[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6FTAAD88DHF07FDGTK5K956":3,"skill-same:01M6FTAAD88DHF07FDGTK5K956":75},{"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":43,"linkOnly":44,"markdownContent":45,"markdownBody":46,"frontMatter":47,"refName":48,"commitSha":49,"skillDirectory":50,"forksCount":51,"repositoryHtmlUrl":52,"repositoryHomepageUrl":6,"ownerHtmlUrl":53,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":54,"install":55,"resources":68},"01M6FTAAD88DHF07FDGTK5K956","ralph-loop",null,"Generate copy-paste bash scripts for Ralph Wiggum\u002FAI agent loops (Codex, Claude Code, OpenCode, Goose). Use when asked for a “Ralph loop”, “Ralph Wiggum loop”, or an AI loop to plan\u002Fbuild code via PROMPT.md + AGENTS.md, SPECS, and IMPLEMENTATION_PLAN.md, including PLANNING vs BUILDING modes, backpressure, sandboxing, and completion conditions.","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\u002Fjordyvandomselaar\u002Fralph-loop\u002FSKILL.md",[17],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42],"loop","ralph loop","ralph","prompt","loops","via","goose","ralph wiggum","build","ai loop","opencode","use","codex","plan","Bash","sandboxing","planning","code","generate","ai agent","2026-11-10 10:12:30",false,"---\nname: ralph-loop\ndescription: Generate copy-paste bash scripts for Ralph Wiggum\u002FAI agent loops (Codex, Claude Code, OpenCode, Goose). Use when asked for a “Ralph loop”, “Ralph Wiggum loop”, or an AI loop to plan\u002Fbuild code via PROMPT.md + AGENTS.md, SPECS, and IMPLEMENTATION_PLAN.md, including PLANNING vs BUILDING modes, backpressure, sandboxing, and completion conditions.\n---\n\n# Ralph Loop\n\n## Overview\nGenerate a ready-to-run bash script that runs an AI coding CLI in a loop. Align with the Ralph playbook flow:\n\n1) **Define requirements** → JTBD → topics of concern → `specs\u002F*.md`\n2) **PLANNING loop** → create\u002Fupdate `IMPLEMENTATION_PLAN.md` (no implementation)\n3) **BUILDING loop** → implement tasks, run tests (backpressure), update plan, commit\n\nThe loop persists context via `PROMPT.md` + `AGENTS.md` (loaded every iteration) plus the on-disk plan\u002Fspecs.\n\n## Workflow\n\n### 1) Collect inputs (ask if missing)\n- **Goal \u002F JTBD** (what outcome is needed)\n- CLI (`codex`, `claude-code`, `opencode`, `goose`, other)\n- **Mode**: `PLANNING`, `BUILDING`, or `BOTH`\n- **Completion condition**\n  - Promise phrase (string to detect), **or**\n  - Test\u002Fcommand to run each iteration, **or**\n  - Plan sentinel (e.g., a line `STATUS: COMPLETE` in `IMPLEMENTATION_PLAN.md`)\n- Max iterations\n- Sandbox choice (`none` | `docker` | other) + **security posture**\n- **Backpressure commands** (tests\u002Flints\u002Fbuild) to embed in `AGENTS.md`\n- **Auto‑approve flags** (ask explicitly)\n  - Codex: `--full-auto`\n  - Claude Code: `--dangerously-skip-permissions`\n\n### 2) Phase 1 — Requirements → specs\nIf the user wants “full Ralph” (or unclear requirements), do this before the loop:\n- Break the JTBD into **topics of concern** (1 topic = 1 spec file).\n- For each topic, draft `specs\u002F\u003Ctopic>.md`.\n- Use subagents to load URLs or existing docs into context for spec quality.\n- Keep specs short and testable.\n\n### 3) Phase 2\u002F3 — PROMPT.md + AGENTS.md\n- **Context loaded each iteration:** `PROMPT.md` + `AGENTS.md`.\n- `AGENTS.md` should include:\n  - project test commands (backpressure)\n  - build\u002Frun instructions\n  - any operational learnings\n- `PROMPT.md` should reference:\n  - `specs\u002F*.md`\n  - `IMPLEMENTATION_PLAN.md`\n  - any relevant project files\u002Fdirs\n\n### 4) Two prompt templates (PLANNING vs BUILDING)\nCreate **two prompts** and swap `PROMPT.md` based on mode.\n\n**PLANNING prompt (no implementation):**\n```\nYou are running a Ralph PLANNING loop for: \u003CJTBD\u002FGOAL>.\n\nRead specs\u002F* and the current codebase. Do a gap analysis and update IMPLEMENTATION_PLAN.md only.\nRules:\n- Do NOT implement.\n- Do NOT commit.\n- Prioritize tasks and keep plan concise.\n- If requirements are unclear, write clarifying questions into the plan.\n\nCompletion:\nIf the plan is complete, add line: STATUS: COMPLETE\n```\n\n**BUILDING prompt:**\n```\nYou are running a Ralph BUILDING loop for: \u003CJTBD\u002FGOAL>.\n\nContext:\n- specs\u002F*\n- IMPLEMENTATION_PLAN.md\n- AGENTS.md (tests\u002Fbackpressure)\n\nTasks:\n1) Pick the most important task from IMPLEMENTATION_PLAN.md.\n2) Investigate relevant code (don’t assume missing).\n3) Implement.\n4) Run the backpressure commands from AGENTS.md.\n5) Update IMPLEMENTATION_PLAN.md (mark done + notes).\n6) Update AGENTS.md if you learned new operational details.\n7) Commit with a clear message.\n\nCompletion:\nIf all tasks are done, add line: STATUS: COMPLETE\n```\n\n### 5) Build the per‑iteration command\n- Codex: `codex exec \u003CFLAGS> \"$(cat PROMPT.md)\"`\n  - Requires git repo.\n- Claude Code: `claude \u003CFLAGS> \"$(cat PROMPT.md)\"`\n- OpenCode: `opencode run \"$(cat PROMPT.md)\"`\n- Goose: `goose run \"$(cat PROMPT.md)\"` (ask if they want the Goose recipe)\n\nIf the CLI is unknown, ask for the exact command to run each iteration.\n\n### 6) Output a copy‑paste script\nProvide **either** a minimal loop or a controlled loop with max iters + stop conditions.\n\n**Minimal loop (Geoff style):**\n```bash\nwhile :; do cat PROMPT.md | claude ; done\n```\n\n**Controlled loop (recommended):**\n```bash\n#!\u002Fusr\u002Fbin\u002Fenv bash\nset -euo pipefail\n\nPROMISE='...'\nMAX_ITERS=...\nCLI_FLAGS=\"...\"  # optional\nPLAN_SENTINEL='STATUS: COMPLETE'\nTEST_CMD='...'   # optional\n\nif ! git rev-parse --is-inside-work-tree >\u002Fdev\u002Fnull 2>&1; then\n  echo \"❌ Run this inside a git repo.\"\n  exit 1\nfi\n\ntouch PROMPT.md AGENTS.md IMPLEMENTATION_PLAN.md\nLOG_FILE=\".ralph\u002Fralph.log\"\nmkdir -p .ralph\n\nCLI_CMD=\"...\" # e.g. \"codex exec\" or \"claude\"\n\nfor i in $(seq 1 \"$MAX_ITERS\"); do\n  echo -e \"\\n=== Ralph iteration $i\u002F$MAX_ITERS ===\" | tee -a \"$LOG_FILE\"\n\n  $CLI_CMD $CLI_FLAGS \"$(cat PROMPT.md)\" | tee -a \"$LOG_FILE\"\n\n  if [[ -n \"${TEST_CMD}\" ]]; then\n    echo \"Running tests: $TEST_CMD\" | tee -a \"$LOG_FILE\"\n    bash -lc \"$TEST_CMD\" | tee -a \"$LOG_FILE\"\n  fi\n\n  if grep -Fq \"$PROMISE\" \"$LOG_FILE\" || grep -Fq \"$PLAN_SENTINEL\" IMPLEMENTATION_PLAN.md; then\n    echo \"✅ Completion detected. Stopping.\" | tee -a \"$LOG_FILE\"\n    exit 0\n  fi\n\ndone\n\necho \"❌ Max iterations reached without completion.\" | tee -a \"$LOG_FILE\"\nexit 1\n```\n\n## Safety\u002FSandbox Guidance (must mention)\n- Running with `--dangerously-skip-permissions` or `--full-auto` implies **trust + risk**.\n- Recommend a **sandbox** (docker\u002Fe2b\u002Ffly) with minimal credentials and restricted network.\n- Escape hatches: `Ctrl+C` to stop; `git reset --hard` to revert.\n\n## Guardrails\n- If requirements are unclear, insist on specs before BUILDING.\n- If the plan looks stale\u002Fwrong, regenerate it (PLANNING loop).\n- If backpressure commands are missing, ask for them and add to `AGENTS.md`.\n","# Ralph Loop\n\n## Overview\nGenerate a ready-to-run bash script that runs an AI coding CLI in a loop. Align with the Ralph playbook flow:\n\n1) **Define requirements** → JTBD → topics of concern → `specs\u002F*.md`\n2) **PLANNING loop** → create\u002Fupdate `IMPLEMENTATION_PLAN.md` (no implementation)\n3) **BUILDING loop** → implement tasks, run tests (backpressure), update plan, commit\n\nThe loop persists context via `PROMPT.md` + `AGENTS.md` (loaded every iteration) plus the on-disk plan\u002Fspecs.\n\n## Workflow\n\n### 1) Collect inputs (ask if missing)\n- **Goal \u002F JTBD** (what outcome is needed)\n- CLI (`codex`, `claude-code`, `opencode`, `goose`, other)\n- **Mode**: `PLANNING`, `BUILDING`, or `BOTH`\n- **Completion condition**\n  - Promise phrase (string to detect), **or**\n  - Test\u002Fcommand to run each iteration, **or**\n  - Plan sentinel (e.g., a line `STATUS: COMPLETE` in `IMPLEMENTATION_PLAN.md`)\n- Max iterations\n- Sandbox choice (`none` | `docker` | other) + **security posture**\n- **Backpressure commands** (tests\u002Flints\u002Fbuild) to embed in `AGENTS.md`\n- **Auto‑approve flags** (ask explicitly)\n  - Codex: `--full-auto`\n  - Claude Code: `--dangerously-skip-permissions`\n\n### 2) Phase 1 — Requirements → specs\nIf the user wants “full Ralph” (or unclear requirements), do this before the loop:\n- Break the JTBD into **topics of concern** (1 topic = 1 spec file).\n- For each topic, draft `specs\u002F\u003Ctopic>.md`.\n- Use subagents to load URLs or existing docs into context for spec quality.\n- Keep specs short and testable.\n\n### 3) Phase 2\u002F3 — PROMPT.md + AGENTS.md\n- **Context loaded each iteration:** `PROMPT.md` + `AGENTS.md`.\n- `AGENTS.md` should include:\n  - project test commands (backpressure)\n  - build\u002Frun instructions\n  - any operational learnings\n- `PROMPT.md` should reference:\n  - `specs\u002F*.md`\n  - `IMPLEMENTATION_PLAN.md`\n  - any relevant project files\u002Fdirs\n\n### 4) Two prompt templates (PLANNING vs BUILDING)\nCreate **two prompts** and swap `PROMPT.md` based on mode.\n\n**PLANNING prompt (no implementation):**\n```\nYou are running a Ralph PLANNING loop for: \u003CJTBD\u002FGOAL>.\n\nRead specs\u002F* and the current codebase. Do a gap analysis and update IMPLEMENTATION_PLAN.md only.\nRules:\n- Do NOT implement.\n- Do NOT commit.\n- Prioritize tasks and keep plan concise.\n- If requirements are unclear, write clarifying questions into the plan.\n\nCompletion:\nIf the plan is complete, add line: STATUS: COMPLETE\n```\n\n**BUILDING prompt:**\n```\nYou are running a Ralph BUILDING loop for: \u003CJTBD\u002FGOAL>.\n\nContext:\n- specs\u002F*\n- IMPLEMENTATION_PLAN.md\n- AGENTS.md (tests\u002Fbackpressure)\n\nTasks:\n1) Pick the most important task from IMPLEMENTATION_PLAN.md.\n2) Investigate relevant code (don’t assume missing).\n3) Implement.\n4) Run the backpressure commands from AGENTS.md.\n5) Update IMPLEMENTATION_PLAN.md (mark done + notes).\n6) Update AGENTS.md if you learned new operational details.\n7) Commit with a clear message.\n\nCompletion:\nIf all tasks are done, add line: STATUS: COMPLETE\n```\n\n### 5) Build the per‑iteration command\n- Codex: `codex exec \u003CFLAGS> \"$(cat PROMPT.md)\"`\n  - Requires git repo.\n- Claude Code: `claude \u003CFLAGS> \"$(cat PROMPT.md)\"`\n- OpenCode: `opencode run \"$(cat PROMPT.md)\"`\n- Goose: `goose run \"$(cat PROMPT.md)\"` (ask if they want the Goose recipe)\n\nIf the CLI is unknown, ask for the exact command to run each iteration.\n\n### 6) Output a copy‑paste script\nProvide **either** a minimal loop or a controlled loop with max iters + stop conditions.\n\n**Minimal loop (Geoff style):**\n```bash\nwhile :; do cat PROMPT.md | claude ; done\n```\n\n**Controlled loop (recommended):**\n```bash\n#!\u002Fusr\u002Fbin\u002Fenv bash\nset -euo pipefail\n\nPROMISE='...'\nMAX_ITERS=...\nCLI_FLAGS=\"...\"  # optional\nPLAN_SENTINEL='STATUS: COMPLETE'\nTEST_CMD='...'   # optional\n\nif ! git rev-parse --is-inside-work-tree >\u002Fdev\u002Fnull 2>&1; then\n  echo \"❌ Run this inside a git repo.\"\n  exit 1\nfi\n\ntouch PROMPT.md AGENTS.md IMPLEMENTATION_PLAN.md\nLOG_FILE=\".ralph\u002Fralph.log\"\nmkdir -p .ralph\n\nCLI_CMD=\"...\" # e.g. \"codex exec\" or \"claude\"\n\nfor i in $(seq 1 \"$MAX_ITERS\"); do\n  echo -e \"\\n=== Ralph iteration $i\u002F$MAX_ITERS ===\" | tee -a \"$LOG_FILE\"\n\n  $CLI_CMD $CLI_FLAGS \"$(cat PROMPT.md)\" | tee -a \"$LOG_FILE\"\n\n  if [[ -n \"${TEST_CMD}\" ]]; then\n    echo \"Running tests: $TEST_CMD\" | tee -a \"$LOG_FILE\"\n    bash -lc \"$TEST_CMD\" | tee -a \"$LOG_FILE\"\n  fi\n\n  if grep -Fq \"$PROMISE\" \"$LOG_FILE\" || grep -Fq \"$PLAN_SENTINEL\" IMPLEMENTATION_PLAN.md; then\n    echo \"✅ Completion detected. Stopping.\" | tee -a \"$LOG_FILE\"\n    exit 0\n  fi\n\ndone\n\necho \"❌ Max iterations reached without completion.\" | tee -a \"$LOG_FILE\"\nexit 1\n```\n\n## Safety\u002FSandbox Guidance (must mention)\n- Running with `--dangerously-skip-permissions` or `--full-auto` implies **trust + risk**.\n- Recommend a **sandbox** (docker\u002Fe2b\u002Ffly) with minimal credentials and restricted network.\n- Escape hatches: `Ctrl+C` to stop; `git reset --hard` to revert.\n\n## Guardrails\n- If requirements are unclear, insist on specs before BUILDING.\n- If the plan looks stale\u002Fwrong, regenerate it (PLANNING loop).\n- If backpressure commands are missing, ask for them and add to `AGENTS.md`.\n",{"name":5,"description":7},"main","e7e336ac628c3e3bd771aff1aaa469c93778f94a","skills\u002Fjordyvandomselaar\u002Fralph-loop",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":56,"prompt":66,"zipAvailable":67},[57,60,63],{"tool":58,"command":59},"npx","npx skills add kbarbel640-del\u002Fskills --skill ralph-loop",{"tool":61,"command":62},"bunx","bunx skills add kbarbel640-del\u002Fskills --skill ralph-loop",{"tool":64,"command":65},"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\u002Fjordyvandomselaar\u002Fralph-loop\u002FSKILL.md",true,[69],{"path":70,"resourceType":71,"resourceTypeDesc":72,"sizeBytes":73,"sourceHtmlUrl":74},"_meta.json","REFERENCE","参考文档",283,"https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fjordyvandomselaar\u002Fralph-loop\u002F_meta.json",[76,107,131,151,157,177],{"skillNo":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":87,"publishedAt":43},"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",[82],{"categoryNo":83,"categoryName":84,"taxonomyType":85,"taxonomyTypeDesc":86},"01JBSEEDCAT000000000000036","内容创作者","PROFESSION","适用职业",[88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106],"crowd prompting","prompting","api","with","tokens","domain","world","prompts","operations","instructions","text","tool","system","improve","productivity","marketplace","https","content","ai agents",{"skillNo":108,"name":109,"nameZh":6,"description":110,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":111,"categories":112,"keywords":114,"publishedAt":43},"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",[113],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},[115,90,116,117,118,119,120,121,122,123,124,125,126,127,128,129,130,95,34],"dilemm ai","arena","analyze","browser","openclaw agent","create","automation","browser automation","bot","openclaw","design","strategy","headless","compete","submit","matchmaking",{"skillNo":132,"name":133,"nameZh":6,"description":134,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":135,"categories":136,"keywords":140,"publishedAt":43},"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",[137],{"categoryNo":138,"categoryName":139,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000021","资料检索与研究",[141,142,143,144,145,146,147,91,148,129,34,149,90,150,28],"arxiv paper reviews","reviews","arxiv","paper","crawler","papers","comments","fetch","read","http",{"skillNo":152,"name":133,"nameZh":6,"description":134,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":153,"categories":154,"keywords":156,"publishedAt":43},"01M6G8HQJ7N7WMY6YV7D7SSJ16","https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fzxrys\u002Farxiv-paper-reviews\u002FSKILL.md",[155],{"categoryNo":138,"categoryName":139,"taxonomyType":20,"taxonomyTypeDesc":21},[144,143,142,141,28,146,147,91,145,129,34,148,149,90,150],{"skillNo":158,"name":159,"nameZh":6,"description":160,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":161,"categories":162,"keywords":163,"publishedAt":43},"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",[],[164,165,166,167,168,169,170,171,172,173,174,175,176],"git","summary","git summary","commits","repository","win32","status","linux","contributors","true","quick","get","branches",{"skillNo":178,"name":179,"nameZh":6,"description":180,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":181,"categories":182,"keywords":187,"publishedAt":43},"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",[183,184],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},{"categoryNo":185,"categoryName":186,"taxonomyType":85,"taxonomyTypeDesc":86},"01JBSEEDCAT000000000000037","律师与法务",[188,189,190,191,91,192,193,48,194,149,195,196,197,198,199,104,200,201,202],"agent constitution","constitution","contracts","tree","query","base","log","check","Rules","projects","compliance","actions","state","governance","github"]