[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6FZWXJ2PPHSWNBFZ423G3C7":3,"skill-same:01M6FZWXJ2PPHSWNBFZ423G3C7":64},{"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":31,"linkOnly":32,"markdownContent":33,"markdownBody":34,"frontMatter":35,"refName":37,"commitSha":38,"skillDirectory":39,"forksCount":40,"repositoryHtmlUrl":41,"repositoryHomepageUrl":6,"ownerHtmlUrl":42,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":43,"install":44,"resources":57},"01M6FZWXJ2PPHSWNBFZ423G3C7","ralph-operations",null,"Use when managing Ralph orchestration loops, analyzing diagnostic data, debugging hat selection, investigating backpressure, or performing post-mortem analysis","kbarbel640-del\u002Fskills","kbarbel640-del","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F255315490?v=4","01M6CJPPQGCCESXMG3K7BBGQ5J","01M6CJPPX2PB2BCZERFVM2C2B3",1,"MIT","https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fpaulpete\u002Fralph-operations\u002FSKILL.md",[],[18,19,20,21,22,23,24,25,26,27,28,29,30],"ralph","operations","ralph operations","orchestration","diagnostics","debugging","analyzing","data","analysis","use","selection","post","loops","2026-11-10 10:12:30",false,"---\nname: ralph-operations\ndescription: Use when managing Ralph orchestration loops, analyzing diagnostic data, debugging hat selection, investigating backpressure, or performing post-mortem analysis\ntags: [loops, diagnostics, debugging, analysis]\n---\n\n# Ralph Operations\n\nManage, monitor, and diagnose Ralph orchestration loops.\n\n## Loop Management\n\n### Quick Reference\n\n| Task | Command |\n|------|---------|\n| List active loops | `ralph loops` |\n| List all (including merged) | `ralph loops --all` |\n| View loop changes | `ralph loops diff \u003Cid>` |\n| View loop logs | `ralph loops logs \u003Cid>` |\n| Follow logs live | `ralph loops logs \u003Cid> -f` |\n| Stop running loop | `ralph loops stop \u003Cid>` |\n| Merge completed loop | `ralph loops merge \u003Cid>` |\n| Retry failed merge | `ralph loops retry \u003Cid>` |\n| Abandon loop | `ralph loops discard \u003Cid>` |\n| Clean stale processes | `ralph loops prune` |\n\n**Loop ID format:** Partial matching works - `a3f2` matches `loop-20250124-143052-a3f2`\n\n### Loop Status\n\n| Status | Color | Meaning |\n|--------|-------|---------|\n| running | green | Loop is actively executing |\n| queued | blue | Completed, waiting for merge |\n| merging | yellow | Merge in progress |\n| needs-review | red | Merge failed, requires intervention |\n| merged | dim | Successfully merged (with `--all`) |\n| discarded | dim | Abandoned (with `--all`) |\n\n### Starting & Stopping\n\nLoops start automatically via `ralph run`:\n- **Primary loop**: Runs in main workspace, holds `.ralph\u002Floop.lock`\n- **Worktree loop**: Created when primary is running, isolated in `.worktrees\u002F\u003Cloop-id>\u002F`\n\n```bash\nralph loops                       # Any loops running?\ncat .ralph\u002Floop.lock 2>\u002Fdev\u002Fnull  # Primary loop details\nralph loops stop \u003Cid>             # Graceful stop\nralph loops stop \u003Cid> --force     # Immediate stop\nralph loops discard \u003Cid>          # Abandon + clean worktree\n```\n\n### Inspecting Loops\n\n```bash\nralph loops diff \u003Cid>             # What changed\nralph loops logs \u003Cid> -f          # Live event log\nralph loops history \u003Cid>          # State changes\nralph loops attach \u003Cid>           # Shell into worktree\n```\n\n**Worktree context files** (`.worktrees\u002F\u003Cloop-id>\u002F`):\n\n| File | Contents |\n|------|----------|\n| `.ralph\u002Fevents.jsonl` | Event stream: hats, iterations, tool calls |\n| `.ralph\u002Fagent\u002Fsummary.md` | Current session summary |\n| `.ralph\u002Fagent\u002Fhandoff.md` | Handoff context for next iteration |\n| `.ralph\u002Fagent\u002Fscratchpad.md` | Working notes |\n| `.ralph\u002Fagent\u002Ftasks.jsonl` | Runtime task state |\n\n**Primary loop** uses the same files at `.ralph\u002Fagent\u002F` in repo root.\n\n### Merge Queue\n\nFlow: `Queued → Merging → Merged` or `→ NeedsReview → Merging (retry)` or `→ Discarded`\n\n```bash\nralph loops merge \u003Cid>            # Queue for merge\nralph loops process               # Process pending merges now\nralph loops retry \u003Cid>            # Retry failed merge\n```\n\n**Reading state:**\n```bash\njq -r '.prompt' .ralph\u002Floop.lock 2>\u002Fdev\u002Fnull\ntail -20 .ralph\u002Fmerge-queue.jsonl | jq .\n```\n\n---\n\n## Diagnostics\n\n### Enabling\n\n```bash\nRALPH_DIAGNOSTICS=1 ralph run -p \"your prompt\"\n```\n\nZero overhead when disabled. Output: `.ralph\u002Fdiagnostics\u002F\u003CYYYY-MM-DDTHH-MM-SS>\u002F`\n\n### Session Discovery\n\n```bash\nLATEST=$(ls -t .ralph\u002Fdiagnostics\u002F | head -1)\nSESSION=\".ralph\u002Fdiagnostics\u002F$LATEST\"\n```\n\n### File Reference\n\n| File | Contains | Key Fields |\n|------|----------|------------|\n| `agent-output.jsonl` | Agent text, tool calls, results | `type`, `iteration`, `hat` |\n| `orchestration.jsonl` | Hat selection, events, backpressure | `event.type`, `iteration`, `hat` |\n| `performance.jsonl` | Timing, latency, token counts | `metric.type`, `iteration`, `hat` |\n| `errors.jsonl` | Parse errors, validation failures | `error_type`, `message`, `context` |\n| `trace.jsonl` | All tracing logs with metadata | `level`, `target`, `message` |\n\n### Diagnostic Workflow\n\n**1. Errors first:**\n```bash\nwc -l \"$SESSION\u002Ferrors.jsonl\"\njq '.' \"$SESSION\u002Ferrors.jsonl\"\njq -s 'group_by(.error_type) | map({type: .[0].error_type, count: length})' \"$SESSION\u002Ferrors.jsonl\"\n```\n\n**2. Orchestration flow:**\n```bash\njq '{iter: .iteration, hat: .hat, event: .event.type}' \"$SESSION\u002Forchestration.jsonl\"\njq 'select(.event.type == \"hat_selected\") | {iter: .iteration, hat: .event.hat, reason: .event.reason}' \"$SESSION\u002Forchestration.jsonl\"\njq 'select(.event.type == \"backpressure_triggered\") | {iter: .iteration, reason: .event.reason}' \"$SESSION\u002Forchestration.jsonl\"\n```\n\n**3. Agent activity:**\n```bash\njq 'select(.type == \"tool_call\") | {iter: .iteration, tool: .name}' \"$SESSION\u002Fagent-output.jsonl\"\njq -s '[.[] | select(.type == \"tool_call\")] | group_by(.iteration) | map({iter: .[0].iteration, tools: [.[].name]})' \"$SESSION\u002Fagent-output.jsonl\"\n```\n\n**4. Performance:**\n```bash\njq 'select(.metric.type == \"iteration_duration\") | {iter: .iteration, ms: .metric.duration_ms}' \"$SESSION\u002Fperformance.jsonl\"\njq -s '[.[] | select(.metric.type == \"token_count\")] | {total_in: (map(.metric.input) | add), total_out: (map(.metric.output) | add)}' \"$SESSION\u002Fperformance.jsonl\"\n```\n\n**5. Trace logs:**\n```bash\njq 'select(.level == \"ERROR\" or .level == \"WARN\")' \"$SESSION\u002Ftrace.jsonl\"\n```\n\n### Quick Health Check\n\n```bash\nSESSION=\".ralph\u002Fdiagnostics\u002F$(ls -t .ralph\u002Fdiagnostics\u002F | head -1)\"\necho \"=== Session: $SESSION ===\"\necho -e \"\\n--- Errors ---\"\nwc -l \u003C \"$SESSION\u002Ferrors.jsonl\" 2>\u002Fdev\u002Fnull || echo \"0\"\necho -e \"\\n--- Iterations ---\"\njq -s 'map(select(.event.type == \"iteration_started\")) | length' \"$SESSION\u002Forchestration.jsonl\"\necho -e \"\\n--- Hats Used ---\"\njq -s '[.[] | select(.event.type == \"hat_selected\") | .event.hat] | unique' \"$SESSION\u002Forchestration.jsonl\"\necho -e \"\\n--- Backpressure Count ---\"\njq -s 'map(select(.event.type == \"backpressure_triggered\")) | length' \"$SESSION\u002Forchestration.jsonl\"\necho -e \"\\n--- Termination ---\"\njq 'select(.event.type == \"loop_terminated\")' \"$SESSION\u002Forchestration.jsonl\"\n```\n\n---\n\n## Troubleshooting\n\n### Stale Processes\n`ralph loops` shows loops that aren't running → `ralph loops prune`\n\n### Orphan Worktrees\n`.worktrees\u002F` has directories not in `ralph loops` → `ralph loops prune` or `git worktree remove .worktrees\u002F\u003Cid> --force`\n\n### Merge Conflicts\nLoop stuck in `needs-review`:\n1. `ralph loops diff \u003Cid>` — see conflicting changes\n2. `ralph loops attach \u003Cid>` — resolve manually, commit, retry\n3. `ralph loops discard \u003Cid>` — abandon if not worth fixing\n\n### Lock Stuck\n\"Loop already running\" but nothing is → `rm .ralph\u002Floop.lock` (safe if process is dead)\n\n### Agent Stuck in Loop\n```bash\njq -s '[.[] | select(.type == \"tool_call\")] | group_by(.name) | map({tool: .[0].name, count: length}) | sort_by(-.count)' \"$SESSION\u002Fagent-output.jsonl\"\n```\nRed flag: Many iterations with few events = agent not making progress.\n\n### Merge Stuck in \"merging\"\nProcess died mid-merge. Unblock:\n```bash\necho '{\"ts\":\"'$(date -u +%Y-%m-%dT%H:%M:%S.000000Z)'\",\"loop_id\":\"\u003Cloop-id>\",\"event\":{\"type\":\"needs_review\",\"reason\":\"Merge process died\"}}' >> .ralph\u002Fmerge-queue.jsonl\nralph loops discard \u003Cloop-id>\n```\n\n### Worktree Corruption\n```bash\ngit worktree repair\nralph loops prune\n```\n\n### Cleanup\n```bash\nralph clean --diagnostics              # Delete all sessions\nralph clean --diagnostics --dry-run    # Preview deletions\n```\n","# Ralph Operations\n\nManage, monitor, and diagnose Ralph orchestration loops.\n\n## Loop Management\n\n### Quick Reference\n\n| Task | Command |\n|------|---------|\n| List active loops | `ralph loops` |\n| List all (including merged) | `ralph loops --all` |\n| View loop changes | `ralph loops diff \u003Cid>` |\n| View loop logs | `ralph loops logs \u003Cid>` |\n| Follow logs live | `ralph loops logs \u003Cid> -f` |\n| Stop running loop | `ralph loops stop \u003Cid>` |\n| Merge completed loop | `ralph loops merge \u003Cid>` |\n| Retry failed merge | `ralph loops retry \u003Cid>` |\n| Abandon loop | `ralph loops discard \u003Cid>` |\n| Clean stale processes | `ralph loops prune` |\n\n**Loop ID format:** Partial matching works - `a3f2` matches `loop-20250124-143052-a3f2`\n\n### Loop Status\n\n| Status | Color | Meaning |\n|--------|-------|---------|\n| running | green | Loop is actively executing |\n| queued | blue | Completed, waiting for merge |\n| merging | yellow | Merge in progress |\n| needs-review | red | Merge failed, requires intervention |\n| merged | dim | Successfully merged (with `--all`) |\n| discarded | dim | Abandoned (with `--all`) |\n\n### Starting & Stopping\n\nLoops start automatically via `ralph run`:\n- **Primary loop**: Runs in main workspace, holds `.ralph\u002Floop.lock`\n- **Worktree loop**: Created when primary is running, isolated in `.worktrees\u002F\u003Cloop-id>\u002F`\n\n```bash\nralph loops                       # Any loops running?\ncat .ralph\u002Floop.lock 2>\u002Fdev\u002Fnull  # Primary loop details\nralph loops stop \u003Cid>             # Graceful stop\nralph loops stop \u003Cid> --force     # Immediate stop\nralph loops discard \u003Cid>          # Abandon + clean worktree\n```\n\n### Inspecting Loops\n\n```bash\nralph loops diff \u003Cid>             # What changed\nralph loops logs \u003Cid> -f          # Live event log\nralph loops history \u003Cid>          # State changes\nralph loops attach \u003Cid>           # Shell into worktree\n```\n\n**Worktree context files** (`.worktrees\u002F\u003Cloop-id>\u002F`):\n\n| File | Contents |\n|------|----------|\n| `.ralph\u002Fevents.jsonl` | Event stream: hats, iterations, tool calls |\n| `.ralph\u002Fagent\u002Fsummary.md` | Current session summary |\n| `.ralph\u002Fagent\u002Fhandoff.md` | Handoff context for next iteration |\n| `.ralph\u002Fagent\u002Fscratchpad.md` | Working notes |\n| `.ralph\u002Fagent\u002Ftasks.jsonl` | Runtime task state |\n\n**Primary loop** uses the same files at `.ralph\u002Fagent\u002F` in repo root.\n\n### Merge Queue\n\nFlow: `Queued → Merging → Merged` or `→ NeedsReview → Merging (retry)` or `→ Discarded`\n\n```bash\nralph loops merge \u003Cid>            # Queue for merge\nralph loops process               # Process pending merges now\nralph loops retry \u003Cid>            # Retry failed merge\n```\n\n**Reading state:**\n```bash\njq -r '.prompt' .ralph\u002Floop.lock 2>\u002Fdev\u002Fnull\ntail -20 .ralph\u002Fmerge-queue.jsonl | jq .\n```\n\n---\n\n## Diagnostics\n\n### Enabling\n\n```bash\nRALPH_DIAGNOSTICS=1 ralph run -p \"your prompt\"\n```\n\nZero overhead when disabled. Output: `.ralph\u002Fdiagnostics\u002F\u003CYYYY-MM-DDTHH-MM-SS>\u002F`\n\n### Session Discovery\n\n```bash\nLATEST=$(ls -t .ralph\u002Fdiagnostics\u002F | head -1)\nSESSION=\".ralph\u002Fdiagnostics\u002F$LATEST\"\n```\n\n### File Reference\n\n| File | Contains | Key Fields |\n|------|----------|------------|\n| `agent-output.jsonl` | Agent text, tool calls, results | `type`, `iteration`, `hat` |\n| `orchestration.jsonl` | Hat selection, events, backpressure | `event.type`, `iteration`, `hat` |\n| `performance.jsonl` | Timing, latency, token counts | `metric.type`, `iteration`, `hat` |\n| `errors.jsonl` | Parse errors, validation failures | `error_type`, `message`, `context` |\n| `trace.jsonl` | All tracing logs with metadata | `level`, `target`, `message` |\n\n### Diagnostic Workflow\n\n**1. Errors first:**\n```bash\nwc -l \"$SESSION\u002Ferrors.jsonl\"\njq '.' \"$SESSION\u002Ferrors.jsonl\"\njq -s 'group_by(.error_type) | map({type: .[0].error_type, count: length})' \"$SESSION\u002Ferrors.jsonl\"\n```\n\n**2. Orchestration flow:**\n```bash\njq '{iter: .iteration, hat: .hat, event: .event.type}' \"$SESSION\u002Forchestration.jsonl\"\njq 'select(.event.type == \"hat_selected\") | {iter: .iteration, hat: .event.hat, reason: .event.reason}' \"$SESSION\u002Forchestration.jsonl\"\njq 'select(.event.type == \"backpressure_triggered\") | {iter: .iteration, reason: .event.reason}' \"$SESSION\u002Forchestration.jsonl\"\n```\n\n**3. Agent activity:**\n```bash\njq 'select(.type == \"tool_call\") | {iter: .iteration, tool: .name}' \"$SESSION\u002Fagent-output.jsonl\"\njq -s '[.[] | select(.type == \"tool_call\")] | group_by(.iteration) | map({iter: .[0].iteration, tools: [.[].name]})' \"$SESSION\u002Fagent-output.jsonl\"\n```\n\n**4. Performance:**\n```bash\njq 'select(.metric.type == \"iteration_duration\") | {iter: .iteration, ms: .metric.duration_ms}' \"$SESSION\u002Fperformance.jsonl\"\njq -s '[.[] | select(.metric.type == \"token_count\")] | {total_in: (map(.metric.input) | add), total_out: (map(.metric.output) | add)}' \"$SESSION\u002Fperformance.jsonl\"\n```\n\n**5. Trace logs:**\n```bash\njq 'select(.level == \"ERROR\" or .level == \"WARN\")' \"$SESSION\u002Ftrace.jsonl\"\n```\n\n### Quick Health Check\n\n```bash\nSESSION=\".ralph\u002Fdiagnostics\u002F$(ls -t .ralph\u002Fdiagnostics\u002F | head -1)\"\necho \"=== Session: $SESSION ===\"\necho -e \"\\n--- Errors ---\"\nwc -l \u003C \"$SESSION\u002Ferrors.jsonl\" 2>\u002Fdev\u002Fnull || echo \"0\"\necho -e \"\\n--- Iterations ---\"\njq -s 'map(select(.event.type == \"iteration_started\")) | length' \"$SESSION\u002Forchestration.jsonl\"\necho -e \"\\n--- Hats Used ---\"\njq -s '[.[] | select(.event.type == \"hat_selected\") | .event.hat] | unique' \"$SESSION\u002Forchestration.jsonl\"\necho -e \"\\n--- Backpressure Count ---\"\njq -s 'map(select(.event.type == \"backpressure_triggered\")) | length' \"$SESSION\u002Forchestration.jsonl\"\necho -e \"\\n--- Termination ---\"\njq 'select(.event.type == \"loop_terminated\")' \"$SESSION\u002Forchestration.jsonl\"\n```\n\n---\n\n## Troubleshooting\n\n### Stale Processes\n`ralph loops` shows loops that aren't running → `ralph loops prune`\n\n### Orphan Worktrees\n`.worktrees\u002F` has directories not in `ralph loops` → `ralph loops prune` or `git worktree remove .worktrees\u002F\u003Cid> --force`\n\n### Merge Conflicts\nLoop stuck in `needs-review`:\n1. `ralph loops diff \u003Cid>` — see conflicting changes\n2. `ralph loops attach \u003Cid>` — resolve manually, commit, retry\n3. `ralph loops discard \u003Cid>` — abandon if not worth fixing\n\n### Lock Stuck\n\"Loop already running\" but nothing is → `rm .ralph\u002Floop.lock` (safe if process is dead)\n\n### Agent Stuck in Loop\n```bash\njq -s '[.[] | select(.type == \"tool_call\")] | group_by(.name) | map({tool: .[0].name, count: length}) | sort_by(-.count)' \"$SESSION\u002Fagent-output.jsonl\"\n```\nRed flag: Many iterations with few events = agent not making progress.\n\n### Merge Stuck in \"merging\"\nProcess died mid-merge. Unblock:\n```bash\necho '{\"ts\":\"'$(date -u +%Y-%m-%dT%H:%M:%S.000000Z)'\",\"loop_id\":\"\u003Cloop-id>\",\"event\":{\"type\":\"needs_review\",\"reason\":\"Merge process died\"}}' >> .ralph\u002Fmerge-queue.jsonl\nralph loops discard \u003Cloop-id>\n```\n\n### Worktree Corruption\n```bash\ngit worktree repair\nralph loops prune\n```\n\n### Cleanup\n```bash\nralph clean --diagnostics              # Delete all sessions\nralph clean --diagnostics --dry-run    # Preview deletions\n```\n",{"name":5,"tags":36,"description":7},[30,22,23,26],"main","e7e336ac628c3e3bd771aff1aaa469c93778f94a","skills\u002Fpaulpete\u002Fralph-operations",0,"https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills","https:\u002F\u002Fgithub.com\u002Fkbarbel640-del","2026-08-23 22:39:37",{"source":8,"skillName":5,"commands":45,"prompt":55,"zipAvailable":56},[46,49,52],{"tool":47,"command":48},"npx","npx skills add kbarbel640-del\u002Fskills --skill ralph-operations",{"tool":50,"command":51},"bunx","bunx skills add kbarbel640-del\u002Fskills --skill ralph-operations",{"tool":53,"command":54},"pnpm","pnpm dlx skills add kbarbel640-del\u002Fskills --skill ralph-operations","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fpaulpete\u002Fralph-operations\u002FSKILL.md",true,[58],{"path":59,"resourceType":60,"resourceTypeDesc":61,"sizeBytes":62,"sourceHtmlUrl":63},"_meta.json","REFERENCE","参考文档",286,"https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fpaulpete\u002Fralph-operations\u002F_meta.json",[65,95,123,144,150,170],{"skillNo":66,"name":67,"nameZh":6,"description":68,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":69,"categories":70,"keywords":76,"publishedAt":31},"01M6G8J55967D6281ACMKAKTEQ","crowd-prompting","A marketplace where AI agents improve prompts, system instructions, tool descriptions, and other text-based content with domain expertise from real-world operations — and earn tokens for valuable contributions.","https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fzzadrian\u002Fcrowd-prompting\u002FSKILL.md",[71],{"categoryNo":72,"categoryName":73,"taxonomyType":74,"taxonomyTypeDesc":75},"01JBSEEDCAT000000000000036","内容创作者","PROFESSION","适用职业",[77,78,79,80,81,82,83,84,19,85,86,87,88,89,90,91,92,93,94],"crowd prompting","prompting","api","with","tokens","domain","world","prompts","instructions","text","tool","system","improve","productivity","marketplace","https","content","ai agents",{"skillNo":96,"name":97,"nameZh":6,"description":98,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":99,"categories":100,"keywords":106,"publishedAt":31},"01M6G8J0PKPAYVET6BWE8W4C26","dilemm-ai","Compete in DilemmAI, the prisoner's dilemma AI arena at dilemm.ai. Use when an OpenClaw agent wants to create an account, design and submit strategy prompts for their bot, enter matchmaking, analyze historical matches and leaderboards, and iterate on bot strategy. Requires headless browser automation (no API available yet).","https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fzyori\u002Fdilemm-ai\u002FSKILL.md",[101],{"categoryNo":102,"categoryName":103,"taxonomyType":104,"taxonomyTypeDesc":105},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[107,79,108,109,110,111,112,113,114,115,116,117,118,119,120,121,122,84,27],"dilemm ai","arena","analyze","browser","openclaw agent","create","automation","browser automation","bot","openclaw","design","strategy","headless","compete","submit","matchmaking",{"skillNo":124,"name":125,"nameZh":6,"description":126,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":127,"categories":128,"keywords":132,"publishedAt":31},"01M6G8HWAF3K9SW7NP3Z83CPJ6","arxiv-paper-reviews","Interact with arXiv Crawler API to fetch papers, read reviews, and submit comments. Use when working with arXiv papers, fetching paper lists by date\u002Fcategory\u002Finterest, viewing paper details with comments, or submitting paper reviews via API at http:\u002F\u002F150.158.152.82:8000.","https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fzxrys\u002Fweak-accept\u002FSKILL.md",[129],{"categoryNo":130,"categoryName":131,"taxonomyType":104,"taxonomyTypeDesc":105},"01JBSEEDCAT000000000000021","资料检索与研究",[133,134,135,136,137,138,139,80,140,121,27,141,79,142,143],"arxiv paper reviews","reviews","arxiv","paper","crawler","papers","comments","fetch","read","http","via",{"skillNo":145,"name":125,"nameZh":6,"description":126,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":146,"categories":147,"keywords":149,"publishedAt":31},"01M6G8HQJ7N7WMY6YV7D7SSJ16","https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fzxrys\u002Farxiv-paper-reviews\u002FSKILL.md",[148],{"categoryNo":130,"categoryName":131,"taxonomyType":104,"taxonomyTypeDesc":105},[136,135,134,133,143,138,139,80,137,121,27,140,141,79,142],{"skillNo":151,"name":152,"nameZh":6,"description":153,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":154,"categories":155,"keywords":156,"publishedAt":31},"01M6G8HM95Y64JNVFC2HN4E2BG","git-summary","Get a quick summary of the current Git repository including status, recent commits, branches, and contributors.","https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fzweack\u002Fgit-summary\u002FSKILL.md",[],[157,158,159,160,161,162,163,164,165,166,167,168,169],"git","summary","git summary","commits","repository","win32","status","linux","contributors","true","quick","get","branches",{"skillNo":171,"name":172,"nameZh":6,"description":173,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":174,"categories":175,"keywords":180,"publishedAt":31},"01M6G8HGEGF05CNEJCGVYFSC4R","agent-constitution","Interact with AgentConstitution governance contracts on Base Sepolia. Check compliance, read rules, log actions, query governance state.","https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fztsalexey\u002Fagent-constitution\u002FSKILL.md",[176,177],{"categoryNo":102,"categoryName":103,"taxonomyType":104,"taxonomyTypeDesc":105},{"categoryNo":178,"categoryName":179,"taxonomyType":74,"taxonomyTypeDesc":75},"01JBSEEDCAT000000000000037","律师与法务",[181,182,183,184,80,185,186,37,187,141,188,189,190,191,192,92,193,194,195],"agent constitution","constitution","contracts","tree","query","base","log","check","Rules","projects","compliance","actions","state","governance","github"]