[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6CK8HAPR4SBJ0PBBWFVT8P3":3,"skill-same:01M6CK8HAPR4SBJ0PBBWFVT8P3":90},{"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":22,"publishedAt":42,"linkOnly":43,"markdownContent":44,"markdownBody":45,"frontMatter":46,"refName":55,"commitSha":56,"skillDirectory":57,"forksCount":58,"repositoryHtmlUrl":59,"repositoryHomepageUrl":6,"ownerHtmlUrl":60,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":61,"install":62,"resources":75},"01M6CK8HAPR4SBJ0PBBWFVT8P3","ralph-loop",null,"Guide OpenClaw agents to execute Ralph Wiggum loops using exec and process tools. Agent orchestrates coding agents (Codex, Claude Code, OpenCode, Goose) with proper TTY support via pty:true. Plans\u002Fbuilds code via PROMPT.md + AGENTS.md, SPECS and IMPLEMENTATION_PLAN.md. Includes PLANNING vs BUILDING modes, backpressure, sandboxing, and completion conditions. Users request loops, agents execute using tools.","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\u002Faddozhang\u002Fralph-loop-agent\u002FSKILL.md",[17],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[23,24,25,26,27,28,29,30,5,31,32,33,34,35,36,37,38,39,40,41],"loop","ralph","ralph loop","Coding-Agent","process-tool","exec-tool","goose","tty","ai-agent","community","PTY","openclaw","opencode","guide","coding","plan","Tools","code","support","2026-11-10 10:12:30",false,"---\nname: ralph-loop\ndescription: Guide OpenClaw agents to execute Ralph Wiggum loops using exec and process tools. Agent orchestrates coding agents (Codex, Claude Code, OpenCode, Goose) with proper TTY support via pty:true. Plans\u002Fbuilds code via PROMPT.md + AGENTS.md, SPECS and IMPLEMENTATION_PLAN.md. Includes PLANNING vs BUILDING modes, backpressure, sandboxing, and completion conditions. Users request loops, agents execute using tools.\nversion: 1.1.0\nauthor: OpenClaw Community\nkeywords: [ralph-loop, ai-agent, coding-agent, pty, tty, automation, loop, opencode, codex, claude, goose, exec-tool, process-tool]\nlicense: MIT\n---\n\n# Ralph Loop\n\n## Overview\nThis skill guides **OpenClaw agents** to execute Ralph Loop workflows using the `exec` and `process` tools. The agent orchestrates AI coding agent sessions following the Ralph playbook flow:\n\n1) **Define Requirements** → JTBD → Focus Topics → `specs\u002F*.md`\n2) **PLANNING Loop** → Create\u002Fupdate `IMPLEMENTATION_PLAN.md` (do not implement)\n3) **BUILDING Loop** → Implement tasks, run tests (backpressure), update plan, commit\n\nThe loop persists context via `PROMPT.md` + `AGENTS.md` (loaded each iteration) and the plan\u002Fspecs on disk.\n\n## How This Skill Works\n\nThis skill generates instructions for **OpenClaw agents** to execute Ralph Loops using the `exec` and `process` tools.\n\n- The agent calls `exec` tool with the coding agent command\n- Uses `pty: true` to provide TTY for interactive CLIs\n- Uses `background: true` for monitoring capabilities\n- Uses `process` tool to monitor progress and detect completion\n\n**Important**: Users don't run these scripts directly - the OpenClaw agent executes them using its tool capabilities.\n\n---\n\n## TTY Requirements\n\nSome coding agents **require a real terminal (TTY)** to work properly, or they will hang:\n\n**Interactive CLIs (need TTY)**:\n- OpenCode, Codex, Claude Code, Pi, Goose\n\n**Non-interactive CLIs (file-based)**:\n- aider, custom scripts\n\n**Solution**: Use **exec + process mode** for interactive CLIs, simple loops for file-based tools.\n\n---\n\n## Agent Tool Usage Patterns\n\n### Interactive CLIs (Recommended Pattern)\n\nFor OpenCode, Codex, Claude Code, Pi, and Goose - these require TTY support:\n\n**When I (the agent) receive a Ralph Loop request, I will:**\n\n1. **Use exec tool** to launch the coding agent:\n   ```\n   exec tool with parameters:\n   - command: \"opencode run --model \u003CMODEL> \\\"$(cat PROMPT.md)\\\"\"\n   - workdir: \u003Cproject_path>\n   - background: true\n   - pty: true\n   - yieldMs: 60000\n   - timeout: 3600\n   ```\n\n2. **Capture session ID** from exec tool response\n\n3. **Use process tool** to monitor:\n   ```\n   process tool with:\n   - action: \"poll\"\n   - sessionId: \u003Ccaptured_session_id>\n   \n   process tool with:\n   - action: \"log\"\n   - sessionId: \u003Ccaptured_session_id>\n   - offset: -30  (for recent output)\n   ```\n\n4. **Check completion** by reading `IMPLEMENTATION_PLAN.md` for sentinel text\n\n5. **Clean up** with process kill if needed:\n   ```\n   process tool with:\n   - action: \"kill\"\n   - sessionId: \u003Csession_id>\n   ```\n\n**Benefits**: TTY support, real-time logs, timeout handling, parallel sessions, workdir isolation\n\n---\n\n## Agent Workflow\n\n### 1) Gather Inputs\n\n**Required**:\n- Goal \u002F JTBD\n- CLI (`opencode`, `codex`, `claude`, `goose`, `pi`, other)\n- Mode (`PLANNING`, `BUILDING`, or `BOTH`)\n- Max iterations (default: PLANNING=5, BUILDING=10)\n\n**Optional**:\n- Completion sentinel (default: `STATUS: COMPLETE` in `IMPLEMENTATION_PLAN.md`)\n- Working directory (default: `$PWD`)\n- Timeout per iteration (default: 3600s)\n- Sandbox choice\n- Auto-approval flags (`--full-auto`, `--yolo`, `--dangerously-skip-permissions`)\n\n**Auto-detect**:\n- If CLI in interactive list → use exec tool with pty: true\n- Extract model flag from CLI requirements\n\n### 2) Requirements → Specs (Optional)\n\nIf requirements are unclear:\n- Break JTBD into focus topics\n- Draft `specs\u002F\u003Ctopic>.md` for each\n- Keep specs short and testable\n\n### 3) PROMPT.md + AGENTS.md\n\n**PROMPT.md** references:\n- `specs\u002F*.md`\n- `IMPLEMENTATION_PLAN.md`\n- Relevant project files\n\n**AGENTS.md** includes:\n- Test commands (backpressure)\n- Build\u002Frun instructions\n- Operational learnings\n\n### 4) Prompt Templates\n\n**PLANNING Prompt** (no implementation):\n```\nYou are running a Ralph PLANNING loop for this goal: \u003Cgoal>.\n\nRead specs\u002F* and the current codebase. Only update IMPLEMENTATION_PLAN.md.\n\nRules:\n- Do not implement\n- Do not commit\n- Create a prioritized task list\n- Write down questions if unclear\n\nCompletion:\nWhen plan is ready, add: STATUS: PLANNING_COMPLETE\n```\n\n**BUILDING Prompt**:\n```\nYou are running a Ralph BUILDING loop for this goal: \u003Cgoal>.\n\nContext: specs\u002F*, IMPLEMENTATION_PLAN.md, AGENTS.md\n\nTasks:\n1) Pick the most important task\n2) Investigate code\n3) Implement\n4) Run backpressure commands from AGENTS.md\n5) Update IMPLEMENTATION_PLAN.md\n6) Update AGENTS.md with learnings\n7) Commit with clear message\n\nCompletion:\nWhen all done, add: STATUS: COMPLETE\n```\n\n### 5) CLI Command Reference\n\nThe agent constructs command strings using these patterns:\n\n| CLI | Command String Pattern |\n|-----|----------------------|\n| **OpenCode** | `opencode run --model \u003CMODEL> \"$(cat PROMPT.md)\"` |\n| **Codex** | `codex exec \u003CFLAGS> \"$(cat PROMPT.md)\"` (requires git) |\n| **Claude Code** | `claude \u003CFLAGS> \"$(cat PROMPT.md)\"` |\n| **Pi** | `pi --provider \u003CPROVIDER> --model \u003CMODEL> -p \"$(cat PROMPT.md)\"` |\n| **Goose** | `goose run \"$(cat PROMPT.md)\"` |\n\nCommon flags:\n- Codex: `--full-auto`, `--yolo`, `--model \u003Cmodel>`\n- Claude: `--dangerously-skip-permissions`\n\n---\n\n## Detailed Agent Tool Usage Examples\n\n### Example 1: OpenCode Ralph Loop\n\n**Agent executes this sequence:**\n\n```\nStep 1: Launch OpenCode with exec tool\n{\n  command: \"opencode run --model github-copilot\u002Fclaude-opus-4.5 \\\"$(cat PROMPT.md)\\\"\",\n  workdir: \"\u002Fpath\u002Fto\u002Fproject\",\n  background: true,\n  pty: true,\n  timeout: 3600,\n  yieldMs: 60000\n}\n\nStep 2: Capture session ID from response\nsessionId: \"abc123\"\n\nStep 3: Monitor with process tool every 10-30 seconds\n{\n  action: \"poll\",\n  sessionId: \"abc123\"\n}\n\nStep 4: Check recent logs\n{\n  action: \"log\",\n  sessionId: \"abc123\",\n  offset: -30\n}\n\nStep 5: Read IMPLEMENTATION_PLAN.md to check for completion\n- Look for: \"STATUS: COMPLETE\" or \"STATUS: PLANNING_COMPLETE\"\n\nStep 6: If complete or timeout, cleanup\n{\n  action: \"kill\",\n  sessionId: \"abc123\"\n}\n```\n\n### Example 2: Codex with Full Auto\n\n**Agent tool calls:**\n\n```\nexec tool:\n{\n  command: \"codex exec --full-auto --model anthropic\u002Fclaude-opus-4 \\\"$(cat PROMPT.md)\\\"\",\n  workdir: \"\u002Fpath\u002Fto\u002Fproject\",\n  background: true,\n  pty: true,\n  timeout: 3600\n}\n\n# Then monitor with process tool as above\n```\n\n---\n\n## Completion Detection\n\nUse flexible regex to match variations:\n\n```bash\ngrep -Eq \"STATUS:?\\s*(PLANNING_)?COMPLETE\" IMPLEMENTATION_PLAN.md\n```\n\n**Matches**:\n- `STATUS: COMPLETE`\n- `STATUS:COMPLETE`\n- `STATUS: PLANNING_COMPLETE`\n- `## Status: PLANNING_COMPLETE`\n\n---\n\n## Safety & Safeguards\n\n### Auto-Approval Flags (Risky!)\n- Codex: `--full-auto` (sandboxed, auto-approve) or `--yolo` (no sandbox!)\n- Claude: `--dangerously-skip-permissions`\n- **Recommendation**: Use sandboxes (docker\u002Fe2b\u002Ffly) and limited credentials\n\n### Escape Hatches\n- Stop: `Ctrl+C`\n- Kill session: process tool with action: \"kill\"\n- Rollback: `git reset --hard HEAD~N`\n\n### Best Practices\n1. **Start small**: Test with 1-2 iterations first\n2. **Workdir isolation**: Prevent reading unrelated files\n3. **Set timeouts**: Default 1h may not fit all tasks\n4. **Monitor actively**: Check logs, don't terminate prematurely\n5. **Requirements first**: Clear specs before building\n6. **Backpressure early**: Add tests from the start\n\n---\n\n## Troubleshooting\n\n| Problem | Solution |\n|---------|----------|\n| OpenCode hangs | Ensure agent uses exec tool with pty: true |\n| Session won't start | Check CLI path, git repo, command syntax |\n| Completion not detected | Verify sentinel format in IMPLEMENTATION_PLAN.md |\n| Process timeout | Agent should increase timeout parameter or simplify tasks |\n| Parallel conflicts | Agent should use git worktrees for isolation |\n| Can't see progress | Agent should use process tool with action: \"log\" |\n\n---\n\n## License\n\nMIT\n\n## Credits\n\nThis skill builds upon work by:\n- **@jordyvandomselaar** - Original Ralph Loop concept and workflow design\n- **@steipete** - Coding agent patterns and exec\u002Fprocess tool usage with pty support\n\nKey improvement: Uses OpenClaw's `exec` tool with `pty: true` to provide TTY for interactive CLIs, solving the hanging issue that occurs with simple background bash execution.\n","# Ralph Loop\n\n## Overview\nThis skill guides **OpenClaw agents** to execute Ralph Loop workflows using the `exec` and `process` tools. The agent orchestrates AI coding agent sessions following the Ralph playbook flow:\n\n1) **Define Requirements** → JTBD → Focus Topics → `specs\u002F*.md`\n2) **PLANNING Loop** → Create\u002Fupdate `IMPLEMENTATION_PLAN.md` (do not implement)\n3) **BUILDING Loop** → Implement tasks, run tests (backpressure), update plan, commit\n\nThe loop persists context via `PROMPT.md` + `AGENTS.md` (loaded each iteration) and the plan\u002Fspecs on disk.\n\n## How This Skill Works\n\nThis skill generates instructions for **OpenClaw agents** to execute Ralph Loops using the `exec` and `process` tools.\n\n- The agent calls `exec` tool with the coding agent command\n- Uses `pty: true` to provide TTY for interactive CLIs\n- Uses `background: true` for monitoring capabilities\n- Uses `process` tool to monitor progress and detect completion\n\n**Important**: Users don't run these scripts directly - the OpenClaw agent executes them using its tool capabilities.\n\n---\n\n## TTY Requirements\n\nSome coding agents **require a real terminal (TTY)** to work properly, or they will hang:\n\n**Interactive CLIs (need TTY)**:\n- OpenCode, Codex, Claude Code, Pi, Goose\n\n**Non-interactive CLIs (file-based)**:\n- aider, custom scripts\n\n**Solution**: Use **exec + process mode** for interactive CLIs, simple loops for file-based tools.\n\n---\n\n## Agent Tool Usage Patterns\n\n### Interactive CLIs (Recommended Pattern)\n\nFor OpenCode, Codex, Claude Code, Pi, and Goose - these require TTY support:\n\n**When I (the agent) receive a Ralph Loop request, I will:**\n\n1. **Use exec tool** to launch the coding agent:\n   ```\n   exec tool with parameters:\n   - command: \"opencode run --model \u003CMODEL> \\\"$(cat PROMPT.md)\\\"\"\n   - workdir: \u003Cproject_path>\n   - background: true\n   - pty: true\n   - yieldMs: 60000\n   - timeout: 3600\n   ```\n\n2. **Capture session ID** from exec tool response\n\n3. **Use process tool** to monitor:\n   ```\n   process tool with:\n   - action: \"poll\"\n   - sessionId: \u003Ccaptured_session_id>\n   \n   process tool with:\n   - action: \"log\"\n   - sessionId: \u003Ccaptured_session_id>\n   - offset: -30  (for recent output)\n   ```\n\n4. **Check completion** by reading `IMPLEMENTATION_PLAN.md` for sentinel text\n\n5. **Clean up** with process kill if needed:\n   ```\n   process tool with:\n   - action: \"kill\"\n   - sessionId: \u003Csession_id>\n   ```\n\n**Benefits**: TTY support, real-time logs, timeout handling, parallel sessions, workdir isolation\n\n---\n\n## Agent Workflow\n\n### 1) Gather Inputs\n\n**Required**:\n- Goal \u002F JTBD\n- CLI (`opencode`, `codex`, `claude`, `goose`, `pi`, other)\n- Mode (`PLANNING`, `BUILDING`, or `BOTH`)\n- Max iterations (default: PLANNING=5, BUILDING=10)\n\n**Optional**:\n- Completion sentinel (default: `STATUS: COMPLETE` in `IMPLEMENTATION_PLAN.md`)\n- Working directory (default: `$PWD`)\n- Timeout per iteration (default: 3600s)\n- Sandbox choice\n- Auto-approval flags (`--full-auto`, `--yolo`, `--dangerously-skip-permissions`)\n\n**Auto-detect**:\n- If CLI in interactive list → use exec tool with pty: true\n- Extract model flag from CLI requirements\n\n### 2) Requirements → Specs (Optional)\n\nIf requirements are unclear:\n- Break JTBD into focus topics\n- Draft `specs\u002F\u003Ctopic>.md` for each\n- Keep specs short and testable\n\n### 3) PROMPT.md + AGENTS.md\n\n**PROMPT.md** references:\n- `specs\u002F*.md`\n- `IMPLEMENTATION_PLAN.md`\n- Relevant project files\n\n**AGENTS.md** includes:\n- Test commands (backpressure)\n- Build\u002Frun instructions\n- Operational learnings\n\n### 4) Prompt Templates\n\n**PLANNING Prompt** (no implementation):\n```\nYou are running a Ralph PLANNING loop for this goal: \u003Cgoal>.\n\nRead specs\u002F* and the current codebase. Only update IMPLEMENTATION_PLAN.md.\n\nRules:\n- Do not implement\n- Do not commit\n- Create a prioritized task list\n- Write down questions if unclear\n\nCompletion:\nWhen plan is ready, add: STATUS: PLANNING_COMPLETE\n```\n\n**BUILDING Prompt**:\n```\nYou are running a Ralph BUILDING loop for this goal: \u003Cgoal>.\n\nContext: specs\u002F*, IMPLEMENTATION_PLAN.md, AGENTS.md\n\nTasks:\n1) Pick the most important task\n2) Investigate code\n3) Implement\n4) Run backpressure commands from AGENTS.md\n5) Update IMPLEMENTATION_PLAN.md\n6) Update AGENTS.md with learnings\n7) Commit with clear message\n\nCompletion:\nWhen all done, add: STATUS: COMPLETE\n```\n\n### 5) CLI Command Reference\n\nThe agent constructs command strings using these patterns:\n\n| CLI | Command String Pattern |\n|-----|----------------------|\n| **OpenCode** | `opencode run --model \u003CMODEL> \"$(cat PROMPT.md)\"` |\n| **Codex** | `codex exec \u003CFLAGS> \"$(cat PROMPT.md)\"` (requires git) |\n| **Claude Code** | `claude \u003CFLAGS> \"$(cat PROMPT.md)\"` |\n| **Pi** | `pi --provider \u003CPROVIDER> --model \u003CMODEL> -p \"$(cat PROMPT.md)\"` |\n| **Goose** | `goose run \"$(cat PROMPT.md)\"` |\n\nCommon flags:\n- Codex: `--full-auto`, `--yolo`, `--model \u003Cmodel>`\n- Claude: `--dangerously-skip-permissions`\n\n---\n\n## Detailed Agent Tool Usage Examples\n\n### Example 1: OpenCode Ralph Loop\n\n**Agent executes this sequence:**\n\n```\nStep 1: Launch OpenCode with exec tool\n{\n  command: \"opencode run --model github-copilot\u002Fclaude-opus-4.5 \\\"$(cat PROMPT.md)\\\"\",\n  workdir: \"\u002Fpath\u002Fto\u002Fproject\",\n  background: true,\n  pty: true,\n  timeout: 3600,\n  yieldMs: 60000\n}\n\nStep 2: Capture session ID from response\nsessionId: \"abc123\"\n\nStep 3: Monitor with process tool every 10-30 seconds\n{\n  action: \"poll\",\n  sessionId: \"abc123\"\n}\n\nStep 4: Check recent logs\n{\n  action: \"log\",\n  sessionId: \"abc123\",\n  offset: -30\n}\n\nStep 5: Read IMPLEMENTATION_PLAN.md to check for completion\n- Look for: \"STATUS: COMPLETE\" or \"STATUS: PLANNING_COMPLETE\"\n\nStep 6: If complete or timeout, cleanup\n{\n  action: \"kill\",\n  sessionId: \"abc123\"\n}\n```\n\n### Example 2: Codex with Full Auto\n\n**Agent tool calls:**\n\n```\nexec tool:\n{\n  command: \"codex exec --full-auto --model anthropic\u002Fclaude-opus-4 \\\"$(cat PROMPT.md)\\\"\",\n  workdir: \"\u002Fpath\u002Fto\u002Fproject\",\n  background: true,\n  pty: true,\n  timeout: 3600\n}\n\n# Then monitor with process tool as above\n```\n\n---\n\n## Completion Detection\n\nUse flexible regex to match variations:\n\n```bash\ngrep -Eq \"STATUS:?\\s*(PLANNING_)?COMPLETE\" IMPLEMENTATION_PLAN.md\n```\n\n**Matches**:\n- `STATUS: COMPLETE`\n- `STATUS:COMPLETE`\n- `STATUS: PLANNING_COMPLETE`\n- `## Status: PLANNING_COMPLETE`\n\n---\n\n## Safety & Safeguards\n\n### Auto-Approval Flags (Risky!)\n- Codex: `--full-auto` (sandboxed, auto-approve) or `--yolo` (no sandbox!)\n- Claude: `--dangerously-skip-permissions`\n- **Recommendation**: Use sandboxes (docker\u002Fe2b\u002Ffly) and limited credentials\n\n### Escape Hatches\n- Stop: `Ctrl+C`\n- Kill session: process tool with action: \"kill\"\n- Rollback: `git reset --hard HEAD~N`\n\n### Best Practices\n1. **Start small**: Test with 1-2 iterations first\n2. **Workdir isolation**: Prevent reading unrelated files\n3. **Set timeouts**: Default 1h may not fit all tasks\n4. **Monitor actively**: Check logs, don't terminate prematurely\n5. **Requirements first**: Clear specs before building\n6. **Backpressure early**: Add tests from the start\n\n---\n\n## Troubleshooting\n\n| Problem | Solution |\n|---------|----------|\n| OpenCode hangs | Ensure agent uses exec tool with pty: true |\n| Session won't start | Check CLI path, git repo, command syntax |\n| Completion not detected | Verify sentinel format in IMPLEMENTATION_PLAN.md |\n| Process timeout | Agent should increase timeout parameter or simplify tasks |\n| Parallel conflicts | Agent should use git worktrees for isolation |\n| Can't see progress | Agent should use process tool with action: \"log\" |\n\n---\n\n## License\n\nMIT\n\n## Credits\n\nThis skill builds upon work by:\n- **@jordyvandomselaar** - Original Ralph Loop concept and workflow design\n- **@steipete** - Coding agent patterns and exec\u002Fprocess tool usage with pty support\n\nKey improvement: Uses OpenClaw's `exec` tool with `pty: true` to provide TTY for interactive CLIs, solving the hanging issue that occurs with simple background bash execution.\n",{"name":5,"author":47,"license":14,"version":48,"keywords":49,"description":7},"OpenClaw Community","1.1.0",[5,31,50,51,30,52,23,35,53,54,29,28,27],"coding-agent","pty","automation","codex","claude","main","e7e336ac628c3e3bd771aff1aaa469c93778f94a","skills\u002Faddozhang\u002Fralph-loop-agent",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":63,"prompt":73,"zipAvailable":74},[64,67,70],{"tool":65,"command":66},"npx","npx skills add kbarbel640-del\u002Fskills --skill ralph-loop",{"tool":68,"command":69},"bunx","bunx skills add kbarbel640-del\u002Fskills --skill ralph-loop",{"tool":71,"command":72},"pnpm","pnpm dlx skills add kbarbel640-del\u002Fskills --skill ralph-loop","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Faddozhang\u002Fralph-loop-agent\u002FSKILL.md",true,[76,82,86],{"path":77,"resourceType":78,"resourceTypeDesc":79,"sizeBytes":80,"sourceHtmlUrl":81},"_meta.json","REFERENCE","参考文档",294,"https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Faddozhang\u002Fralph-loop-agent\u002F_meta.json",{"path":83,"resourceType":78,"resourceTypeDesc":79,"sizeBytes":84,"sourceHtmlUrl":85},"package.json",1961,"https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Faddozhang\u002Fralph-loop-agent\u002Fpackage.json",{"path":87,"resourceType":78,"resourceTypeDesc":79,"sizeBytes":88,"sourceHtmlUrl":89},"README.md",12491,"https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Faddozhang\u002Fralph-loop-agent\u002FREADME.md",[91,122,145,166,172,192],{"skillNo":92,"name":93,"nameZh":6,"description":94,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":95,"categories":96,"keywords":102,"publishedAt":42},"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",[97],{"categoryNo":98,"categoryName":99,"taxonomyType":100,"taxonomyTypeDesc":101},"01JBSEEDCAT000000000000036","内容创作者","PROFESSION","适用职业",[103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121],"crowd prompting","prompting","api","with","tokens","domain","world","prompts","operations","instructions","text","tool","system","improve","productivity","marketplace","https","content","ai agents",{"skillNo":123,"name":124,"nameZh":6,"description":125,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":126,"categories":127,"keywords":129,"publishedAt":42},"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",[128],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},[130,105,131,132,133,134,135,52,136,137,34,138,139,140,141,142,143,110,144],"dilemm ai","arena","analyze","browser","openclaw agent","create","browser automation","bot","design","strategy","headless","compete","submit","matchmaking","use",{"skillNo":146,"name":147,"nameZh":6,"description":148,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":149,"categories":150,"keywords":154,"publishedAt":42},"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",[151],{"categoryNo":152,"categoryName":153,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000021","资料检索与研究",[155,156,157,158,159,160,161,106,162,142,144,163,105,164,165],"arxiv paper reviews","reviews","arxiv","paper","crawler","papers","comments","fetch","read","http","via",{"skillNo":167,"name":147,"nameZh":6,"description":148,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":168,"categories":169,"keywords":171,"publishedAt":42},"01M6G8HQJ7N7WMY6YV7D7SSJ16","https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fzxrys\u002Farxiv-paper-reviews\u002FSKILL.md",[170],{"categoryNo":152,"categoryName":153,"taxonomyType":20,"taxonomyTypeDesc":21},[158,157,156,155,165,160,161,106,159,142,144,162,163,105,164],{"skillNo":173,"name":174,"nameZh":6,"description":175,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":176,"categories":177,"keywords":178,"publishedAt":42},"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",[],[179,180,181,182,183,184,185,186,187,188,189,190,191],"git","summary","git summary","commits","repository","win32","status","linux","contributors","true","quick","get","branches",{"skillNo":193,"name":194,"nameZh":6,"description":195,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":196,"categories":197,"keywords":202,"publishedAt":42},"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",[198,199],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},{"categoryNo":200,"categoryName":201,"taxonomyType":100,"taxonomyTypeDesc":101},"01JBSEEDCAT000000000000037","律师与法务",[203,204,205,206,106,207,208,55,209,163,210,211,212,213,214,119,215,216,217],"agent constitution","constitution","contracts","tree","query","base","log","check","Rules","projects","compliance","actions","state","governance","github"]