[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M70FPE2W82PKVT7E2JYDSA55":3,"skill-same:01M70FPE2W82PKVT7E2JYDSA55":72},{"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":23,"publishedAt":44,"linkOnly":45,"markdownContent":46,"markdownBody":47,"frontMatter":48,"refName":50,"commitSha":51,"skillDirectory":52,"forksCount":53,"repositoryHtmlUrl":54,"repositoryHomepageUrl":6,"ownerHtmlUrl":55,"ownerBlogUrl":6,"ownerDescription":56,"updatedAt":57,"install":58,"resources":71},"01M70FPE2W82PKVT7E2JYDSA55","click-path-audit",null,"Trace every user-facing button\u002Ftouchpoint through its full state change sequence to find bugs where functions individually work but cancel each other out, produce wrong final state, or leave the UI in an inconsistent state. Use when: systematic debugging found no bugs but users report broken buttons, or after any major refactor touching shared state stores.","mdnaimul22\u002Fhuman-skills","mdnaimul22","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F64520358?v=4","01M70FH95MH2H796Q01TYSFZ03","Naimul","01M70FH96798CQR4YHA13F17GA",3,"MIT","https:\u002F\u002Fgithub.com\u002Fmdnaimul22\u002Fhuman-skills\u002Fblob\u002Fmain\u002Fskills\u002Fstorage\u002Faffaan-m_ECC\u002Fclick-path-audit\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43],"audit","click path audit","path","click","bugs","but","full","refactor","ui","sequence","systematic","buttons","change","work","when","debugging","systematic debugging","broken","community","shared","2026-11-10 10:12:30",false,"---\nname: click-path-audit\ndescription: \"Trace every user-facing button\u002Ftouchpoint through its full state change sequence to find bugs where functions individually work but cancel each other out, produce wrong final state, or leave the UI in an inconsistent state. Use when: systematic debugging found no bugs but users report broken buttons, or after any major refactor touching shared state stores.\"\nmetadata:\n  origin: community\n---\n\n# \u002Fclick-path-audit — Behavioural Flow Audit\n\nFind bugs that static code reading misses: state interaction side effects, race conditions between sequential calls, and handlers that silently undo each other.\n\n## The Problem This Solves\n\nTraditional debugging checks:\n- Does the function exist? (missing wiring)\n- Does it crash? (runtime errors)\n- Does it return the right type? (data flow)\n\nBut it does NOT check:\n- **Does the final UI state match what the button label promises?**\n- **Does function B silently undo what function A just did?**\n- **Does shared state (Zustand\u002FRedux\u002Fcontext) have side effects that cancel the intended action?**\n\nReal example: A \"New Email\" button called `setComposeMode(true)` then `selectThread(null)`. Both worked individually. But `selectThread` had a side effect resetting `composeMode: false`. The button did nothing. 54 bugs were found by systematic debugging — this one was missed.\n\n---\n\n## How It Works\n\nFor EVERY interactive touchpoint in the target area:\n\n```\n1. IDENTIFY the handler (onClick, onSubmit, onChange, etc.)\n2. TRACE every function call in the handler, IN ORDER\n3. For EACH function call:\n   a. What state does it READ?\n   b. What state does it WRITE?\n   c. Does it have SIDE EFFECTS on shared state?\n   d. Does it reset\u002Fclear any state as a side effect?\n4. CHECK: Does any later call UNDO a state change from an earlier call?\n5. CHECK: Is the FINAL state what the user expects from the button label?\n6. CHECK: Are there race conditions (async calls that resolve in wrong order)?\n```\n\n---\n\n## Execution Steps\n\n### Step 1: Map State Stores\n\nBefore auditing any touchpoint, build a side-effect map of every state store action:\n\n```\nFor each Zustand store \u002F React context in scope:\n  For each action\u002Fsetter:\n    - What fields does it set?\n    - Does it RESET other fields as a side effect?\n    - Document: actionName → {sets: [...], resets: [...]}\n```\n\nThis is the critical reference. The \"New Email\" bug was invisible without knowing that `selectThread` resets `composeMode`.\n\n**Output format:**\n```\nSTORE: emailStore\n  setComposeMode(bool) → sets: {composeMode}\n  selectThread(thread|null) → sets: {selectedThread, selectedThreadId, messages, drafts, selectedDraft, summary} RESETS: {composeMode: false, composeData: null, redraftOpen: false}\n  setDraftGenerating(bool) → sets: {draftGenerating}\n  ...\n\nDANGEROUS RESETS (actions that clear state they don't own):\n  selectThread → resets composeMode (owned by setComposeMode)\n  reset → resets everything\n```\n\n### Step 2: Audit Each Touchpoint\n\nFor each button\u002Ftoggle\u002Fform submit in the target area:\n\n```\nTOUCHPOINT: [Button label] in [Component:line]\n  HANDLER: onClick → {\n    call 1: functionA() → sets {X: true}\n    call 2: functionB() → sets {Y: null} RESETS {X: false}  ← CONFLICT\n  }\n  EXPECTED: User sees [description of what button label promises]\n  ACTUAL: X is false because functionB reset it\n  VERDICT: BUG — [description]\n```\n\n**Check each of these bug patterns:**\n\n#### Pattern 1: Sequential Undo\n```\nhandler() {\n  setState_A(true)     \u002F\u002F sets X = true\n  setState_B(null)     \u002F\u002F side effect: resets X = false\n}\n\u002F\u002F Result: X is false. First call was pointless.\n```\n\n#### Pattern 2: Async Race\n```\nhandler() {\n  fetchA().then(() => setState({ loading: false }))\n  fetchB().then(() => setState({ loading: true }))\n}\n\u002F\u002F Result: final loading state depends on which resolves first\n```\n\n#### Pattern 3: Stale Closure\n```\nconst [count, setCount] = useState(0)\nconst handler = useCallback(() => {\n  setCount(count + 1)  \u002F\u002F captures stale count\n  setCount(count + 1)  \u002F\u002F same stale count — increments by 1, not 2\n}, [count])\n```\n\n#### Pattern 4: Missing State Transition\n```\n\u002F\u002F Button says \"Save\" but handler only validates, never actually saves\n\u002F\u002F Button says \"Delete\" but handler sets a flag without calling the API\n\u002F\u002F Button says \"Send\" but the API endpoint is removed\u002Fbroken\n```\n\n#### Pattern 5: Conditional Dead Path\n```\nhandler() {\n  if (someState) {        \u002F\u002F someState is ALWAYS false at this point\n    doTheActualThing()    \u002F\u002F never reached\n  }\n}\n```\n\n#### Pattern 6: useEffect Interference\n```\n\u002F\u002F Button sets stateX = true\n\u002F\u002F A useEffect watches stateX and resets it to false\n\u002F\u002F User sees nothing happen\n```\n\n### Step 3: Report\n\nFor each bug found:\n\n```\nCLICK-PATH-NNN: [severity: CRITICAL\u002FHIGH\u002FMEDIUM\u002FLOW]\n  Touchpoint: [Button label] in [file:line]\n  Pattern: [Sequential Undo \u002F Async Race \u002F Stale Closure \u002F Missing Transition \u002F Dead Path \u002F useEffect Interference]\n  Handler: [function name or inline]\n  Trace:\n    1. [call] → sets {field: value}\n    2. [call] → RESETS {field: value}  ← CONFLICT\n  Expected: [what user expects]\n  Actual: [what actually happens]\n  Fix: [specific fix]\n```\n\n---\n\n## Scope Control\n\nThis audit is expensive. Scope it appropriately:\n\n- **Full app audit:** Use when launching or after major refactor. Launch parallel agents per page.\n- **Single page audit:** Use after building a new page or after a user reports a broken button.\n- **Store-focused audit:** Use after modifying a Zustand store — audit all consumers of the changed actions.\n\n### Recommended agent split for full app:\n\n```\nAgent 1: Map ALL state stores (Step 1) — this is shared context for all other agents\nAgent 2: Dashboard (Tasks, Notes, Journal, Ideas)\nAgent 3: Chat (DanteChatColumn, JustChatPage)\nAgent 4: Emails (ThreadList, DraftArea, EmailsPage)\nAgent 5: Projects (ProjectsPage, ProjectOverviewTab, NewProjectWizard)\nAgent 6: CRM (all sub-tabs)\nAgent 7: Profile, Settings, Vault, Notifications\nAgent 8: Management Suite (all pages)\n```\n\nAgent 1 MUST complete first. Its output is input for all other agents.\n\n---\n\n## When to Use\n\n- After systematic debugging finds \"no bugs\" but users report broken UI\n- After modifying any Zustand store action (check all callers)\n- After any refactor that touches shared state\n- Before release, on critical user flows\n- When a button \"does nothing\" — this is THE tool for that\n\n## When NOT to Use\n\n- For API-level bugs (wrong response shape, missing endpoint) — use systematic-debugging\n- For styling\u002Flayout issues — visual inspection\n- For performance issues — profiling tools\n\n---\n\n## Integration with Other Skills\n\n- Run AFTER `\u002Fsuperpowers:systematic-debugging` (which finds the other 54 bug types)\n- Run BEFORE `\u002Fsuperpowers:verification-before-completion` (which verifies fixes work)\n- Feeds into `\u002Fsuperpowers:test-driven-development` — every bug found here should get a test\n\n---\n\n## Example: The Bug That Inspired This Skill\n\n**ThreadList.tsx \"New Email\" button:**\n```\nonClick={() => {\n  useEmailStore.getState().setComposeMode(true)   \u002F\u002F ✓ sets composeMode = true\n  useEmailStore.getState().selectThread(null)      \u002F\u002F ✗ RESETS composeMode = false\n}}\n```\n\nStore definition:\n```\nselectThread: (thread) => set({\n  selectedThread: thread,\n  selectedThreadId: thread?.id ?? null,\n  messages: [],\n  drafts: [],\n  selectedDraft: null,\n  summary: null,\n  composeMode: false,     \u002F\u002F ← THIS silent reset killed the button\n  composeData: null,\n  redraftOpen: false,\n})\n```\n\n**Systematic debugging missed it** because:\n- The button has an onClick handler (not dead)\n- Both functions exist (no missing wiring)\n- Neither function crashes (no runtime error)\n- The data types are correct (no type mismatch)\n\n**Click-path audit catches it** because:\n- Step 1 maps `selectThread` resets `composeMode`\n- Step 2 traces the handler: call 1 sets true, call 2 resets false\n- Verdict: Sequential Undo — final state contradicts button intent\n","# \u002Fclick-path-audit — Behavioural Flow Audit\n\nFind bugs that static code reading misses: state interaction side effects, race conditions between sequential calls, and handlers that silently undo each other.\n\n## The Problem This Solves\n\nTraditional debugging checks:\n- Does the function exist? (missing wiring)\n- Does it crash? (runtime errors)\n- Does it return the right type? (data flow)\n\nBut it does NOT check:\n- **Does the final UI state match what the button label promises?**\n- **Does function B silently undo what function A just did?**\n- **Does shared state (Zustand\u002FRedux\u002Fcontext) have side effects that cancel the intended action?**\n\nReal example: A \"New Email\" button called `setComposeMode(true)` then `selectThread(null)`. Both worked individually. But `selectThread` had a side effect resetting `composeMode: false`. The button did nothing. 54 bugs were found by systematic debugging — this one was missed.\n\n---\n\n## How It Works\n\nFor EVERY interactive touchpoint in the target area:\n\n```\n1. IDENTIFY the handler (onClick, onSubmit, onChange, etc.)\n2. TRACE every function call in the handler, IN ORDER\n3. For EACH function call:\n   a. What state does it READ?\n   b. What state does it WRITE?\n   c. Does it have SIDE EFFECTS on shared state?\n   d. Does it reset\u002Fclear any state as a side effect?\n4. CHECK: Does any later call UNDO a state change from an earlier call?\n5. CHECK: Is the FINAL state what the user expects from the button label?\n6. CHECK: Are there race conditions (async calls that resolve in wrong order)?\n```\n\n---\n\n## Execution Steps\n\n### Step 1: Map State Stores\n\nBefore auditing any touchpoint, build a side-effect map of every state store action:\n\n```\nFor each Zustand store \u002F React context in scope:\n  For each action\u002Fsetter:\n    - What fields does it set?\n    - Does it RESET other fields as a side effect?\n    - Document: actionName → {sets: [...], resets: [...]}\n```\n\nThis is the critical reference. The \"New Email\" bug was invisible without knowing that `selectThread` resets `composeMode`.\n\n**Output format:**\n```\nSTORE: emailStore\n  setComposeMode(bool) → sets: {composeMode}\n  selectThread(thread|null) → sets: {selectedThread, selectedThreadId, messages, drafts, selectedDraft, summary} RESETS: {composeMode: false, composeData: null, redraftOpen: false}\n  setDraftGenerating(bool) → sets: {draftGenerating}\n  ...\n\nDANGEROUS RESETS (actions that clear state they don't own):\n  selectThread → resets composeMode (owned by setComposeMode)\n  reset → resets everything\n```\n\n### Step 2: Audit Each Touchpoint\n\nFor each button\u002Ftoggle\u002Fform submit in the target area:\n\n```\nTOUCHPOINT: [Button label] in [Component:line]\n  HANDLER: onClick → {\n    call 1: functionA() → sets {X: true}\n    call 2: functionB() → sets {Y: null} RESETS {X: false}  ← CONFLICT\n  }\n  EXPECTED: User sees [description of what button label promises]\n  ACTUAL: X is false because functionB reset it\n  VERDICT: BUG — [description]\n```\n\n**Check each of these bug patterns:**\n\n#### Pattern 1: Sequential Undo\n```\nhandler() {\n  setState_A(true)     \u002F\u002F sets X = true\n  setState_B(null)     \u002F\u002F side effect: resets X = false\n}\n\u002F\u002F Result: X is false. First call was pointless.\n```\n\n#### Pattern 2: Async Race\n```\nhandler() {\n  fetchA().then(() => setState({ loading: false }))\n  fetchB().then(() => setState({ loading: true }))\n}\n\u002F\u002F Result: final loading state depends on which resolves first\n```\n\n#### Pattern 3: Stale Closure\n```\nconst [count, setCount] = useState(0)\nconst handler = useCallback(() => {\n  setCount(count + 1)  \u002F\u002F captures stale count\n  setCount(count + 1)  \u002F\u002F same stale count — increments by 1, not 2\n}, [count])\n```\n\n#### Pattern 4: Missing State Transition\n```\n\u002F\u002F Button says \"Save\" but handler only validates, never actually saves\n\u002F\u002F Button says \"Delete\" but handler sets a flag without calling the API\n\u002F\u002F Button says \"Send\" but the API endpoint is removed\u002Fbroken\n```\n\n#### Pattern 5: Conditional Dead Path\n```\nhandler() {\n  if (someState) {        \u002F\u002F someState is ALWAYS false at this point\n    doTheActualThing()    \u002F\u002F never reached\n  }\n}\n```\n\n#### Pattern 6: useEffect Interference\n```\n\u002F\u002F Button sets stateX = true\n\u002F\u002F A useEffect watches stateX and resets it to false\n\u002F\u002F User sees nothing happen\n```\n\n### Step 3: Report\n\nFor each bug found:\n\n```\nCLICK-PATH-NNN: [severity: CRITICAL\u002FHIGH\u002FMEDIUM\u002FLOW]\n  Touchpoint: [Button label] in [file:line]\n  Pattern: [Sequential Undo \u002F Async Race \u002F Stale Closure \u002F Missing Transition \u002F Dead Path \u002F useEffect Interference]\n  Handler: [function name or inline]\n  Trace:\n    1. [call] → sets {field: value}\n    2. [call] → RESETS {field: value}  ← CONFLICT\n  Expected: [what user expects]\n  Actual: [what actually happens]\n  Fix: [specific fix]\n```\n\n---\n\n## Scope Control\n\nThis audit is expensive. Scope it appropriately:\n\n- **Full app audit:** Use when launching or after major refactor. Launch parallel agents per page.\n- **Single page audit:** Use after building a new page or after a user reports a broken button.\n- **Store-focused audit:** Use after modifying a Zustand store — audit all consumers of the changed actions.\n\n### Recommended agent split for full app:\n\n```\nAgent 1: Map ALL state stores (Step 1) — this is shared context for all other agents\nAgent 2: Dashboard (Tasks, Notes, Journal, Ideas)\nAgent 3: Chat (DanteChatColumn, JustChatPage)\nAgent 4: Emails (ThreadList, DraftArea, EmailsPage)\nAgent 5: Projects (ProjectsPage, ProjectOverviewTab, NewProjectWizard)\nAgent 6: CRM (all sub-tabs)\nAgent 7: Profile, Settings, Vault, Notifications\nAgent 8: Management Suite (all pages)\n```\n\nAgent 1 MUST complete first. Its output is input for all other agents.\n\n---\n\n## When to Use\n\n- After systematic debugging finds \"no bugs\" but users report broken UI\n- After modifying any Zustand store action (check all callers)\n- After any refactor that touches shared state\n- Before release, on critical user flows\n- When a button \"does nothing\" — this is THE tool for that\n\n## When NOT to Use\n\n- For API-level bugs (wrong response shape, missing endpoint) — use systematic-debugging\n- For styling\u002Flayout issues — visual inspection\n- For performance issues — profiling tools\n\n---\n\n## Integration with Other Skills\n\n- Run AFTER `\u002Fsuperpowers:systematic-debugging` (which finds the other 54 bug types)\n- Run BEFORE `\u002Fsuperpowers:verification-before-completion` (which verifies fixes work)\n- Feeds into `\u002Fsuperpowers:test-driven-development` — every bug found here should get a test\n\n---\n\n## Example: The Bug That Inspired This Skill\n\n**ThreadList.tsx \"New Email\" button:**\n```\nonClick={() => {\n  useEmailStore.getState().setComposeMode(true)   \u002F\u002F ✓ sets composeMode = true\n  useEmailStore.getState().selectThread(null)      \u002F\u002F ✗ RESETS composeMode = false\n}}\n```\n\nStore definition:\n```\nselectThread: (thread) => set({\n  selectedThread: thread,\n  selectedThreadId: thread?.id ?? null,\n  messages: [],\n  drafts: [],\n  selectedDraft: null,\n  summary: null,\n  composeMode: false,     \u002F\u002F ← THIS silent reset killed the button\n  composeData: null,\n  redraftOpen: false,\n})\n```\n\n**Systematic debugging missed it** because:\n- The button has an onClick handler (not dead)\n- Both functions exist (no missing wiring)\n- Neither function crashes (no runtime error)\n- The data types are correct (no type mismatch)\n\n**Click-path audit catches it** because:\n- Step 1 maps `selectThread` resets `composeMode`\n- Step 2 traces the handler: call 1 sets true, call 2 resets false\n- Verdict: Sequential Undo — final state contradicts button intent\n",{"name":5,"metadata":49,"description":7},{"origin":42},"main","74715deacdc69119d739f38916f8ee4f0f979ebf","skills\u002Fstorage\u002Faffaan-m_ECC\u002Fclick-path-audit",0,"https:\u002F\u002Fgithub.com\u002Fmdnaimul22\u002Fhuman-skills","https:\u002F\u002Fgithub.com\u002Fmdnaimul22","AI Agents Workflows Automation | Specializing in Python, FastAPI, MCP Agents & Custom ERP.","2026-11-11 21:16:57",{"source":8,"skillName":5,"commands":59,"prompt":69,"zipAvailable":70},[60,63,66],{"tool":61,"command":62},"npx","npx skills add mdnaimul22\u002Fhuman-skills --skill click-path-audit",{"tool":64,"command":65},"bunx","bunx skills add mdnaimul22\u002Fhuman-skills --skill click-path-audit",{"tool":67,"command":68},"pnpm","pnpm dlx skills add mdnaimul22\u002Fhuman-skills --skill click-path-audit","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fmdnaimul22\u002Fhuman-skills\u002Fblob\u002Fmain\u002Fskills\u002Fstorage\u002Faffaan-m_ECC\u002Fclick-path-audit\u002FSKILL.md",true,[],[73,81,107,129,148,163],{"skillNo":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":79,"publishedAt":80},"01M72JT3YP1SQHD0MANGDXQ4RT","higgsfield-websites","Build, edit, and deploy full-stack websites, apps and games via the Higgsfield CLI (`higgsfield website …`). Each is a React 19 + TanStack Start SSR app in one Cloudflare Worker (D1\u002FR2\u002FKV\u002FDO\u002FContainers). THREE product types, picked via `--type` on create: `website` (standalone, no Higgsfield integration — references\u002Fwebsite-flow.md), `app` (Sign in with Higgsfield + fnf SDK, Quanta — references\u002Fapp-flow.md), `game` (realtime multiplayer rooms — references\u002Fgame-flow.md). Routes to the right flow; each carries its own rules and deploy\u002Fpublish gates.\nUse when: \"build me a website\", \"make a landing page\", \"create a web app\", \"build a SaaS dashboard \u002F portfolio\", \"make me a game\", \"deploy this site\", \"publish\". Also owns GAME ART: \"make a spritesheet\", \"tileable texture\", \"animate a 3D character\", game music\u002FSFX — see the game-* references.\nNOT for: single image\u002Fvideo\u002Faudio generation (higgsfield-generate), product photos (higgsfield-product-photoshoot), marketplace cards (higgsfield-marketplace-cards).","https:\u002F\u002Fgithub.com\u002Fmdnaimul22\u002Fhuman-skills\u002Fblob\u002Fmain\u002Fskills\u002Fstorage\u002Fhiggsfield-ai_skills\u002Fhiggsfield-websites\u002FSKILL.md",[],[],"2026-11-10 22:39:42",{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":99,"publishedAt":44},"01M70JPK8HAXXA85P7Q8NKZZYG","writing-skills","Use when creating new skills, editing existing skills, or verifying skills work before deployment","https:\u002F\u002Fgithub.com\u002Fmdnaimul22\u002Fhuman-skills\u002Fblob\u002Fmain\u002Fskills\u002Fstorage\u002Fobra_superpowers\u002Fwriting-skills\u002FSKILL.md",[87,90,95,96],{"categoryNo":88,"categoryName":89,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":91,"categoryName":92,"taxonomyType":93,"taxonomyTypeDesc":94},"01JBSEEDCAT000000000000036","内容创作者","PROFESSION","适用职业",{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":97,"categoryName":98,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000008","测试与质量",[100,101,102,103,104,105,106,38,37],"writing","writing skills","editing","deployment","use","Existing","new",{"skillNo":108,"name":109,"nameZh":6,"description":110,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":111,"categories":112,"keywords":118,"publishedAt":44},"01M70JP4PHBH1CQVVDWZ94W159","writing-plans","Use when you have a spec or requirements for a multi-step task, before touching code","https:\u002F\u002Fgithub.com\u002Fmdnaimul22\u002Fhuman-skills\u002Fblob\u002Fmain\u002Fskills\u002Fstorage\u002Fobra_superpowers\u002Fwriting-plans\u002FSKILL.md",[113,114,115],{"categoryNo":88,"categoryName":89,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":91,"categoryName":92,"taxonomyType":93,"taxonomyTypeDesc":94},{"categoryNo":116,"categoryName":117,"taxonomyType":93,"taxonomyTypeDesc":94},"01JBSEEDCAT000000000000030","开发工程师",[100,119,120,121,38,122,123,104,124,125,126,127,128],"writing plans","plans","you","code","for","requirements","task","multi","spec","multi-step task",{"skillNo":130,"name":131,"nameZh":6,"description":132,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":133,"categories":134,"keywords":135,"publishedAt":44},"01M70JNTYVGXFZT8PASZ844TH8","verification-before-completion","Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always","https:\u002F\u002Fgithub.com\u002Fmdnaimul22\u002Fhuman-skills\u002Fblob\u002Fmain\u002Fskills\u002Fstorage\u002Fobra_superpowers\u002Fverification-before-completion\u002FSKILL.md",[],[136,137,138,139,140,141,104,142,143,144,38,145,37,146,147],"verification","verification before completion","complete","about","output","assertions","prs","evidence","claim","claims","commands","running",{"skillNo":149,"name":150,"nameZh":6,"description":151,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":152,"categories":153,"keywords":155,"publishedAt":44},"01M70JNGVSQDESWN0Q5BPJ875V","using-superpowers","Use when starting any conversation - establishes how to find and use skills, requiring skill invocation before ANY response including clarifying questions","https:\u002F\u002Fgithub.com\u002Fmdnaimul22\u002Fhuman-skills\u002Fblob\u002Fmain\u002Fskills\u002Fstorage\u002Fobra_superpowers\u002Fusing-superpowers\u002FSKILL.md",[154],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[156,157,158,159,104,38,160,161,162],"using superpowers","superpowers","conversation","how to","how","find","questions",{"skillNo":164,"name":165,"nameZh":6,"description":166,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":167,"categories":168,"keywords":169,"publishedAt":44},"01M70JN57CE588NPYPYTWH1DWG","using-git-worktrees","Use when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git worktree fallback","https:\u002F\u002Fgithub.com\u002Fmdnaimul22\u002Fhuman-skills\u002Fblob\u002Fmain\u002Fskills\u002Fstorage\u002Fobra_superpowers\u002Fusing-git-worktrees\u002FSKILL.md",[],[170,171,172,173,174,175,38,37,176,177,178,179,180,181,182,120,104,183,184],"using git worktrees","Using git","git","worktrees","git worktrees","implementation","git worktree","worktree","native","Tools","isolation","fallback","feature","via","workspace"]