[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6QAJCTTCKRPADYKB51QRBHK":3,"skill-same:01M6QAJCTTCKRPADYKB51QRBHK":76},{"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":43,"linkOnly":44,"markdownContent":45,"markdownBody":46,"frontMatter":47,"refName":53,"commitSha":54,"skillDirectory":55,"forksCount":14,"repositoryHtmlUrl":56,"repositoryHomepageUrl":57,"ownerHtmlUrl":58,"ownerBlogUrl":59,"ownerDescription":60,"updatedAt":61,"install":62,"resources":75},"01M6QAJCTTCKRPADYKB51QRBHK","agenthub",null,"Multi-agent collaboration plugin that spawns N parallel subagents competing on the same task via git worktree isolation. Agents work independently, results are evaluated by metric or LLM judge, and the best branch is merged. Use when: user wants multiple approaches tried in parallel — code optimization, content variation, research exploration, or any task that benefits from parallel competition. Requires: a git repo.","Tashima-Tarsh\u002FDisha6.6","Tashima-Tarsh","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F269906498?v=4","01M6PBH98X03XERH0HFT4PFB1P","NITISH KUMAR","01M6PBH9DA0M6KM3Z12P848F0K",0,"MIT","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fagenthub\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[5,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42],"git worktree isolation","code","metric","worktree isolation","benefits","judge","isolation","competition","exploration","subagents","repo","branch","work","parallel","multi-agent","git worktree","llm judge","worktree","git","2026-11-10 10:12:30",false,"---\nname: \"agenthub\"\ndescription: \"Multi-agent collaboration plugin that spawns N parallel subagents competing on the same task via git worktree isolation. Agents work independently, results are evaluated by metric or LLM judge, and the best branch is merged. Use when: user wants multiple approaches tried in parallel — code optimization, content variation, research exploration, or any task that benefits from parallel competition. Requires: a git repo.\"\nlicense: MIT\nmetadata:\n  version: 2.1.2\n  author: Alireza Rezvani\n  category: engineering\n  updated: 2026-03-17\n---\n\n# AgentHub — Multi-Agent Collaboration\n\nSpawn N parallel AI agents that compete on the same task. Each agent works in an isolated git worktree. The coordinator evaluates results and merges the winner.\n\n## Slash Commands\n\n| Command | Description |\n|---------|-------------|\n| `\u002Fhub:hub-init` | Create a new collaboration session — task, agent count, eval criteria |\n| `\u002Fhub:spawn` | Launch N parallel subagents in isolated worktrees |\n| `\u002Fhub:hub-status` | Show DAG state, agent progress, branch status |\n| `\u002Fhub:eval` | Rank agent results by metric or LLM judge |\n| `\u002Fhub:merge` | Merge winning branch, archive losers |\n| `\u002Fhub:board` | Read\u002Fwrite the agent message board |\n| `\u002Fhub:run` | One-shot lifecycle: init → baseline → spawn → eval → merge |\n\n## Agent Templates\n\nWhen spawning with `--template`, agents follow a predefined iteration pattern:\n\n| Template | Pattern | Use Case |\n|----------|---------|----------|\n| `optimizer` | Edit → eval → keep\u002Fdiscard → repeat x10 | Performance, latency, size |\n| `refactorer` | Restructure → test → iterate until green | Code quality, tech debt |\n| `test-writer` | Write tests → measure coverage → repeat | Test coverage gaps |\n| `bug-fixer` | Reproduce → diagnose → fix → verify | Bug fix approaches |\n\nTemplates are defined in `references\u002Fagent-templates.md`.\n\n## When This Skill Activates\n\nTrigger phrases:\n- \"try multiple approaches\"\n- \"have agents compete\"\n- \"parallel optimization\"\n- \"spawn N agents\"\n- \"compare different solutions\"\n- \"fan-out\" or \"tournament\"\n- \"generate content variations\"\n- \"compare different drafts\"\n- \"A\u002FB test copy\"\n- \"explore multiple strategies\"\n\n## Coordinator Protocol\n\nThe main Claude Code session is the coordinator. It follows this lifecycle:\n\n```\nINIT → DISPATCH → MONITOR → EVALUATE → MERGE\n```\n\n### 1. Init\n\nRun `\u002Fhub:hub-init` to create a session. This generates:\n- `.agenthub\u002Fsessions\u002F{session-id}\u002Fconfig.yaml` — task config\n- `.agenthub\u002Fsessions\u002F{session-id}\u002Fstate.json` — state machine\n- `.agenthub\u002Fboard\u002F` — message board channels\n\n### 2. Dispatch\n\nRun `\u002Fhub:spawn` to launch agents. For each agent 1..N:\n- Post task assignment to `.agenthub\u002Fboard\u002Fdispatch\u002F`\n- Spawn via Agent tool with `isolation: \"worktree\"`\n- All agents launched in a single message (parallel)\n\n### 3. Monitor\n\nRun `\u002Fhub:hub-status` to check progress:\n- `dag_analyzer.py --status --session {id}` shows branch state\n- Board `progress\u002F` channel has agent updates\n\n### 4. Evaluate\n\nRun `\u002Fhub:eval` to rank results:\n- **Metric mode**: run eval command in each worktree, parse numeric result\n- **Judge mode**: read diffs, coordinator ranks by quality\n- **Hybrid**: metric first, LLM-judge for ties\n\n### 5. Merge\n\nRun `\u002Fhub:merge` to finalize:\n- `git merge --no-ff` winner into base branch\n- Tag losers: `git tag hub\u002Farchive\u002F{session}\u002Fagent-{i}`\n- Clean up worktrees\n- Post merge summary to board\n\n## Agent Protocol\n\nEach subagent receives this prompt pattern:\n\n```\nYou are agent-{i} in hub session {session-id}.\nYour task: {task description}\n\nInstructions:\n1. Read your assignment at .agenthub\u002Fboard\u002Fdispatch\u002F{seq}-agent-{i}.md\n2. Work in your worktree — make changes, run tests, iterate\n3. Commit all changes with descriptive messages\n4. Write your result summary to .agenthub\u002Fboard\u002Fresults\u002Fagent-{i}-result.md\n5. Exit when done\n```\n\nAgents do NOT see each other's work. They do NOT communicate with each other. They only write to the board for the coordinator to read.\n\n## DAG Model\n\n### Branch Naming\n\n```\nhub\u002F{session-id}\u002Fagent-{N}\u002Fattempt-{M}\n```\n\n- Session ID: timestamp-based (`YYYYMMDD-HHMMSS`)\n- Agent N: sequential (1 to agent-count)\n- Attempt M: increments on retry (usually 1)\n\n### Frontier Detection\n\nFrontier = branch tips with no child branches. Equivalent to AgentHub's \"leaves\" query.\n\n```bash\npython scripts\u002Fdag_analyzer.py --frontier --session {id}\n```\n\n### Immutability\n\nThe DAG is append-only:\n- Never rebase or force-push agent branches\n- Never delete commits (only branch refs after archival)\n- Every approach preserved via git tags\n\n## Message Board\n\nLocation: `.agenthub\u002Fboard\u002F`\n\n### Channels\n\n| Channel | Writer | Reader | Purpose |\n|---------|--------|--------|---------|\n| `dispatch\u002F` | Coordinator | Agents | Task assignments |\n| `progress\u002F` | Agents | Coordinator | Status updates |\n| `results\u002F` | Agents + Coordinator | All | Final results + merge summary |\n\n### Post Format\n\n```markdown\n---\nauthor: agent-1\ntimestamp: 2026-03-17T14:30:22Z\nchannel: results\nparent: null\n---\n\n## Result Summary\n\n- **Approach**: Replaced O(n²) sort with hash map\n- **Files changed**: 3\n- **Metric**: 142ms (baseline: 180ms, delta: -38ms)\n- **Confidence**: High — all tests pass\n```\n\n### Board Rules\n\n- Append-only: never edit or delete posts\n- Unique filenames: `{seq:03d}-{author}-{timestamp}.md`\n- YAML frontmatter required on all posts\n\n## Evaluation Modes\n\n### Metric-Based\n\nBest for: benchmarks, test pass rates, file sizes, response times.\n\n```bash\npython scripts\u002Fresult_ranker.py --session {id} \\\n  --eval-cmd \"pytest bench.py --json\" \\\n  --metric p50_ms --direction lower\n```\n\nThe ranker runs the eval command in each agent's worktree directory and parses the metric from stdout.\n\n### LLM Judge\n\nBest for: code quality, readability, architecture decisions.\n\nThe coordinator reads each agent's diff (`git diff base...agent-branch`) and ranks by:\n1. Correctness (does it solve the task?)\n2. Simplicity (fewer lines changed preferred)\n3. Quality (clean execution, good structure)\n\n### Hybrid\n\nRun metric first. If top agents are within 10% of each other, use LLM judge to break ties.\n\n## Session Lifecycle\n\n```\ninit → running → evaluating → merged\n                            → archived (if no winner)\n```\n\nState transitions managed by `session_manager.py`:\n\n| From | To | Trigger |\n|------|----|---------|\n| `init` | `running` | `\u002Fhub:spawn` completes |\n| `running` | `evaluating` | All agents return |\n| `evaluating` | `merged` | `\u002Fhub:merge` completes |\n| `evaluating` | `archived` | No winner \u002F all failed |\n\n## Proactive Triggers\n\nThe coordinator should act when:\n\n| Signal | Action |\n|--------|--------|\n| All agents crashed | Post failure summary, suggest retry with different constraints |\n| No improvement over baseline | Archive session, suggest different approaches |\n| Orphan worktrees detected | Run `session_manager.py --cleanup {id}` |\n| Session stuck in `running` | Check board for progress, consider timeout |\n\n## Installation\n\n```bash\n# Copy to your Claude Code skills directory\ncp -r engineering\u002Fagenthub ~\u002F.claude\u002Fskills\u002Fagenthub\n\n# Or install via ClawHub\nclawhub install agenthub\n```\n\n## Scripts\n\n| Script | Purpose |\n|--------|---------|\n| `hub_init.py` | Initialize `.agenthub\u002F` structure and session |\n| `dag_analyzer.py` | Frontier detection, DAG graph, branch status |\n| `board_manager.py` | Message board CRUD (channels, posts, threads) |\n| `result_ranker.py` | Rank agents by metric or diff quality |\n| `session_manager.py` | Session state machine and cleanup |\n\n## Related Skills\n\n- **autoresearch-agent** — Single-agent optimization loop (use AgentHub when you want N agents competing)\n- **self-improving-agent** — Self-modifying agent (use AgentHub when you want external competition)\n- **git-worktree-manager** — Git worktree utilities (AgentHub uses worktrees internally)\n","# AgentHub — Multi-Agent Collaboration\n\nSpawn N parallel AI agents that compete on the same task. Each agent works in an isolated git worktree. The coordinator evaluates results and merges the winner.\n\n## Slash Commands\n\n| Command | Description |\n|---------|-------------|\n| `\u002Fhub:hub-init` | Create a new collaboration session — task, agent count, eval criteria |\n| `\u002Fhub:spawn` | Launch N parallel subagents in isolated worktrees |\n| `\u002Fhub:hub-status` | Show DAG state, agent progress, branch status |\n| `\u002Fhub:eval` | Rank agent results by metric or LLM judge |\n| `\u002Fhub:merge` | Merge winning branch, archive losers |\n| `\u002Fhub:board` | Read\u002Fwrite the agent message board |\n| `\u002Fhub:run` | One-shot lifecycle: init → baseline → spawn → eval → merge |\n\n## Agent Templates\n\nWhen spawning with `--template`, agents follow a predefined iteration pattern:\n\n| Template | Pattern | Use Case |\n|----------|---------|----------|\n| `optimizer` | Edit → eval → keep\u002Fdiscard → repeat x10 | Performance, latency, size |\n| `refactorer` | Restructure → test → iterate until green | Code quality, tech debt |\n| `test-writer` | Write tests → measure coverage → repeat | Test coverage gaps |\n| `bug-fixer` | Reproduce → diagnose → fix → verify | Bug fix approaches |\n\nTemplates are defined in `references\u002Fagent-templates.md`.\n\n## When This Skill Activates\n\nTrigger phrases:\n- \"try multiple approaches\"\n- \"have agents compete\"\n- \"parallel optimization\"\n- \"spawn N agents\"\n- \"compare different solutions\"\n- \"fan-out\" or \"tournament\"\n- \"generate content variations\"\n- \"compare different drafts\"\n- \"A\u002FB test copy\"\n- \"explore multiple strategies\"\n\n## Coordinator Protocol\n\nThe main Claude Code session is the coordinator. It follows this lifecycle:\n\n```\nINIT → DISPATCH → MONITOR → EVALUATE → MERGE\n```\n\n### 1. Init\n\nRun `\u002Fhub:hub-init` to create a session. This generates:\n- `.agenthub\u002Fsessions\u002F{session-id}\u002Fconfig.yaml` — task config\n- `.agenthub\u002Fsessions\u002F{session-id}\u002Fstate.json` — state machine\n- `.agenthub\u002Fboard\u002F` — message board channels\n\n### 2. Dispatch\n\nRun `\u002Fhub:spawn` to launch agents. For each agent 1..N:\n- Post task assignment to `.agenthub\u002Fboard\u002Fdispatch\u002F`\n- Spawn via Agent tool with `isolation: \"worktree\"`\n- All agents launched in a single message (parallel)\n\n### 3. Monitor\n\nRun `\u002Fhub:hub-status` to check progress:\n- `dag_analyzer.py --status --session {id}` shows branch state\n- Board `progress\u002F` channel has agent updates\n\n### 4. Evaluate\n\nRun `\u002Fhub:eval` to rank results:\n- **Metric mode**: run eval command in each worktree, parse numeric result\n- **Judge mode**: read diffs, coordinator ranks by quality\n- **Hybrid**: metric first, LLM-judge for ties\n\n### 5. Merge\n\nRun `\u002Fhub:merge` to finalize:\n- `git merge --no-ff` winner into base branch\n- Tag losers: `git tag hub\u002Farchive\u002F{session}\u002Fagent-{i}`\n- Clean up worktrees\n- Post merge summary to board\n\n## Agent Protocol\n\nEach subagent receives this prompt pattern:\n\n```\nYou are agent-{i} in hub session {session-id}.\nYour task: {task description}\n\nInstructions:\n1. Read your assignment at .agenthub\u002Fboard\u002Fdispatch\u002F{seq}-agent-{i}.md\n2. Work in your worktree — make changes, run tests, iterate\n3. Commit all changes with descriptive messages\n4. Write your result summary to .agenthub\u002Fboard\u002Fresults\u002Fagent-{i}-result.md\n5. Exit when done\n```\n\nAgents do NOT see each other's work. They do NOT communicate with each other. They only write to the board for the coordinator to read.\n\n## DAG Model\n\n### Branch Naming\n\n```\nhub\u002F{session-id}\u002Fagent-{N}\u002Fattempt-{M}\n```\n\n- Session ID: timestamp-based (`YYYYMMDD-HHMMSS`)\n- Agent N: sequential (1 to agent-count)\n- Attempt M: increments on retry (usually 1)\n\n### Frontier Detection\n\nFrontier = branch tips with no child branches. Equivalent to AgentHub's \"leaves\" query.\n\n```bash\npython scripts\u002Fdag_analyzer.py --frontier --session {id}\n```\n\n### Immutability\n\nThe DAG is append-only:\n- Never rebase or force-push agent branches\n- Never delete commits (only branch refs after archival)\n- Every approach preserved via git tags\n\n## Message Board\n\nLocation: `.agenthub\u002Fboard\u002F`\n\n### Channels\n\n| Channel | Writer | Reader | Purpose |\n|---------|--------|--------|---------|\n| `dispatch\u002F` | Coordinator | Agents | Task assignments |\n| `progress\u002F` | Agents | Coordinator | Status updates |\n| `results\u002F` | Agents + Coordinator | All | Final results + merge summary |\n\n### Post Format\n\n```markdown\n---\nauthor: agent-1\ntimestamp: 2026-03-17T14:30:22Z\nchannel: results\nparent: null\n---\n\n## Result Summary\n\n- **Approach**: Replaced O(n²) sort with hash map\n- **Files changed**: 3\n- **Metric**: 142ms (baseline: 180ms, delta: -38ms)\n- **Confidence**: High — all tests pass\n```\n\n### Board Rules\n\n- Append-only: never edit or delete posts\n- Unique filenames: `{seq:03d}-{author}-{timestamp}.md`\n- YAML frontmatter required on all posts\n\n## Evaluation Modes\n\n### Metric-Based\n\nBest for: benchmarks, test pass rates, file sizes, response times.\n\n```bash\npython scripts\u002Fresult_ranker.py --session {id} \\\n  --eval-cmd \"pytest bench.py --json\" \\\n  --metric p50_ms --direction lower\n```\n\nThe ranker runs the eval command in each agent's worktree directory and parses the metric from stdout.\n\n### LLM Judge\n\nBest for: code quality, readability, architecture decisions.\n\nThe coordinator reads each agent's diff (`git diff base...agent-branch`) and ranks by:\n1. Correctness (does it solve the task?)\n2. Simplicity (fewer lines changed preferred)\n3. Quality (clean execution, good structure)\n\n### Hybrid\n\nRun metric first. If top agents are within 10% of each other, use LLM judge to break ties.\n\n## Session Lifecycle\n\n```\ninit → running → evaluating → merged\n                            → archived (if no winner)\n```\n\nState transitions managed by `session_manager.py`:\n\n| From | To | Trigger |\n|------|----|---------|\n| `init` | `running` | `\u002Fhub:spawn` completes |\n| `running` | `evaluating` | All agents return |\n| `evaluating` | `merged` | `\u002Fhub:merge` completes |\n| `evaluating` | `archived` | No winner \u002F all failed |\n\n## Proactive Triggers\n\nThe coordinator should act when:\n\n| Signal | Action |\n|--------|--------|\n| All agents crashed | Post failure summary, suggest retry with different constraints |\n| No improvement over baseline | Archive session, suggest different approaches |\n| Orphan worktrees detected | Run `session_manager.py --cleanup {id}` |\n| Session stuck in `running` | Check board for progress, consider timeout |\n\n## Installation\n\n```bash\n# Copy to your Claude Code skills directory\ncp -r engineering\u002Fagenthub ~\u002F.claude\u002Fskills\u002Fagenthub\n\n# Or install via ClawHub\nclawhub install agenthub\n```\n\n## Scripts\n\n| Script | Purpose |\n|--------|---------|\n| `hub_init.py` | Initialize `.agenthub\u002F` structure and session |\n| `dag_analyzer.py` | Frontier detection, DAG graph, branch status |\n| `board_manager.py` | Message board CRUD (channels, posts, threads) |\n| `result_ranker.py` | Rank agents by metric or diff quality |\n| `session_manager.py` | Session state machine and cleanup |\n\n## Related Skills\n\n- **autoresearch-agent** — Single-agent optimization loop (use AgentHub when you want N agents competing)\n- **self-improving-agent** — Self-modifying agent (use AgentHub when you want external competition)\n- **git-worktree-manager** — Git worktree utilities (AgentHub uses worktrees internally)\n",{"name":5,"license":15,"metadata":48,"description":7},{"author":49,"updated":50,"version":51,"category":52},"Alireza Rezvani",1773705600000,"2.1.2","engineering","main","0da4485785ee599388900be50db1635489d53056",".agents\u002Fskills\u002Fagenthub","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6","https:\u002F\u002Fdisha6.6.thenitishkr.in\u002F","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh","www.thenitishkr","thenitishkr | AI • Cyber-security • Research\r\n","2026-11-08 03:33:25",{"source":8,"skillName":5,"commands":63,"prompt":73,"zipAvailable":74},[64,67,70],{"tool":65,"command":66},"npx","npx skills add Tashima-Tarsh\u002FDisha6.6 --skill agenthub",{"tool":68,"command":69},"bunx","bunx skills add Tashima-Tarsh\u002FDisha6.6 --skill agenthub",{"tool":71,"command":72},"pnpm","pnpm dlx skills add Tashima-Tarsh\u002FDisha6.6 --skill agenthub","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fagenthub\u002FSKILL.md",true,[],[77,107,131,156,181,202],{"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":86,"publishedAt":43},"01M6QRD07D4TGNDK6VJ4EHF8BV","youtube-full","Use when the user needs YouTube transcripts, video search, channel browsing, playlist extraction, or content monitoring. Trigger phrases: 'get the transcript for', 'search YouTube for', 'what are the latest videos on', 'list this playlist', 'monitor this channel', or any request involving a YouTube URL, video ID, or @handle. Do NOT use for downloading video or audio files, YouTube engagement data (likes, comments), or private\u002Fage-restricted videos.","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fyoutube-full\u002FSKILL.md",[83],{"categoryNo":84,"categoryName":85,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000016","图像与多媒体",[87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106],"youtube full","youtube","full","transcript","search","monitoring","data","Video","Audio","list","files","do","get","age","trigger","URL","for","browsing","request","youtube transcripts",{"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":113,"publishedAt":43},"01M6QRCJ3112VYPA97YG7KGMC2","x-twitter-growth","X\u002FTwitter growth engine for building audience, crafting viral content, and analyzing engagement. Use when the user wants to grow on X\u002FTwitter, write tweets or threads, analyze their X profile, research competitors on X, plan a posting strategy, or optimize engagement. Complements social-content (generic multi-platform) with X-specific depth: algorithm mechanics, thread engineering, reply strategy, profile optimization, and competitive intelligence via web search.","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fx-twitter-growth\u002FSKILL.md",[],[114,115,116,117,91,118,52,119,120,121,122,123,124,125,126,127,128,129,130,103],"twitter","x twitter growth","growth","research","content","plan","web search","competitors","analyze","engine","write","strategy","use","platform","grow","posting","competitive",{"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":138,"publishedAt":43},"01M6QRBN3EHQNJY42RERP7A149","write-a-skill","Create new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, build, or author a new skill.","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fwrite-a-skill\u002FSKILL.md",[137],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[139,124,140,141,142,143,144,145,126,146,147,53,148,149,150,151,152,153,154,155],"write a skill","github","create","https","productivity","matt pocock","direct","example","build","new skill","structure","new agent","resources","with","tree","progressive disclosure","author",{"skillNo":157,"name":158,"nameZh":6,"description":159,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":160,"categories":161,"keywords":162,"publishedAt":43},"01M6QRB6G8P33PNGAF9Y69EJ9T","wrap-up","Close out a launched Claude Managed Agent — recap every primitive the founder now owns, regenerate the single-file overview page, and suggest the next 1-2 upgrades. Use when the user says \"wrap up\", \"close this out\", \"what do I own now\", \"give me the summary\", \"recap the agent\", or when the orchestrator routes phase=wrap-up. primitives_inventory.py tables everything owned (agent, environment, session, memory, outcome, deployment); overview_page.py regenerates a self-contained .\u002Fmy-agent\u002Fagent-overview.html; upgrade_suggester.py ranks the next moves from recorded deferrals plus standing hardening steps. Companion to run-without-you; the last stop before phase=done.","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fwrap-up\u002FSKILL.md",[],[163,164,165,166,167,168,169,170,171,126,172,98,173,174,175,176,177,178,179,180],"wrap up","up","wrap","gemini","deployment","run","file","hardening","closeout","stop","upgrade","founder","close","companion","you","tables","directions","phase",{"skillNo":182,"name":183,"nameZh":6,"description":184,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":185,"categories":186,"keywords":188,"publishedAt":43},"01M6QRA5AYC1RBFZ39GTWGS3N8","workflow-builder","Design and write deterministic multi-agent workflow scripts (.js files in .claude\u002Fworkflows\u002F) for Claude Code's Workflow tool. Use when a user wants to build, create, author, scaffold, or run a custom Claude Code workflow, orchestrate sub-agents (fan-out, pipeline, loop, judge-panel), or automate a repeatable multi-step task across fresh-context agents.","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fworkflow-builder\u002FSKILL.md",[187],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[189,190,191,192,193,141,168,25,194,195,196,38,124,197,97,198,199,200,29,201],"workflow","workflow builder","builder","design","workflows","orchestrate","pipeline","loop","context","across","fresh","scripts","claude code workflow",{"skillNo":203,"name":204,"nameZh":6,"description":205,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":206,"categories":207,"keywords":208,"publishedAt":43},"01M6QR7QMCZESKQA0ERW1E657M","weekly-review","Use when someone wants to run a weekly review, close open loops, audit stalled projects and commitments, get their system back to trusted, restart a lapsed review habit, or says \"\u002Fcs:weekly-review\". Walks David Allen's three-phase loop — GET CLEAR, GET CURRENT, GET CREATIVE — with deterministic scripts that inventory open loops, gate the checklist with named gaps, and score commitment health 0-100.","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fweekly-review\u002FSKILL.md",[],[209,210,211,212,213,214,215,216,217,196,218,219,220,221,222,223,99,224,225,180],"review","weekly review","weekly","deterministic scripts","reflect","feeds","inventory","open","team","projects","project-management","scanner","conversation","back","project","sprint","cadence"]