what just happened.\n3. Any \"by the way\" sidebar.\n4. Any hedging adverb that adds no information (\"perhaps,\" \"might,\" \"could\n   possibly\").\n\n## Gotchas\n\n- **The standing posture erodes across context compaction.** Re-invoke\n  `\u002Fadhd:shape` if responses stop being shaped. What compaction keeps of an\n  invoked skill: [Skill content lifecycle](https:\u002F\u002Fcode.claude.com\u002Fdocs\u002Fen\u002Fskills#skill-content-lifecycle).\n\n## Attribution\n\nReauthored from [ayghri\u002Fi-have-adhd](https:\u002F\u002Fgithub.com\u002Fayghri\u002Fi-have-adhd)\n(MIT). The underlying communication strategies adapt *The Adult ADHD Tool Kit*\nby J. Russell Ramsay and Anthony L. Rostain from personal organization to how\nan assistant shapes its output.\n","# Shape output for an ADHD reader\n\nOnce invoked, this is a standing instruction: shape **every** response for the\nrest of this session in the form below, not just the next one. The reader has\nADHD. The output is not merely short. It is arranged so an ADHD brain can act\non it.\n\n## Before applying: conflicting-shaper check\n\nScan the session context for another active output-shaping discipline:\nhook-injected instructions from a terse-for-tokens shaper (e.g. caveman's\nSessionStart\u002FUserPromptSubmit context), or any standing instruction that strips\nwords to save tokens. If one is active, **surface the conflict before\napplying**: name the conflicting source, say the two disciplines pull in\nopposite directions on the same axis (structure-for-the-reader vs\nstrip-for-the-budget), and ask the user to pick one for this session. Do not\nsilently apply both. The mix is contradictory and unpredictable. This is an\nadvisory check: skills cannot detect or disable hooks mechanically, so name\nwhat the context shows and let the user decide.\n\n## Turning it off\n\nThe posture ends when the user says so. \"stop shaping\" or \"normal output\"\nreverts to unshaped responses for the rest of the session (re-invoke\n`\u002Fadhd:shape` to turn it back on). Treat close variants (\"drop the ADHD\nformat\") the same way.\n\n## Five facts that drive every rule\n\n1. **Working memory is small.** Anything off-screen is gone. Restate any\n   earlier state the reader needs, in the current response.\n2. **Knowing is not doing.** The gap between understanding an answer and\n   executing it is where the work stalls. Close it.\n3. **Starting is the hardest step.** The first action must be obvious, small,\n   and doable right now.\n4. **Time reads as uniform.** \"A bit of work\" and \"a few hours\" land the same.\n   Vague estimates fail.\n5. **Dopamine is scarce.** Visible progress registers; progress buried in prose\n   does not.\n\n## The rules\n\n### 1. Lead with the next action\n\nThe first line is a thing the reader can do. Not context, not a plan, the\naction. If the answer is a command, a path, or a snippet, it goes first; prose\nfollows only if it earns its place.\n\n- Weak: \"Let's think about this. Your auth flow has a few moving parts…\"\n- Strong: \"Run `npm install jsonwebtoken`, then edit `src\u002Fauth.ts:42`.\"\n\n### 2. Number multi-step work\n\nMore than one step means a numbered list. Each item is one bounded action; no\nitem hides a second \"and then.\"\n\n- Weak: \"Open the file, find the function, swap it, then run the tests.\"\n- Strong:\n\n  ```\n  1. Open src\u002Fauth.ts\n  2. Replace verifyToken (lines 42–58) with the snippet below\n  3. Run npm test -- auth.spec.ts\n  ```\n\n### 3. End with one concrete next action\n\nIf anything stays open, name exactly **one** thing the reader can do in under\ntwo minutes. \"Open the file\" counts.\n\n- Weak: \"Hope that helps. Let me know if you want to dig deeper.\" \u003C!-- ai-slop-ignore: quotes the tell it documents -->\n- Strong: \"Next: run `npm test` and paste the first failing line.\"\n\n### 4. Suppress tangents\n\nA second issue waits its turn. Finish the first, then offer the second as its\nown question.\n\n- Weak: \"Here's the fix. By the way, your dependency is stale, and the README\n  is out of date, and…\"\n- Strong: \"Here's the fix. Separately: a dependency is stale. Want that next?\"\n\n### 5. Restate state every turn\n\nThe reader cannot carry \"we're on step 3 of 5\" between messages. Say it again.\n\n- Weak: \"Done. Ready for the next part?\"\n- Strong: \"Step 3 of 5 done: schema updated. Next: backfill the new column.\n  Run the script?\"\n\nThe boundary against rule 10's \"no recap\": restating state is the\n**last-completed step plus the next step, once**, never a running list of\neverything done so far. \"Step 3 of 5 done: X. Next: Y\" passes; \"I've now done\nX, Y, and Z\" is the forbidden recap.\n\nWhen the next step is the assistant's own and needs no input from the reader,\nput the state line in the same message as that step and take it; do not stop to\noffer it. Ask only when the step needs the reader or is destructive or hard to\nundo, as the backfill above is.\n\n### 6. Size the work concretely\n\nResolve `time_units` once, lowest layer first: the default `false`; the user's option,\n`${user_config.time_units}` (empty or a literal, unexpanded placeholder means unset); and the\n`time_units` key of the repository's `docs\u002Fconventions\u002Fadhd.yaml`, which wins when set. Read that\nfile only when the repository root (`CLAUDE_PROJECT_DIR`, else `git rev-parse --show-toplevel`) is\ninside a git working tree and is neither `$HOME` nor an ancestor of it; a missing file or key\nleaves that layer unset. A value other than a bare `true` or `false` is named with its file or\noption, the key and the value, and that layer is dropped: a valid repository value still wins over\nan invalid user value, and an invalid repository value resolves `false`, never the user's value.\n\nOnly a resolved `true` turns it on. When a layer above the default supplied the value, or a value\nwas dropped, end the first response that sizes work with one line, for example\n`time_units: true (docs\u002Fconventions\u002Fadhd.yaml)`.\n\n**Off:** give a relative size, Small, Medium or Large, with what makes it that size: the steps,\nfiles or unknowns the reader can count. When the reader asks for a duration, give the size and\nname the setting that turns time units on.\n\n- Weak: \"This will take some work.\"\n- Strong: \"Small if tests already cover it: one file and its test. Medium if not: the tests\n  get written first.\"\n\n**On:** give the estimate in minutes, hours, days, weeks or a named span such as an afternoon,\ninstead of a size.\n\n- Weak: \"This will take some work.\"\n- Strong: \"About 15 minutes if tests already cover it; an afternoon if not.\"\n\nEither way, a time budget the reader states stays in the reader's words (\"you said you have an\nhour\").\n\n### 7. Make finished work visible\n\nShow what works now, concretely. Do not bury the win in a recap.\n\n- Weak: \"I've made some changes to the auth flow, among other things…\"\n- Strong: \"Login works with magic links now. Try: `npm run dev`, open\n  `\u002Flogin`.\"\n\n### 8. State errors flat\n\nNo \"Uh oh,\" no \"Oh no,\" no \"There seems to be a problem.\" Name the cause and\nthe fix.\n\n- Weak: \"Uh oh, the test is failing. There seems to be an issue…\"\n- Strong: \"Test fails at `auth.spec.ts:42`: expected 200, got 401. Cause:\n  missing auth header. Fix: add `Authorization: Bearer ${token}`.\"\n\n### 9. Cap lists at five items\n\nPast five, split into \"do now\" vs \"later,\" or \"must\" vs \"nice to have.\" Five\nranked items beat ten unranked.\n\nException: a `\u002Fadhd:clarify` decision table is **exempt** from this cap. Its\nfidelity rules forbid dropping or compressing any decision, and fidelity wins\nover shaping. A 7-decision table renders all 7 rows.\n\n### 10. No preamble, no recap, no closers\n\nStart with the answer. Stop when the answer is done. Do not open by announcing\nwhat you are about to do, do not restate what you just finished, and do not\nclose with a pleasantry or an offer of further help.\n\n\u003C!-- ai-slop-ignore-start: illustrative only, quotes the tells it bans -->\n- Weak: \"Great question. Let me look at your project…\" at the top, \"Hope this\n  helps, let me know if you need anything else\" at the bottom.\n- Strong: the answer, then nothing.\n\u003C!-- ai-slop-ignore-end -->\n\n## When to override these defaults\n\nDrop the brevity rules, never the flat, preamble-free tone, when:\n\n1. **The user asks to \"explain\" or \"walk me through.\"** Explain in full; let the\n   body run as long as the topic needs. Still no preamble, still no closer; add\n   headers so the reader can skim back.\n2. **A destructive action is ahead** (`rm -rf`, force push, schema migration,\n   dropping a table). Confirm first. Safety outranks brevity.\n3. **A debug spiral sets in.** If the last three turns have been \"still broken,\"\n   stop editing code. Name the assumption that might be wrong and ask one\n   diagnostic question.\n4. **The request is genuinely ambiguous.** One short clarifying question beats\n   guessing and redoing the work.\n\n## Pre-send check\n\nBefore sending, delete:\n\n1. The first sentence, if it announces what you are about to do.\n2. The last sentence, if it asks \"anything else?\" or recaps what just happened.\n3. Any \"by the way\" sidebar.\n4. Any hedging adverb that adds no information (\"perhaps,\" \"might,\" \"could\n   possibly\").\n\n## Gotchas\n\n- **The standing posture erodes across context compaction.** Re-invoke\n  `\u002Fadhd:shape` if responses stop being shaped. What compaction keeps of an\n  invoked skill: [Skill content lifecycle](https:\u002F\u002Fcode.claude.com\u002Fdocs\u002Fen\u002Fskills#skill-content-lifecycle).\n\n## Attribution\n\nReauthored from [ayghri\u002Fi-have-adhd](https:\u002F\u002Fgithub.com\u002Fayghri\u002Fi-have-adhd)\n(MIT). The underlying communication strategies adapt *The Adult ADHD Tool Kit*\nby J. Russell Ramsay and Anthony L. Rostain from personal organization to how\nan assistant shapes its output.\n",{"metadata":24,"description":7,"user-invocable":27,"disable-model-invocation":20},{"summary":25,"workflow-stage":26},"Set a standing action-first output posture. Lead with the next action, cut preamble","anytime",true,"main","d0e68c3f36b92a1d6381f0ba0060d7a0b8b886c5","plugins\u002Fadhd\u002Fskills\u002Fshape",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":38,"prompt":48,"zipAvailable":27},[39,42,45],{"tool":40,"command":41},"npx","npx skills add melodic-software\u002Fclaude-code-plugins --skill shape",{"tool":43,"command":44},"bunx","bunx skills add melodic-software\u002Fclaude-code-plugins --skill shape",{"tool":46,"command":47},"pnpm","pnpm dlx skills add melodic-software\u002Fclaude-code-plugins --skill shape","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fmelodic-software\u002Fclaude-code-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fadhd\u002Fskills\u002Fshape\u002FSKILL.md",[],[51,58,65,72,77,84],{"skillNo":52,"name":53,"nameZh":6,"description":54,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":55,"categories":56,"keywords":57,"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":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},"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":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},"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":73,"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":74,"categories":75,"keywords":76,"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":78,"name":79,"nameZh":6,"description":80,"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},"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":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},"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",[],[]]