[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7CM1ATTR7TMB3HC8R2J3TBB":3,"skill-same:01M7CM1ATTR7TMB3HC8R2J3TBB":48},{"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":14,"repositoryHtmlUrl":31,"repositoryHomepageUrl":6,"ownerHtmlUrl":32,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":33,"install":34,"resources":47},"01M7CM1ATTR7TMB3HC8R2J3TBB","coordinator-mode",null,"Advanced multi-agent orchestration with parallel workers, synthesis protocols, and coordinator lifecycle. Use when complex tasks require multiple agents working in parallel with intelligent result synthesis.","haliltek\u002Fdev.tr","haliltek","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F31656259?v=4","01M7CKZCVHYRZ5CFNDBMFT5S7Q","Halil TEK","01M7CKZCWH3RX91D93NHE4DP2J",0,"AGPL-3.0","https:\u002F\u002Fgithub.com\u002Fhaliltek\u002Fdev.tr\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fcoordinator-mode\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: coordinator-mode\ndescription: Advanced multi-agent orchestration with parallel workers, synthesis protocols, and coordinator lifecycle. Use when complex tasks require multiple agents working in parallel with intelligent result synthesis.\nwhen_to_use: \"When the user needs multi-agent coordination, parallel task execution, complex multi-domain work, or when \u002Fcoordinate or \u002Forchestrate is invoked. NOT for single-domain tasks.\"\nallowed-tools: Read, Grep, Glob, Bash, Write, Edit, Agent\nversion: 1.0.0\neffort: high\n---\n\n# Coordinator Mode — Multi-Agent Orchestration\n\n> Distilled from production-proven coordinator patterns. Transforms sequential agent chains into intelligent parallel orchestration.\n\n## Overview\n\nThe Coordinator is a specialized orchestration mode where **you become the conductor** — decomposing complex tasks into worker subtasks, dispatching them in parallel where safe, and synthesizing results into cohesive output.\n\n**You are NOT a worker. You are the coordinator.** Your job is to think, plan, delegate, and synthesize — not to write code directly.\n\n---\n\n## Coordinator Lifecycle\n\n```\nUser Request\n    ↓\n1. DECOMPOSE — Break task into worker subtasks\n    ↓\n2. CLASSIFY — Mark each subtask: Research | Implementation | Verification\n    ↓\n3. DISPATCH — Launch workers (parallel for reads, sequential for writes)\n    ↓\n4. MONITOR — Track worker completion notifications\n    ↓\n5. SYNTHESIZE — Combine results into unified response\n    ↓\n6. VERIFY — Ensure completeness before reporting to user\n```\n\n---\n\n## Phase-Based Workflow\n\n| Phase | Purpose | Concurrency | Worker Type |\n|-------|---------|-------------|-------------|\n| **Research** | Gather information, explore codebase | ✅ Fully parallel | Read-only agents |\n| **Synthesis** | Analyze findings, plan approach | ❌ Coordinator only | No workers |\n| **Implementation** | Make changes to code\u002Ffiles | ⚠️ Sequential per file set | Write-capable agents |\n| **Verification** | Test, lint, validate changes | ✅ Parallel (independent) | Test\u002Fsecurity agents |\n\n> 🔴 **Rule:** NEVER skip the Synthesis phase. Research → direct Implementation = poor results.\n\n---\n\n## Concurrency Rules\n\n### Safe to Parallelize\n- ✅ Multiple agents reading different files\n- ✅ Security audit + performance audit (read-only)\n- ✅ Test runner + linter (independent)\n- ✅ Exploring different directories\n\n### Must Be Sequential\n- ❌ Two agents writing to the same file\n- ❌ Implementation that depends on another agent's output\n- ❌ Database migration + code that uses the new schema\n- ❌ API change + frontend that consumes the API\n\n---\n\n## Worker Prompt Writing Guide\n\n### 🔴 The Golden Rule: Never Delegate Understanding\n\n```\n❌ WRONG: \"Based on your findings, fix the bug\"\n❌ WRONG: \"Based on the research, implement it\"\n❌ WRONG: \"Look at the code and do what's needed\"\n\n✅ RIGHT: \"The bug is in src\u002Fauth\u002Fjwt.ts line 45 — the token expiry\n          check uses `\u003C` instead of `\u003C=`, causing off-by-one failures\n          at exactly the expiry time. Change line 45 from\n          `if (now \u003C expiry)` to `if (now \u003C= expiry)`\"\n```\n\n> **Why:** Phrases like \"based on your findings\" push synthesis onto the worker instead of doing it yourself. Write prompts that prove YOU understood — include file paths, line numbers, what specifically to change.\n\n### Writing Effective Worker Prompts\n\nBrief the worker like a **smart colleague who just walked into the room**:\n\n1. **Explain what** you're trying to accomplish and why\n2. **Describe what** you've already learned or ruled out\n3. **Give enough context** about the surrounding problem for judgment calls\n4. **Be specific** about scope: what's in, what's out, what another agent handles\n5. **State the output format** you expect (\"report in under 200 words\")\n\n### Prompt Templates\n\n#### Research Worker\n```\nInvestigate [specific question] in [file\u002Fdirectory scope].\nContext: We're trying to [goal] because [reason].\nI've already checked [what you checked] and found [what you found].\nReport: List [specific deliverable]. Under 200 words.\n```\n\n#### Implementation Worker\n```\nModify [specific file(s)] to [specific change].\nContext: [Why this change is needed].\nThe current code at [file:line] does [X], change it to [Y].\nConstraints: Don't touch [out-of-scope files]. Another agent handles [related area].\nVerify: [How the worker should confirm success].\n```\n\n#### Verification Worker\n```\nVerify that [specific change] works correctly.\nRun: [specific commands].\nCheck: [what success looks like].\nReport: Pass\u002Ffail with details on any failures.\n```\n\n---\n\n## Fork Semantics\n\n### When to Fork (vs. Spawn Fresh Agent)\n\n| Scenario | Action | Why |\n|----------|--------|-----|\n| Open-ended research question | **Fork** (omit agent type) | Fork inherits context, shorter prompt |\n| Independent parallel research | **Fork** multiple in one message | Each fork shares cache |\n| Specialized domain work | **Spawn** (specify agent type) | Fresh specialist starts clean |\n| Second opinion on your work | **Spawn** | Independent perspective |\n\n### Fork Rules\n\n1. **Don't peek.** Don't read the fork's output file mid-flight. You'll get a completion notification. Reading the transcript pulls tool noise into your context.\n\n2. **Don't race.** After launching, you know nothing about what the fork found. Never fabricate or predict fork results. If the user asks before notification lands, say \"the fork is still running.\"\n\n3. **Keep prompts short.** Forks inherit your full context — write a *directive* (what to do), not a *briefing* (what the situation is).\n\n---\n\n## Anti-Patterns\n\n| Anti-Pattern | Why It's Bad | Fix |\n|---|---|---|\n| \"Look at the code and fix it\" | Zero context = workers make wrong assumptions | Provide specific file paths, line numbers, and what to change |\n| Skipping Research phase | Implementation without understanding = rework | Always research first, even briefly |\n| Launching 10+ workers at once | Overwhelms synthesis, diminishing returns | 2-5 workers per round, synthesize, then more if needed |\n| Fabricating worker results | User gets wrong information | Wait for actual notification, say \"still running\" if asked |\n| Coordinator writes code directly | Loses orchestration benefits | Always delegate to appropriate specialist |\n\n---\n\n## Synthesis Protocol\n\nAfter all workers complete:\n\n```markdown\n## Coordinator Synthesis\n\n### Task: [Original Request]\n\n### Workers Dispatched\n| Worker | Type | Status | Key Finding |\n|--------|------|--------|-------------|\n| agent-1 | Research | ✅ | Found X in file Y |\n| agent-2 | Research | ✅ | Identified Y pattern |\n\n### Consolidated Analysis\n[Your synthesis — not a copy-paste of worker output]\n\n### Decision & Rationale\n[What you decided based on ALL worker findings and why]\n\n### Implementation Plan\n1. [Specific change with file path]\n2. [Specific change with file path]\n\n### Remaining Risk\n- [Anything workers flagged but couldn't resolve]\n```\n\n---\n\n## Continue vs. Spawn Decision\n\n| Situation | Action |\n|-----------|--------|\n| Worker completed, need follow-up on same topic | **Continue** (send message to worker ID) |\n| Worker completed, need different domain work | **Spawn new** specialist |\n| Worker failed, need retry with same context | **Continue** with corrected instructions |\n| Worker failed, need fundamentally different approach | **Spawn new** |\n\n---\n\n## Best Practices\n\n1. **Start with 2-3 workers** — add more after synthesis if needed\n2. **Research before implementation** — always, even for \"simple\" tasks\n3. **Synthesize, don't copy** — your summary should add insight, not repeat\n4. **Verify independently** — verification workers shouldn't trust implementation workers\n5. **Track state** — note which workers are pending\u002Fcompleted\u002Ffailed\n6. **Share scratchpad** — use a known directory for cross-worker artifacts\n","# Coordinator Mode — Multi-Agent Orchestration\n\n> Distilled from production-proven coordinator patterns. Transforms sequential agent chains into intelligent parallel orchestration.\n\n## Overview\n\nThe Coordinator is a specialized orchestration mode where **you become the conductor** — decomposing complex tasks into worker subtasks, dispatching them in parallel where safe, and synthesizing results into cohesive output.\n\n**You are NOT a worker. You are the coordinator.** Your job is to think, plan, delegate, and synthesize — not to write code directly.\n\n---\n\n## Coordinator Lifecycle\n\n```\nUser Request\n    ↓\n1. DECOMPOSE — Break task into worker subtasks\n    ↓\n2. CLASSIFY — Mark each subtask: Research | Implementation | Verification\n    ↓\n3. DISPATCH — Launch workers (parallel for reads, sequential for writes)\n    ↓\n4. MONITOR — Track worker completion notifications\n    ↓\n5. SYNTHESIZE — Combine results into unified response\n    ↓\n6. VERIFY — Ensure completeness before reporting to user\n```\n\n---\n\n## Phase-Based Workflow\n\n| Phase | Purpose | Concurrency | Worker Type |\n|-------|---------|-------------|-------------|\n| **Research** | Gather information, explore codebase | ✅ Fully parallel | Read-only agents |\n| **Synthesis** | Analyze findings, plan approach | ❌ Coordinator only | No workers |\n| **Implementation** | Make changes to code\u002Ffiles | ⚠️ Sequential per file set | Write-capable agents |\n| **Verification** | Test, lint, validate changes | ✅ Parallel (independent) | Test\u002Fsecurity agents |\n\n> 🔴 **Rule:** NEVER skip the Synthesis phase. Research → direct Implementation = poor results.\n\n---\n\n## Concurrency Rules\n\n### Safe to Parallelize\n- ✅ Multiple agents reading different files\n- ✅ Security audit + performance audit (read-only)\n- ✅ Test runner + linter (independent)\n- ✅ Exploring different directories\n\n### Must Be Sequential\n- ❌ Two agents writing to the same file\n- ❌ Implementation that depends on another agent's output\n- ❌ Database migration + code that uses the new schema\n- ❌ API change + frontend that consumes the API\n\n---\n\n## Worker Prompt Writing Guide\n\n### 🔴 The Golden Rule: Never Delegate Understanding\n\n```\n❌ WRONG: \"Based on your findings, fix the bug\"\n❌ WRONG: \"Based on the research, implement it\"\n❌ WRONG: \"Look at the code and do what's needed\"\n\n✅ RIGHT: \"The bug is in src\u002Fauth\u002Fjwt.ts line 45 — the token expiry\n          check uses `\u003C` instead of `\u003C=`, causing off-by-one failures\n          at exactly the expiry time. Change line 45 from\n          `if (now \u003C expiry)` to `if (now \u003C= expiry)`\"\n```\n\n> **Why:** Phrases like \"based on your findings\" push synthesis onto the worker instead of doing it yourself. Write prompts that prove YOU understood — include file paths, line numbers, what specifically to change.\n\n### Writing Effective Worker Prompts\n\nBrief the worker like a **smart colleague who just walked into the room**:\n\n1. **Explain what** you're trying to accomplish and why\n2. **Describe what** you've already learned or ruled out\n3. **Give enough context** about the surrounding problem for judgment calls\n4. **Be specific** about scope: what's in, what's out, what another agent handles\n5. **State the output format** you expect (\"report in under 200 words\")\n\n### Prompt Templates\n\n#### Research Worker\n```\nInvestigate [specific question] in [file\u002Fdirectory scope].\nContext: We're trying to [goal] because [reason].\nI've already checked [what you checked] and found [what you found].\nReport: List [specific deliverable]. Under 200 words.\n```\n\n#### Implementation Worker\n```\nModify [specific file(s)] to [specific change].\nContext: [Why this change is needed].\nThe current code at [file:line] does [X], change it to [Y].\nConstraints: Don't touch [out-of-scope files]. Another agent handles [related area].\nVerify: [How the worker should confirm success].\n```\n\n#### Verification Worker\n```\nVerify that [specific change] works correctly.\nRun: [specific commands].\nCheck: [what success looks like].\nReport: Pass\u002Ffail with details on any failures.\n```\n\n---\n\n## Fork Semantics\n\n### When to Fork (vs. Spawn Fresh Agent)\n\n| Scenario | Action | Why |\n|----------|--------|-----|\n| Open-ended research question | **Fork** (omit agent type) | Fork inherits context, shorter prompt |\n| Independent parallel research | **Fork** multiple in one message | Each fork shares cache |\n| Specialized domain work | **Spawn** (specify agent type) | Fresh specialist starts clean |\n| Second opinion on your work | **Spawn** | Independent perspective |\n\n### Fork Rules\n\n1. **Don't peek.** Don't read the fork's output file mid-flight. You'll get a completion notification. Reading the transcript pulls tool noise into your context.\n\n2. **Don't race.** After launching, you know nothing about what the fork found. Never fabricate or predict fork results. If the user asks before notification lands, say \"the fork is still running.\"\n\n3. **Keep prompts short.** Forks inherit your full context — write a *directive* (what to do), not a *briefing* (what the situation is).\n\n---\n\n## Anti-Patterns\n\n| Anti-Pattern | Why It's Bad | Fix |\n|---|---|---|\n| \"Look at the code and fix it\" | Zero context = workers make wrong assumptions | Provide specific file paths, line numbers, and what to change |\n| Skipping Research phase | Implementation without understanding = rework | Always research first, even briefly |\n| Launching 10+ workers at once | Overwhelms synthesis, diminishing returns | 2-5 workers per round, synthesize, then more if needed |\n| Fabricating worker results | User gets wrong information | Wait for actual notification, say \"still running\" if asked |\n| Coordinator writes code directly | Loses orchestration benefits | Always delegate to appropriate specialist |\n\n---\n\n## Synthesis Protocol\n\nAfter all workers complete:\n\n```markdown\n## Coordinator Synthesis\n\n### Task: [Original Request]\n\n### Workers Dispatched\n| Worker | Type | Status | Key Finding |\n|--------|------|--------|-------------|\n| agent-1 | Research | ✅ | Found X in file Y |\n| agent-2 | Research | ✅ | Identified Y pattern |\n\n### Consolidated Analysis\n[Your synthesis — not a copy-paste of worker output]\n\n### Decision & Rationale\n[What you decided based on ALL worker findings and why]\n\n### Implementation Plan\n1. [Specific change with file path]\n2. [Specific change with file path]\n\n### Remaining Risk\n- [Anything workers flagged but couldn't resolve]\n```\n\n---\n\n## Continue vs. Spawn Decision\n\n| Situation | Action |\n|-----------|--------|\n| Worker completed, need follow-up on same topic | **Continue** (send message to worker ID) |\n| Worker completed, need different domain work | **Spawn new** specialist |\n| Worker failed, need retry with same context | **Continue** with corrected instructions |\n| Worker failed, need fundamentally different approach | **Spawn new** |\n\n---\n\n## Best Practices\n\n1. **Start with 2-3 workers** — add more after synthesis if needed\n2. **Research before implementation** — always, even for \"simple\" tasks\n3. **Synthesize, don't copy** — your summary should add insight, not repeat\n4. **Verify independently** — verification workers shouldn't trust implementation workers\n5. **Track state** — note which workers are pending\u002Fcompleted\u002Ffailed\n6. **Share scratchpad** — use a known directory for cross-worker artifacts\n",{"name":5,"effort":24,"version":25,"description":7,"when_to_use":26,"allowed-tools":27},"high","1.0.0","When the user needs multi-agent coordination, parallel task execution, complex multi-domain work, or when \u002Fcoordinate or \u002Forchestrate is invoked. NOT for single-domain tasks.","Read, Grep, Glob, Bash, Write, Edit, Agent","main","35fc33da79b31d7f8dadfc704083baff1b5672a0",".agents\u002Fskills\u002Fcoordinator-mode","https:\u002F\u002Fgithub.com\u002Fhaliltek\u002Fdev.tr","https:\u002F\u002Fgithub.com\u002Fhaliltek","2026-11-13 01:38:48",{"source":8,"skillName":5,"commands":35,"prompt":45,"zipAvailable":46},[36,39,42],{"tool":37,"command":38},"npx","npx skills add haliltek\u002Fdev.tr --skill coordinator-mode",{"tool":40,"command":41},"bunx","bunx skills add haliltek\u002Fdev.tr --skill coordinator-mode",{"tool":43,"command":44},"pnpm","pnpm dlx skills add haliltek\u002Fdev.tr --skill coordinator-mode","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fhaliltek\u002Fdev.tr\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fcoordinator-mode\u002FSKILL.md",true,[],[49,56,63,70,77,84],{"skillNo":50,"name":51,"nameZh":6,"description":52,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":53,"categories":54,"keywords":55,"publishedAt":19},"01M7CM8JAC0X6HVS8VCHH51KPZ","respectfully","Wraps any prompt with a reminder to respect CLAUDE.md files","https:\u002F\u002Fgithub.com\u002Fhaliltek\u002Fdev.tr\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Frespectfully\u002FSKILL.md",[],[],{"skillNo":57,"name":58,"nameZh":6,"description":59,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":60,"categories":61,"keywords":62,"publishedAt":19},"01M7CM8FPHK4J5EP607Y77XHA4","recruiter","Think like a skeptical technical recruiter when working on the daily.dev Recruiter platform. Use when reviewing UI\u002FUX, features, or code in webapp\u002Fpages\u002Frecruiter.","https:\u002F\u002Fgithub.com\u002Fhaliltek\u002Fdev.tr\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Frecruiter\u002FSKILL.md",[],[],{"skillNo":64,"name":65,"nameZh":6,"description":66,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":67,"categories":68,"keywords":69,"publishedAt":19},"01M7CM8CB9XR2W46XJ3T2X0245","changelog","Generate a daily.dev changelog post for a new feature or update. Use when a team member needs to write a changelog announcement.","https:\u002F\u002Fgithub.com\u002Fhaliltek\u002Fdev.tr\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fchangelog\u002FSKILL.md",[],[],{"skillNo":71,"name":72,"nameZh":6,"description":73,"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},"01M7CM88HKHZP4S2H9GYKWCBPB","webapp-testing","Web application testing principles. E2E, Playwright, deep audit strategies.","https:\u002F\u002Fgithub.com\u002Fhaliltek\u002Fdev.tr\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fwebapp-testing\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},"01M7CM831R2XYCHFNRGXD6NYS1","web-design-guidelines","Review UI code for Web Interface Guidelines compliance. Use when asked to \"review my UI\", \"check accessibility\", \"audit design\", \"review UX\", or \"check my site against best practices\".","https:\u002F\u002Fgithub.com\u002Fhaliltek\u002Fdev.tr\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fweb-design-guidelines\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},"01M7CM7XTJ13ZQFZ9Y5SRYF8CP","vulnerability-scanner","Advanced vulnerability analysis principles. OWASP 2025, Supply Chain Security, attack surface mapping, risk prioritization.","https:\u002F\u002Fgithub.com\u002Fhaliltek\u002Fdev.tr\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fvulnerability-scanner\u002FSKILL.md",[],[]]