[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M75CWB262YVES2W60WTXV25H":3,"skill-same:01M75CWB262YVES2W60WTXV25H":89},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":28,"commitSha":29,"skillDirectory":30,"forksCount":13,"repositoryHtmlUrl":31,"repositoryHomepageUrl":6,"ownerHtmlUrl":32,"ownerBlogUrl":6,"ownerDescription":33,"updatedAt":34,"install":35,"resources":48},"01M75CWB262YVES2W60WTXV25H","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.","AdmiralGallade\u002Fharness-repository","AdmiralGallade","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F59243621?v=4","01M759AG0891RDPWNGJBX1Y2TG","01M759AG10MS924J53ZWJ60AEC",0,"MIT","https:\u002F\u002Fgithub.com\u002FAdmiralGallade\u002Fharness-repository\u002Fblob\u002Fmain\u002Fharnesses\u002Fclaude-skills\u002Fengineering\u002Fagenthub\u002Fskills\u002Fagenthub\u002FSKILL.md",[],[],"2026-11-12 13:55:43",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:init` | Create a new collaboration session — task, agent count, eval criteria |\n| `\u002Fhub:spawn` | Launch N parallel subagents in isolated worktrees |\n| `\u002Fhub: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: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: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:init` | Create a new collaboration session — task, agent count, eval criteria |\n| `\u002Fhub:spawn` | Launch N parallel subagents in isolated worktrees |\n| `\u002Fhub: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: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: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":14,"metadata":23,"description":7},{"author":24,"updated":25,"version":26,"category":27},"Alireza Rezvani",1773705600000,"2.1.2","engineering","main","f3af6b6781621109871cca9e2989364afc509f3d","harnesses\u002Fclaude-skills\u002Fengineering\u002Fagenthub\u002Fskills\u002Fagenthub","https:\u002F\u002Fgithub.com\u002FAdmiralGallade\u002Fharness-repository","https:\u002F\u002Fgithub.com\u002FAdmiralGallade","Eager to learn!\r\nI'll do anything for more knowledge anywhere.","2026-06-06 07:34:31",{"source":8,"skillName":5,"commands":36,"prompt":46,"zipAvailable":47},[37,40,43],{"tool":38,"command":39},"npx","npx skills add AdmiralGallade\u002Fharness-repository --skill agenthub",{"tool":41,"command":42},"bunx","bunx skills add AdmiralGallade\u002Fharness-repository --skill agenthub",{"tool":44,"command":45},"pnpm","pnpm dlx skills add AdmiralGallade\u002Fharness-repository --skill agenthub","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FAdmiralGallade\u002Fharness-repository\u002Fblob\u002Fmain\u002Fharnesses\u002Fclaude-skills\u002Fengineering\u002Fagenthub\u002Fskills\u002Fagenthub\u002FSKILL.md",true,[49,55,59,63,69,73,77,81,85],{"path":50,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":53,"sourceHtmlUrl":54},"references\u002Fagent-templates.md","REFERENCE","参考文档",7795,"https:\u002F\u002Fgithub.com\u002FAdmiralGallade\u002Fharness-repository\u002Fblob\u002Fmain\u002Fharnesses\u002Fclaude-skills\u002Fengineering\u002Fagenthub\u002Fskills\u002Fagenthub\u002Freferences\u002Fagent-templates.md",{"path":56,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":57,"sourceHtmlUrl":58},"references\u002Fcoordination-strategies.md",5946,"https:\u002F\u002Fgithub.com\u002FAdmiralGallade\u002Fharness-repository\u002Fblob\u002Fmain\u002Fharnesses\u002Fclaude-skills\u002Fengineering\u002Fagenthub\u002Fskills\u002Fagenthub\u002Freferences\u002Fcoordination-strategies.md",{"path":60,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":61,"sourceHtmlUrl":62},"references\u002Fdag-patterns.md",4091,"https:\u002F\u002Fgithub.com\u002FAdmiralGallade\u002Fharness-repository\u002Fblob\u002Fmain\u002Fharnesses\u002Fclaude-skills\u002Fengineering\u002Fagenthub\u002Fskills\u002Fagenthub\u002Freferences\u002Fdag-patterns.md",{"path":64,"resourceType":65,"resourceTypeDesc":66,"sizeBytes":67,"sourceHtmlUrl":68},"scripts\u002Fboard_manager.py","SCRIPT","脚本",8562,"https:\u002F\u002Fgithub.com\u002FAdmiralGallade\u002Fharness-repository\u002Fblob\u002Fmain\u002Fharnesses\u002Fclaude-skills\u002Fengineering\u002Fagenthub\u002Fskills\u002Fagenthub\u002Fscripts\u002Fboard_manager.py",{"path":70,"resourceType":65,"resourceTypeDesc":66,"sizeBytes":71,"sourceHtmlUrl":72},"scripts\u002Fdag_analyzer.py",8942,"https:\u002F\u002Fgithub.com\u002FAdmiralGallade\u002Fharness-repository\u002Fblob\u002Fmain\u002Fharnesses\u002Fclaude-skills\u002Fengineering\u002Fagenthub\u002Fskills\u002Fagenthub\u002Fscripts\u002Fdag_analyzer.py",{"path":74,"resourceType":65,"resourceTypeDesc":66,"sizeBytes":75,"sourceHtmlUrl":76},"scripts\u002Fdry_run.py",11415,"https:\u002F\u002Fgithub.com\u002FAdmiralGallade\u002Fharness-repository\u002Fblob\u002Fmain\u002Fharnesses\u002Fclaude-skills\u002Fengineering\u002Fagenthub\u002Fskills\u002Fagenthub\u002Fscripts\u002Fdry_run.py",{"path":78,"resourceType":65,"resourceTypeDesc":66,"sizeBytes":79,"sourceHtmlUrl":80},"scripts\u002Fhub_init.py",8528,"https:\u002F\u002Fgithub.com\u002FAdmiralGallade\u002Fharness-repository\u002Fblob\u002Fmain\u002Fharnesses\u002Fclaude-skills\u002Fengineering\u002Fagenthub\u002Fskills\u002Fagenthub\u002Fscripts\u002Fhub_init.py",{"path":82,"resourceType":65,"resourceTypeDesc":66,"sizeBytes":83,"sourceHtmlUrl":84},"scripts\u002Fresult_ranker.py",10557,"https:\u002F\u002Fgithub.com\u002FAdmiralGallade\u002Fharness-repository\u002Fblob\u002Fmain\u002Fharnesses\u002Fclaude-skills\u002Fengineering\u002Fagenthub\u002Fskills\u002Fagenthub\u002Fscripts\u002Fresult_ranker.py",{"path":86,"resourceType":65,"resourceTypeDesc":66,"sizeBytes":87,"sourceHtmlUrl":88},"scripts\u002Fsession_manager.py",9991,"https:\u002F\u002Fgithub.com\u002FAdmiralGallade\u002Fharness-repository\u002Fblob\u002Fmain\u002Fharnesses\u002Fclaude-skills\u002Fengineering\u002Fagenthub\u002Fskills\u002Fagenthub\u002Fscripts\u002Fsession_manager.py",[90,98,105,112,119,126],{"skillNo":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":94,"licenseFileUrl":6,"sourceHtmlUrl":95,"categories":96,"keywords":97,"publishedAt":18},"01M75JSM6WGJ71BTHM6VC8CJ1X","verify-sign","Add an Artifact Verification (SscaArtifactVerification) step to an existing Harness pipeline to verify Cosign signatures on container or local-stage artifacts. Supports CI, Security, and CD Deploy (containerized step group). Supports Third-Party registries (Docker, ECR, GCR, GAR, ACR), Harness Artifact Registry (HAR), and Harness Local Stage artifacts. Only works with existing pipelines. Use when asked to verify signed artifacts, verify artifact signature, verify-sign, validate Cosign signature, or configure SscaArtifactVerification. Trigger phrases: verify sign, verify artifact, artifact verification, verify signature, verify-sign, SscaArtifactVerification, verify signed image, verify Cosign, HAR verification.","Apache-2.0","https:\u002F\u002Fgithub.com\u002FAdmiralGallade\u002Fharness-repository\u002Fblob\u002Fmain\u002Fharnesses\u002Fharness-skills\u002Fskills\u002Fverify-sign\u002FSKILL.md",[],[],{"skillNo":99,"name":100,"nameZh":6,"description":101,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":94,"licenseFileUrl":6,"sourceHtmlUrl":102,"categories":103,"keywords":104,"publishedAt":18},"01M75JSDSTP77TFM3JFGBB8QKP","template-usage","Track Harness template dependencies, usage, and adoption via MCP v2 tools. Find which pipelines or other templates reference a given template, analyze update impact, identify unused templates, and compare version adoption. Use when asked about template usage, template references, template dependencies, impact analysis before updating a template, finding unused templates, or tracking template adoption across projects. Trigger phrases: template usage, who uses template, template references, template dependencies, template impact, unused templates, template adoption. Do NOT use for creating or updating templates (use create-template instead).","https:\u002F\u002Fgithub.com\u002FAdmiralGallade\u002Fharness-repository\u002Fblob\u002Fmain\u002Fharnesses\u002Fharness-skills\u002Fskills\u002Ftemplate-usage\u002FSKILL.md",[],[],{"skillNo":106,"name":107,"nameZh":6,"description":108,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":94,"licenseFileUrl":6,"sourceHtmlUrl":109,"categories":110,"keywords":111,"publishedAt":18},"01M75JS76Q2KC8PD598H2DZZRA","sign-artifact","Add an Artifact Signing (SscaArtifactSigning) step to an existing Harness pipeline to Cosign-sign container or local-stage artifacts with keyless, key-based, or Vault signing. Supports Third-Party registries (Docker, ECR, GCR, GAR, ACR), Harness Artifact Registry (HAR), and Harness Local Stage artifacts. Place after image build\u002Fpush; optionally upload .sig to the registry. Only works with existing pipelines. Use when asked to sign artifacts, add artifact signing, Cosign sign image, attach signature to registry, or configure SscaArtifactSigning. Trigger phrases: sign artifact, artifact signing, sign image, Cosign sign, add signing step, SscaArtifactSigning, attach signature, sign container image, HAR signing.","https:\u002F\u002Fgithub.com\u002FAdmiralGallade\u002Fharness-repository\u002Fblob\u002Fmain\u002Fharnesses\u002Fharness-skills\u002Fskills\u002Fsign-artifact\u002FSKILL.md",[],[],{"skillNo":113,"name":114,"nameZh":6,"description":115,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":94,"licenseFileUrl":6,"sourceHtmlUrl":116,"categories":117,"keywords":118,"publishedAt":18},"01M75JS16EEFFHA44EBNE8KWNT","sei-analytics","Advanced engineering analytics via Harness Software Engineering Insights (SEI) MCP. Configure sprint velocity and estimation accuracy tracking, engineering investment allocation breakdowns, sprint planning with capacity forecasts, and release readiness assessments. Use when asked about sprint analytics, investment allocation, sprint planning, capacity forecasting, or release readiness. Do NOT use for DORA metrics (use dora-metrics instead). Trigger phrases: sprint velocity, sprint analytics, investment allocation, capacity planning, sprint forecast, release readiness, engineering productivity, estimation accuracy, sprint planning, scope creep, code quality trends.","https:\u002F\u002Fgithub.com\u002FAdmiralGallade\u002Fharness-repository\u002Fblob\u002Fmain\u002Fharnesses\u002Fharness-skills\u002Fskills\u002Fsei-analytics\u002FSKILL.md",[],[],{"skillNo":120,"name":121,"nameZh":6,"description":122,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":94,"licenseFileUrl":6,"sourceHtmlUrl":123,"categories":124,"keywords":125,"publishedAt":18},"01M75JRWE3X3E7V9JFQ4ENZYZM","security-report","Generate security compliance reports using Harness SCS and STO via MCP. Analyze vulnerabilities, SBOMs, and manage exemptions. Use when user says \"security report\", \"vulnerabilities\", \"SBOM\", \"security scan\", \"compliance check\", or asks about application security.","https:\u002F\u002Fgithub.com\u002FAdmiralGallade\u002Fharness-repository\u002Fblob\u002Fmain\u002Fharnesses\u002Fharness-skills\u002Fskills\u002Fsecurity-report\u002FSKILL.md",[],[],{"skillNo":127,"name":128,"nameZh":6,"description":129,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":94,"licenseFileUrl":6,"sourceHtmlUrl":130,"categories":131,"keywords":132,"publishedAt":18},"01M75JRSFJSNZFZRFKX8MSPCS2","scorecard-review","Review service maturity scorecards and compliance using Harness IDP via MCP. Check production readiness, security, and documentation scores. Use when user says \"scorecard\", \"service maturity\", \"production readiness\", \"compliance score\", or asks about service health scores.","https:\u002F\u002Fgithub.com\u002FAdmiralGallade\u002Fharness-repository\u002Fblob\u002Fmain\u002Fharnesses\u002Fharness-skills\u002Fskills\u002Fscorecard-review\u002FSKILL.md",[],[]]