[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7AMDVT9S2DG9RSM2MCAGF1R":3,"skill-same:01M7AMDVT9S2DG9RSM2MCAGF1R":100},{"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":16,"sourceHtmlUrl":17,"categories":18,"keywords":19,"publishedAt":20,"linkOnly":21,"markdownContent":22,"markdownBody":23,"frontMatter":24,"refName":34,"commitSha":35,"skillDirectory":36,"forksCount":14,"repositoryHtmlUrl":37,"repositoryHomepageUrl":6,"ownerHtmlUrl":38,"ownerBlogUrl":6,"ownerDescription":39,"updatedAt":40,"install":41,"resources":54},"01M7AMDVT9S2DG9RSM2MCAGF1R","workorai",null,"WorkorAI talent marketplace skill: candidate job search and employer hiring with white-box match explanations via the WorkorAI MCP server (https:\u002F\u002Fworkorai.com\u002Fmcp). Use when the user asks to find a job, apply to jobs, respond to employer invitations, or when an employer wants to post jobs, search and evaluate candidates, invite them, and review applicants.","GongYuanCaiJi\u002Fdsh-claude-code-templates","GongYuanCaiJi","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F129952120?v=4","01M7AK39Q4W3VPF7C1K8M58BFX","劉昱廷 Yu-Ting Liu","01M7AK39QPS2RAJKRQY0EPQJPZ",0,"MIT","https:\u002F\u002Fgithub.com\u002FGongYuanCaiJi\u002Fdsh-claude-code-templates\u002Fblob\u002Fmain\u002Fskills\u002Fcareer\u002Fworkorai\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002FGongYuanCaiJi\u002Fdsh-claude-code-templates\u002Fblob\u002Fmain\u002Fskills\u002Fcareer\u002Fworkorai\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: workorai\ndescription: \"WorkorAI talent marketplace skill: candidate job search and employer hiring with white-box match explanations via the WorkorAI MCP server (https:\u002F\u002Fworkorai.com\u002Fmcp). Use when the user asks to find a job, apply to jobs, respond to employer invitations, or when an employer wants to post jobs, search and evaluate candidates, invite them, and review applicants.\"\nversion: 0.4.2\nauthor: WorkorAI\nrepo: https:\u002F\u002Fgithub.com\u002Fwork0r-ai\u002Fagent-kit\nlicense: MIT\ntags: [WorkorAI, Job Search, Hiring, Recruiting, Talent Marketplace, MCP]\n---\n\n# WorkorAI\n\nUse this skill for WorkorAI talent marketplace workflows through the\nWorkorAI MCP server. The MCP surface is dual-role (candidate +\nemployer); this skill routes by intent and delegates the heavy\nschema\u002Frecipe detail to the `references\u002F` files.\n\n## Trigger Mapping\n\n- Treat generic candidate job-search requests as WorkorAI intents by\n  default.\n- Treat employer hiring requests as WorkorAI intents when the user\n  asks to hire, post jobs, find candidates, review candidate matches,\n  or configure WorkorAI MCP access.\n- Strong candidate phrases include \"найди мне работу\", \"найти работу\",\n  \"ищу работу\", \"подбери вакансию\", \"хочу работу\", \"find me a job\",\n  \"I need work\", \"help me find a job\", and \"show me jobs\".\n- Strong employer phrases include \"найди кандидатов\", \"хочу нанять\",\n  \"hire developers\", \"find candidates\", \"post a job\", \"search talent\",\n  and \"help me recruit\".\n- Do not wait for the user to say \"WorkorAI\", \"MCP\", or \"API key\".\n- Skip this skill only when the user clearly asks for generic career\n  advice, resume writing, interview coaching, generic hiring advice,\n  or jobs\u002Fcandidates outside WorkorAI.\n\n## First Response — Role Decision\n\n1. Decide role from the user's intent. If genuinely ambiguous, ask\n   one short clarifying question (\"Are you looking for a job or\n   hiring?\") — do not run candidate and employer flows in parallel.\n2. **Candidate intent**: read `references\u002Fcandidate-catalog.md`,\n   `references\u002Fcandidate-recipes.md`, and `references\u002Fauth-flow.md`. Run the\n   candidate flow: discover (`candidate.search_jobs` → `candidate.get_job`)\n   then act (`apply_to_job`, accept\u002Fdecline invitations, withdraw, saved\n   jobs). Edge cases: `references\u002Fcandidate-troubleshooting.md`.\n   - First visible reply: lead with the career-agent persona + value\n     (mirror the user's language), then the one-time setup — use the\n     canonical first-touch in `references\u002Fauth-flow.md` (\"What To Say\n     First (Candidate)\"). This is a developer tool: narrate the steps\n     you run; never print the key value.\n3. **Employer intent**: read `references\u002Femployer-catalog.md`,\n   `references\u002Femployer-recipes.md`, and the employer sections of\n   `references\u002Fauth-flow.md`. Pick the recipe that matches the user's\n   intent (hire-from-specific-job, free-form hire, funnel review,\n   pending-invites cleanup, or job lifecycle).\n   - To FIND \u002F EVALUATE \u002F COMPARE candidates for a vacancy (the core hire flow):\n     `employer.search_candidates_for_job(jobId, tier:'best')` → cascade to\n     `good`\u002F`weak` via `tierCounts` → EXPLAIN each from its `matchExplanation`\n     (lead with `verifiedSkills` = proven in interview, plus the `rationale`) →\n     for the shortlist, `employer.get_candidate_evidence(jobId, userId)` for the\n     interview facts + Q&A → write your own evidence-backed comparative review,\n     then invite. This is the platform's value — you justify the ranking on our\n     white-box data, you are not handing the user a black-box score.\n4. All tools (candidate and employer) are visible in an anonymous\n   `tools\u002Flist` — visibility is discovery, not authorization. The\n   signal you have no usable key is a **failed call**, not a missing\n   tool: an unauthenticated employer call returns\n   `requires employer authentication`. When that happens (or before the\n   first call, if no saved key was found), send the user to the\n   matching onboarding URL (Candidate Home or Employer Dashboard) and\n   accept the new key inline, then retry with the `apiKey` argument.\n5. Do not use shell `curl` or raw JSON-RPC probing unless the user\n   explicitly asks to debug MCP connectivity.\n\n## Saved Key Behavior\n\n- Resolve `scripts\u002Fcredential-store.mjs` relative to this `SKILL.md`.\n- Before asking the user for a key, run a role-scoped lookup:\n  - `node scripts\u002Fcredential-store.mjs get --role=candidate`\n  - `node scripts\u002Fcredential-store.mjs get --role=employer`\n- Default role (no `--role`) is `candidate` for backward compatibility.\n- If a saved key is returned, do not print it. Use it only as the\n  `apiKey` argument for tools in the matching role.\n- When the user provides a new key, validate it with a single tool\n  call in the matching role.\n- After the first successful call with a user-provided key, the next\n  user-facing step must be asking: \"Save this WorkorAI key for future\n  searches on this machine?\"\n- Save with `node scripts\u002Fcredential-store.mjs save --best-effort\n  --role=\u003Crole>` and pass the key through stdin, not the command\n  argument.\n- Use `save --shared-file --role=\u003Crole>` only when the user explicitly\n  wants the shared-file fallback.\n- Never store the key in a repository, chat transcript, visible\n  command line, or MCP config unless the user explicitly chooses that\n  storage mode.\n- Redact WorkorAI keys in user-visible output as `wai_[REDACTED]`.\n\n## Candidate Quick Path\n\n- Onboarding URL chain: `https:\u002F\u002Fworkorai.com\u002Fcandidate\u002Flogin` →\n  `\u002Fcandidate\u002Fprofile` → wait for interview evaluation →\n  `\u002Fcandidate\u002Fhome?tab=mcp` to copy the MCP key.\n- Full 9-tool surface (one candidate key calls all of them — role + ACTIVE\n  access, no per-tool scope):\n  - Discover: `candidate.search_jobs` → `candidate.get_job`.\n  - Apply: `candidate.apply_to_job` (idempotent; gated on a completed +\n    evaluated interview — GATE_LOCKED\u002FGATE_EVALUATING\u002FGATE_FAILED route back\n    to onboarding, do not blind-retry).\n  - Invitations: `candidate.accept_invitation` (→ APPLIED) \u002F\n    `candidate.decline_invitation` (TERMINAL — blocks re-invite; confirm\n    first). See what's pending with `candidate.get_applications`.\n  - Manage: `candidate.withdraw_application` (soft exit, re-invitable),\n    `candidate.set_saved_job` (desired-state, NOT a toggle) \u002F\n    `candidate.get_saved_jobs` (PUBLISHED-only).\n- Always present two distinct links per recommended job: job page\n  (`jobUrl`\u002F`url`) and apply (`applicationUrl`\u002F`applyUrl`). Never show\n  apply-only.\n- Surface `matchScore` and matched\u002Fmissing skills — treat missing skills as\n  gaps to discuss, not rejections. (`matchScore` is `null` on the no-score\n  recency browse — a free-text `q` or a not-yet-interviewed candidate;\n  `seniorityFit`\u002F`matchReasons` are always `UNKNOWN`\u002F`[]`.)\n- Strongest scored match → present an `Agent Pick` (fit bars bound to real\n  `matchExplanation` fields), not a flat list; no-score browse → plain list,\n  no bars. See `references\u002Fcandidate-recipes.md` Recipe 6.\n- Treat raw `jobId` as internal\u002Fdebug metadata unless the user asks\n  for it.\n- Mini-schemas: `references\u002Fcandidate-catalog.md`. Recipes:\n  `references\u002Fcandidate-recipes.md`. Edge cases:\n  `references\u002Fcandidate-troubleshooting.md`.\n\n## Employer Quick Path\n\n- Key issuance URL: `https:\u002F\u002Fworkorai.com\u002Femployer\u002Fdashboard`\n  (Employer MCP card on the page).\n- Hire recipe: `employer.search_candidates_for_job(jobId, tier:'best')` (cascade\n  to `good`\u002F`weak` via `tierCounts`; explain from each `matchExplanation` —\n  `verifiedSkills`\u002F`rationale`) → `employer.get_candidate_evidence(jobId, userId)`\n  for the shortlist (interview facts + Q&A → your own comparative review) →\n  `employer.get_candidate(userId)` (inspect `existingApplications`) →\n  `employer.invite_candidate(jobId, candidateUserId)`. Track with\n  `employer.list_invitations(jobId)` and later\n  `employer.list_applicants(jobId)`.\n- Free-form hire: `employer.search_candidates_by_query(query)` →\n  pick or create a vacancy → invite.\n- Review funnel: `employer.list_applicants(jobId)` →\n  `employer.set_review_status(applicationId, 'SHORTLISTED')` (unlocks\n  contact) → `employer.get_applicant_detail(applicationId)` and\n  optional `employer.get_applicant_transcript`.\n- Re-invite rules: WITHDRAWN can be re-invited (the service UPDATEs\n  the row); DECLINED, INVITED, and APPLIED all block with\n  `INVITE_BLOCKED: INVITE_NOT_ALLOWED`. Always call\n  `employer.get_candidate` first when the candidate has any prior\n  interaction.\n- Contact gating: applicant contact fields are returned only when\n  `reviewStatus ∈ {SHORTLISTED, HIRED}`. Below that, fields are null.\n- `employer.create_job` is synchronous and takes 5-30 s (Gemini\n  parse). On client timeout, do NOT resubmit rawText — recover via\n  `employer.list_jobs({ status: 'DRAFT' })` and pick the newest row.\n- Full mini-schema: `references\u002Femployer-catalog.md`. Recipes:\n  `references\u002Femployer-recipes.md`. Edge cases:\n  `references\u002Femployer-troubleshooting.md`.\n\n## References\n\nRead on demand based on intent:\n\n- `references\u002Fcandidate-catalog.md` — candidate tool mini-schemas (9)\n- `references\u002Fcandidate-recipes.md` — candidate calling-order recipes\n- `references\u002Fcandidate-troubleshooting.md` — candidate-side error scenarios\n- `references\u002Femployer-catalog.md` — employer tool mini-schemas (19)\n- `references\u002Femployer-recipes.md` — employer calling-order recipes\n- `references\u002Femployer-troubleshooting.md` — employer-side error scenarios\n- `references\u002Fauth-flow.md` — candidate and employer onboarding plus\n  saved-key flow\n- `references\u002Ftroubleshooting.md` — general \u002F cross-role MCP issues\n","# WorkorAI\n\nUse this skill for WorkorAI talent marketplace workflows through the\nWorkorAI MCP server. The MCP surface is dual-role (candidate +\nemployer); this skill routes by intent and delegates the heavy\nschema\u002Frecipe detail to the `references\u002F` files.\n\n## Trigger Mapping\n\n- Treat generic candidate job-search requests as WorkorAI intents by\n  default.\n- Treat employer hiring requests as WorkorAI intents when the user\n  asks to hire, post jobs, find candidates, review candidate matches,\n  or configure WorkorAI MCP access.\n- Strong candidate phrases include \"найди мне работу\", \"найти работу\",\n  \"ищу работу\", \"подбери вакансию\", \"хочу работу\", \"find me a job\",\n  \"I need work\", \"help me find a job\", and \"show me jobs\".\n- Strong employer phrases include \"найди кандидатов\", \"хочу нанять\",\n  \"hire developers\", \"find candidates\", \"post a job\", \"search talent\",\n  and \"help me recruit\".\n- Do not wait for the user to say \"WorkorAI\", \"MCP\", or \"API key\".\n- Skip this skill only when the user clearly asks for generic career\n  advice, resume writing, interview coaching, generic hiring advice,\n  or jobs\u002Fcandidates outside WorkorAI.\n\n## First Response — Role Decision\n\n1. Decide role from the user's intent. If genuinely ambiguous, ask\n   one short clarifying question (\"Are you looking for a job or\n   hiring?\") — do not run candidate and employer flows in parallel.\n2. **Candidate intent**: read `references\u002Fcandidate-catalog.md`,\n   `references\u002Fcandidate-recipes.md`, and `references\u002Fauth-flow.md`. Run the\n   candidate flow: discover (`candidate.search_jobs` → `candidate.get_job`)\n   then act (`apply_to_job`, accept\u002Fdecline invitations, withdraw, saved\n   jobs). Edge cases: `references\u002Fcandidate-troubleshooting.md`.\n   - First visible reply: lead with the career-agent persona + value\n     (mirror the user's language), then the one-time setup — use the\n     canonical first-touch in `references\u002Fauth-flow.md` (\"What To Say\n     First (Candidate)\"). This is a developer tool: narrate the steps\n     you run; never print the key value.\n3. **Employer intent**: read `references\u002Femployer-catalog.md`,\n   `references\u002Femployer-recipes.md`, and the employer sections of\n   `references\u002Fauth-flow.md`. Pick the recipe that matches the user's\n   intent (hire-from-specific-job, free-form hire, funnel review,\n   pending-invites cleanup, or job lifecycle).\n   - To FIND \u002F EVALUATE \u002F COMPARE candidates for a vacancy (the core hire flow):\n     `employer.search_candidates_for_job(jobId, tier:'best')` → cascade to\n     `good`\u002F`weak` via `tierCounts` → EXPLAIN each from its `matchExplanation`\n     (lead with `verifiedSkills` = proven in interview, plus the `rationale`) →\n     for the shortlist, `employer.get_candidate_evidence(jobId, userId)` for the\n     interview facts + Q&A → write your own evidence-backed comparative review,\n     then invite. This is the platform's value — you justify the ranking on our\n     white-box data, you are not handing the user a black-box score.\n4. All tools (candidate and employer) are visible in an anonymous\n   `tools\u002Flist` — visibility is discovery, not authorization. The\n   signal you have no usable key is a **failed call**, not a missing\n   tool: an unauthenticated employer call returns\n   `requires employer authentication`. When that happens (or before the\n   first call, if no saved key was found), send the user to the\n   matching onboarding URL (Candidate Home or Employer Dashboard) and\n   accept the new key inline, then retry with the `apiKey` argument.\n5. Do not use shell `curl` or raw JSON-RPC probing unless the user\n   explicitly asks to debug MCP connectivity.\n\n## Saved Key Behavior\n\n- Resolve `scripts\u002Fcredential-store.mjs` relative to this `SKILL.md`.\n- Before asking the user for a key, run a role-scoped lookup:\n  - `node scripts\u002Fcredential-store.mjs get --role=candidate`\n  - `node scripts\u002Fcredential-store.mjs get --role=employer`\n- Default role (no `--role`) is `candidate` for backward compatibility.\n- If a saved key is returned, do not print it. Use it only as the\n  `apiKey` argument for tools in the matching role.\n- When the user provides a new key, validate it with a single tool\n  call in the matching role.\n- After the first successful call with a user-provided key, the next\n  user-facing step must be asking: \"Save this WorkorAI key for future\n  searches on this machine?\"\n- Save with `node scripts\u002Fcredential-store.mjs save --best-effort\n  --role=\u003Crole>` and pass the key through stdin, not the command\n  argument.\n- Use `save --shared-file --role=\u003Crole>` only when the user explicitly\n  wants the shared-file fallback.\n- Never store the key in a repository, chat transcript, visible\n  command line, or MCP config unless the user explicitly chooses that\n  storage mode.\n- Redact WorkorAI keys in user-visible output as `wai_[REDACTED]`.\n\n## Candidate Quick Path\n\n- Onboarding URL chain: `https:\u002F\u002Fworkorai.com\u002Fcandidate\u002Flogin` →\n  `\u002Fcandidate\u002Fprofile` → wait for interview evaluation →\n  `\u002Fcandidate\u002Fhome?tab=mcp` to copy the MCP key.\n- Full 9-tool surface (one candidate key calls all of them — role + ACTIVE\n  access, no per-tool scope):\n  - Discover: `candidate.search_jobs` → `candidate.get_job`.\n  - Apply: `candidate.apply_to_job` (idempotent; gated on a completed +\n    evaluated interview — GATE_LOCKED\u002FGATE_EVALUATING\u002FGATE_FAILED route back\n    to onboarding, do not blind-retry).\n  - Invitations: `candidate.accept_invitation` (→ APPLIED) \u002F\n    `candidate.decline_invitation` (TERMINAL — blocks re-invite; confirm\n    first). See what's pending with `candidate.get_applications`.\n  - Manage: `candidate.withdraw_application` (soft exit, re-invitable),\n    `candidate.set_saved_job` (desired-state, NOT a toggle) \u002F\n    `candidate.get_saved_jobs` (PUBLISHED-only).\n- Always present two distinct links per recommended job: job page\n  (`jobUrl`\u002F`url`) and apply (`applicationUrl`\u002F`applyUrl`). Never show\n  apply-only.\n- Surface `matchScore` and matched\u002Fmissing skills — treat missing skills as\n  gaps to discuss, not rejections. (`matchScore` is `null` on the no-score\n  recency browse — a free-text `q` or a not-yet-interviewed candidate;\n  `seniorityFit`\u002F`matchReasons` are always `UNKNOWN`\u002F`[]`.)\n- Strongest scored match → present an `Agent Pick` (fit bars bound to real\n  `matchExplanation` fields), not a flat list; no-score browse → plain list,\n  no bars. See `references\u002Fcandidate-recipes.md` Recipe 6.\n- Treat raw `jobId` as internal\u002Fdebug metadata unless the user asks\n  for it.\n- Mini-schemas: `references\u002Fcandidate-catalog.md`. Recipes:\n  `references\u002Fcandidate-recipes.md`. Edge cases:\n  `references\u002Fcandidate-troubleshooting.md`.\n\n## Employer Quick Path\n\n- Key issuance URL: `https:\u002F\u002Fworkorai.com\u002Femployer\u002Fdashboard`\n  (Employer MCP card on the page).\n- Hire recipe: `employer.search_candidates_for_job(jobId, tier:'best')` (cascade\n  to `good`\u002F`weak` via `tierCounts`; explain from each `matchExplanation` —\n  `verifiedSkills`\u002F`rationale`) → `employer.get_candidate_evidence(jobId, userId)`\n  for the shortlist (interview facts + Q&A → your own comparative review) →\n  `employer.get_candidate(userId)` (inspect `existingApplications`) →\n  `employer.invite_candidate(jobId, candidateUserId)`. Track with\n  `employer.list_invitations(jobId)` and later\n  `employer.list_applicants(jobId)`.\n- Free-form hire: `employer.search_candidates_by_query(query)` →\n  pick or create a vacancy → invite.\n- Review funnel: `employer.list_applicants(jobId)` →\n  `employer.set_review_status(applicationId, 'SHORTLISTED')` (unlocks\n  contact) → `employer.get_applicant_detail(applicationId)` and\n  optional `employer.get_applicant_transcript`.\n- Re-invite rules: WITHDRAWN can be re-invited (the service UPDATEs\n  the row); DECLINED, INVITED, and APPLIED all block with\n  `INVITE_BLOCKED: INVITE_NOT_ALLOWED`. Always call\n  `employer.get_candidate` first when the candidate has any prior\n  interaction.\n- Contact gating: applicant contact fields are returned only when\n  `reviewStatus ∈ {SHORTLISTED, HIRED}`. Below that, fields are null.\n- `employer.create_job` is synchronous and takes 5-30 s (Gemini\n  parse). On client timeout, do NOT resubmit rawText — recover via\n  `employer.list_jobs({ status: 'DRAFT' })` and pick the newest row.\n- Full mini-schema: `references\u002Femployer-catalog.md`. Recipes:\n  `references\u002Femployer-recipes.md`. Edge cases:\n  `references\u002Femployer-troubleshooting.md`.\n\n## References\n\nRead on demand based on intent:\n\n- `references\u002Fcandidate-catalog.md` — candidate tool mini-schemas (9)\n- `references\u002Fcandidate-recipes.md` — candidate calling-order recipes\n- `references\u002Fcandidate-troubleshooting.md` — candidate-side error scenarios\n- `references\u002Femployer-catalog.md` — employer tool mini-schemas (19)\n- `references\u002Femployer-recipes.md` — employer calling-order recipes\n- `references\u002Femployer-troubleshooting.md` — employer-side error scenarios\n- `references\u002Fauth-flow.md` — candidate and employer onboarding plus\n  saved-key flow\n- `references\u002Ftroubleshooting.md` — general \u002F cross-role MCP issues\n",{"name":5,"repo":25,"tags":26,"author":27,"license":15,"version":33,"description":7},"https:\u002F\u002Fgithub.com\u002Fwork0r-ai\u002Fagent-kit",[27,28,29,30,31,32],"WorkorAI","Job Search","Hiring","Recruiting","Talent Marketplace","MCP","0.4.2","main","51493f354fd03e3f941d4df7fd64c0b8c7a2632d","skills\u002Fcareer\u002Fworkorai","https:\u002F\u002Fgithub.com\u002FGongYuanCaiJi\u002Fdsh-claude-code-templates","https:\u002F\u002Fgithub.com\u002FGongYuanCaiJi","漏洞研究、根因分析、黑箱測試｜做 AI agent 工具｜Vulnerability research, root-cause analysis, AI agent tooling","2026-08-16 02:24:07",{"source":8,"skillName":5,"commands":42,"prompt":52,"zipAvailable":53},[43,46,49],{"tool":44,"command":45},"npx","npx skills add GongYuanCaiJi\u002Fdsh-claude-code-templates --skill workorai",{"tool":47,"command":48},"bunx","bunx skills add GongYuanCaiJi\u002Fdsh-claude-code-templates --skill workorai",{"tool":50,"command":51},"pnpm","pnpm dlx skills add GongYuanCaiJi\u002Fdsh-claude-code-templates --skill workorai","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FGongYuanCaiJi\u002Fdsh-claude-code-templates\u002Fblob\u002Fmain\u002Fskills\u002Fcareer\u002Fworkorai\u002FSKILL.md",true,[55,60,66,70,74,78,82,86,90,94],{"path":56,"resourceType":57,"resourceTypeDesc":58,"sizeBytes":59,"sourceHtmlUrl":16},"LICENSE.txt","LICENSE","许可证",1039,{"path":61,"resourceType":62,"resourceTypeDesc":63,"sizeBytes":64,"sourceHtmlUrl":65},"references\u002Fauth-flow.md","REFERENCE","参考文档",10490,"https:\u002F\u002Fgithub.com\u002FGongYuanCaiJi\u002Fdsh-claude-code-templates\u002Fblob\u002Fmain\u002Fskills\u002Fcareer\u002Fworkorai\u002Freferences\u002Fauth-flow.md",{"path":67,"resourceType":62,"resourceTypeDesc":63,"sizeBytes":68,"sourceHtmlUrl":69},"references\u002Fcandidate-catalog.md",12697,"https:\u002F\u002Fgithub.com\u002FGongYuanCaiJi\u002Fdsh-claude-code-templates\u002Fblob\u002Fmain\u002Fskills\u002Fcareer\u002Fworkorai\u002Freferences\u002Fcandidate-catalog.md",{"path":71,"resourceType":62,"resourceTypeDesc":63,"sizeBytes":72,"sourceHtmlUrl":73},"references\u002Fcandidate-recipes.md",6779,"https:\u002F\u002Fgithub.com\u002FGongYuanCaiJi\u002Fdsh-claude-code-templates\u002Fblob\u002Fmain\u002Fskills\u002Fcareer\u002Fworkorai\u002Freferences\u002Fcandidate-recipes.md",{"path":75,"resourceType":62,"resourceTypeDesc":63,"sizeBytes":76,"sourceHtmlUrl":77},"references\u002Fcandidate-troubleshooting.md",6521,"https:\u002F\u002Fgithub.com\u002FGongYuanCaiJi\u002Fdsh-claude-code-templates\u002Fblob\u002Fmain\u002Fskills\u002Fcareer\u002Fworkorai\u002Freferences\u002Fcandidate-troubleshooting.md",{"path":79,"resourceType":62,"resourceTypeDesc":63,"sizeBytes":80,"sourceHtmlUrl":81},"references\u002Femployer-catalog.md",20045,"https:\u002F\u002Fgithub.com\u002FGongYuanCaiJi\u002Fdsh-claude-code-templates\u002Fblob\u002Fmain\u002Fskills\u002Fcareer\u002Fworkorai\u002Freferences\u002Femployer-catalog.md",{"path":83,"resourceType":62,"resourceTypeDesc":63,"sizeBytes":84,"sourceHtmlUrl":85},"references\u002Femployer-recipes.md",6249,"https:\u002F\u002Fgithub.com\u002FGongYuanCaiJi\u002Fdsh-claude-code-templates\u002Fblob\u002Fmain\u002Fskills\u002Fcareer\u002Fworkorai\u002Freferences\u002Femployer-recipes.md",{"path":87,"resourceType":62,"resourceTypeDesc":63,"sizeBytes":88,"sourceHtmlUrl":89},"references\u002Femployer-troubleshooting.md",6167,"https:\u002F\u002Fgithub.com\u002FGongYuanCaiJi\u002Fdsh-claude-code-templates\u002Fblob\u002Fmain\u002Fskills\u002Fcareer\u002Fworkorai\u002Freferences\u002Femployer-troubleshooting.md",{"path":91,"resourceType":62,"resourceTypeDesc":63,"sizeBytes":92,"sourceHtmlUrl":93},"references\u002Ftroubleshooting.md",5203,"https:\u002F\u002Fgithub.com\u002FGongYuanCaiJi\u002Fdsh-claude-code-templates\u002Fblob\u002Fmain\u002Fskills\u002Fcareer\u002Fworkorai\u002Freferences\u002Ftroubleshooting.md",{"path":95,"resourceType":96,"resourceTypeDesc":97,"sizeBytes":98,"sourceHtmlUrl":99},"scripts\u002Fcredential-store.mjs","SCRIPT","脚本",22996,"https:\u002F\u002Fgithub.com\u002FGongYuanCaiJi\u002Fdsh-claude-code-templates\u002Fblob\u002Fmain\u002Fskills\u002Fcareer\u002Fworkorai\u002Fscripts\u002Fcredential-store.mjs",[101,108,117,124,131,138],{"skillNo":102,"name":103,"nameZh":6,"description":104,"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":20},"01M7ARMYTZ5D4B7N5SKFXV345V","zapier-make-patterns","No-code automation democratizes workflow building. Zapier and Make (formerly Integromat) let non-developers automate business processes without writing code. But no-code doesn't mean no-complexity - these platforms have their own patterns, pitfalls, and breaking points.  This skill covers when to use which platform, how to build reliable automations, and when to graduate to code-based solutions. Key insight: Zapier optimizes for simplicity and integrations (7000+ apps), Make optimizes for power","https:\u002F\u002Fgithub.com\u002FGongYuanCaiJi\u002Fdsh-claude-code-templates\u002Fblob\u002Fmain\u002Fskills\u002Fworkflow-automation\u002Fzapier-make-patterns\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":112,"licenseFileUrl":113,"sourceHtmlUrl":114,"categories":115,"keywords":116,"publishedAt":20},"01M7ARMX1BVNEAR98SBANMDF2V","yeet","Use only when the user explicitly asks to stage, commit, push, and open a GitHub pull request in one flow using the GitHub CLI (`gh`).","Apache-2.0","https:\u002F\u002Fgithub.com\u002FGongYuanCaiJi\u002Fdsh-claude-code-templates\u002Fblob\u002Fmain\u002Fskills\u002Fworkflow-automation\u002Fyeet\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002FGongYuanCaiJi\u002Fdsh-claude-code-templates\u002Fblob\u002Fmain\u002Fskills\u002Fworkflow-automation\u002Fyeet\u002FSKILL.md",[],[],{"skillNo":118,"name":119,"nameZh":6,"description":120,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":121,"categories":122,"keywords":123,"publishedAt":20},"01M7ARMPR4RQ417MG1HMPGNQHH","workflow-automation","Workflow automation is the infrastructure that makes AI agents reliable. Without durable execution, a network hiccup during a 10-step payment flow means lost money and angry customers. With it, workflows resume exactly where they left off.  This skill covers the platforms (n8n, Temporal, Inngest) and patterns (sequential, parallel, orchestrator-worker) that turn brittle scripts into production-grade automation.  Key insight: The platforms make different tradeoffs. n8n optimizes for accessibility","https:\u002F\u002Fgithub.com\u002FGongYuanCaiJi\u002Fdsh-claude-code-templates\u002Fblob\u002Fmain\u002Fskills\u002Fworkflow-automation\u002Fworkflow-automation\u002FSKILL.md",[],[],{"skillNo":125,"name":126,"nameZh":6,"description":127,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":128,"categories":129,"keywords":130,"publishedAt":20},"01M7ARMHBERDMKGDMV7K6MQ6YP","trigger-dev","Trigger.dev expert for background jobs, AI workflows, and reliable async execution with excellent developer experience and TypeScript-first design. Use when: trigger.dev, trigger dev, background task, ai background job, long running task.","https:\u002F\u002Fgithub.com\u002FGongYuanCaiJi\u002Fdsh-claude-code-templates\u002Fblob\u002Fmain\u002Fskills\u002Fworkflow-automation\u002Ftrigger-dev\u002FSKILL.md",[],[],{"skillNo":132,"name":133,"nameZh":6,"description":134,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":135,"categories":136,"keywords":137,"publishedAt":20},"01M7ARME0A7KFT330Q2H25HE2B","slack-automation","Automate Slack workspace operations including messaging, search, channel management, and reaction workflows through Composio's Slack toolkit.","https:\u002F\u002Fgithub.com\u002FGongYuanCaiJi\u002Fdsh-claude-code-templates\u002Fblob\u002Fmain\u002Fskills\u002Fworkflow-automation\u002Fslack-automation\u002FSKILL.md",[],[],{"skillNo":139,"name":140,"nameZh":6,"description":141,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":142,"categories":143,"keywords":144,"publishedAt":20},"01M7ARM8D87V18WDG0GEZS11ZT","planning-with-files","Transforms workflow to use Manus-style persistent markdown files for planning, progress tracking, and knowledge storage. Use when starting complex tasks, multi-step projects, research tasks, or when the user mentions planning, organizing work, tracking progress, or wants structured output.","https:\u002F\u002Fgithub.com\u002FGongYuanCaiJi\u002Fdsh-claude-code-templates\u002Fblob\u002Fmain\u002Fskills\u002Fworkflow-automation\u002Fplanning-with-files\u002FSKILL.md",[],[]]