[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6FS7MA4HXB42VZQB91E4M16":3,"skill-same:01M6FS7MA4HXB42VZQB91E4M16":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":40,"linkOnly":41,"markdownContent":42,"markdownBody":43,"frontMatter":44,"refName":45,"commitSha":46,"skillDirectory":47,"forksCount":48,"repositoryHtmlUrl":49,"repositoryHomepageUrl":6,"ownerHtmlUrl":50,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":51,"install":52,"resources":65},"01M6FS7MA4HXB42VZQB91E4M16","agent-council",null,"Complete toolkit for creating autonomous AI agents and managing Discord channels for OpenClaw. Use when setting up multi-agent systems, creating new agents, or managing Discord channel organization.","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\u002Fitsahedge\u002Fagent-council\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],"agent council","council","use","channels","multi","complete","systems","organization","autonomous ai agents","up","openclaw","channel","autonomous","multi-agent","toolkit","ai agents","discord","2026-11-10 10:12:30",false,"---\nname: agent-council\ndescription: Complete toolkit for creating autonomous AI agents and managing Discord channels for OpenClaw. Use when setting up multi-agent systems, creating new agents, or managing Discord channel organization.\n---\n\n# Agent Council\n\nComplete toolkit for creating and managing autonomous AI agents with Discord integration for OpenClaw.\n\n## What This Skill Does\n\n**Agent Creation:**\n- Creates autonomous AI agents with self-contained workspaces\n- Generates SOUL.md (personality & responsibilities)\n- Generates HEARTBEAT.md (cron execution logic)\n- Sets up memory system (hybrid architecture)\n- Configures gateway automatically\n- Binds agents to Discord channels (optional)\n- Sets up daily memory cron jobs (optional)\n\n**Discord Channel Management:**\n- Creates Discord channels via API\n- Configures OpenClaw gateway allowlists\n- Sets channel-specific system prompts\n- Renames channels and updates references\n- Optional workspace file search\n\n## Installation\n\n```bash\n# Install from ClawHub\nclawhub install agent-council\n\n# Or manual install\ncp -r . ~\u002F.openclaw\u002Fskills\u002Fagent-council\u002F\nopenclaw gateway config.patch --raw '{\n  \"skills\": {\n    \"entries\": {\n      \"agent-council\": {\"enabled\": true}\n    }\n  }\n}'\n```\n\n## Part 1: Agent Creation\n\n### Quick Start\n\n```bash\nscripts\u002Fcreate-agent.sh \\\n  --name \"Watson\" \\\n  --id \"watson\" \\\n  --emoji \"?\" \\\n  --specialty \"Research and analysis specialist\" \\\n  --model \"anthropic\u002Fclaude-opus-4-5\" \\\n  --workspace \"$HOME\u002Fagents\u002Fwatson\" \\\n  --discord-channel \"1234567890\"\n```\n\n### Workflow\n\n#### 1. Gather Requirements\n\nAsk the user:\n- **Agent name** (e.g., \"Watson\")\n- **Agent ID** (lowercase, hyphenated, e.g., \"watson\")\n- **Emoji** (e.g., \"?\")\n- **Specialty** (what the agent does)\n- **Model** (which LLM to use)\n- **Workspace** (where to create agent files)\n- **Discord channel ID** (optional)\n\n#### 2. Run Creation Script\n\n```bash\nscripts\u002Fcreate-agent.sh \\\n  --name \"Agent Name\" \\\n  --id \"agent-id\" \\\n  --emoji \"?\" \\\n  --specialty \"What this agent does\" \\\n  --model \"provider\u002Fmodel-name\" \\\n  --workspace \"\u002Fpath\u002Fto\u002Fworkspace\" \\\n  --discord-channel \"1234567890\"  # Optional\n```\n\nThe script automatically:\n- ✅ Creates workspace with memory subdirectory\n- ✅ Generates SOUL.md and HEARTBEAT.md\n- ✅ Updates gateway config (preserves existing agents)\n- ✅ Adds Discord channel binding (if specified)\n- ✅ Restarts gateway to apply changes\n- ✅ Prompts for daily memory cron setup\n\n#### 3. Customize Agent\n\nAfter creation:\n- **SOUL.md** - Refine personality, responsibilities, boundaries\n- **HEARTBEAT.md** - Add periodic checks and cron logic\n- **Workspace files** - Add agent-specific configuration\n\n### Agent Architecture\n\n**Self-contained structure:**\n```\nagents\u002F\n├── watson\u002F\n│   ├── SOUL.md              # Personality and responsibilities\n│   ├── HEARTBEAT.md         # Cron execution logic\n│   ├── memory\u002F              # Agent-specific memory\n│   │   ├── 2026-02-01.md   # Daily memory logs\n│   │   └── 2026-02-02.md\n│   └── .openclaw\u002F\n│       └── skills\u002F          # Agent-specific skills (optional)\n```\n\n**Memory system:**\n- Agent-specific memory: `\u003Cworkspace>\u002Fmemory\u002FYYYY-MM-DD.md`\n- Shared memory access: Agents can read shared workspace\n- Daily updates: Optional cron job for summaries\n\n**Cron jobs:**\nIf your agent needs scheduled tasks:\n1. Create HEARTBEAT.md with execution logic\n2. Add cron jobs with `--session \u003Cagent-id>`\n3. Document in SOUL.md\n\n### Examples\n\n**Research agent:**\n```bash\nscripts\u002Fcreate-agent.sh \\\n  --name \"Watson\" \\\n  --id \"watson\" \\\n  --emoji \"?\" \\\n  --specialty \"Deep research and competitive analysis\" \\\n  --model \"anthropic\u002Fclaude-opus-4-5\" \\\n  --workspace \"$HOME\u002Fagents\u002Fwatson\" \\\n  --discord-channel \"1234567890\"\n```\n\n**Image generation agent:**\n```bash\nscripts\u002Fcreate-agent.sh \\\n  --name \"Picasso\" \\\n  --id \"picasso\" \\\n  --emoji \"?\" \\\n  --specialty \"Image generation and editing specialist\" \\\n  --model \"google\u002Fgemini-3-flash-preview\" \\\n  --workspace \"$HOME\u002Fagents\u002Fpicasso\" \\\n  --discord-channel \"9876543210\"\n```\n\n**Health tracking agent:**\n```bash\nscripts\u002Fcreate-agent.sh \\\n  --name \"Nurse Joy\" \\\n  --id \"nurse-joy\" \\\n  --emoji \"?\" \\\n  --specialty \"Health tracking and wellness monitoring\" \\\n  --model \"anthropic\u002Fclaude-opus-4-5\" \\\n  --workspace \"$HOME\u002Fagents\u002Fnurse-joy\" \\\n  --discord-channel \"5555555555\"\n```\n\n## Part 2: Discord Channel Management\n\n### Channel Creation\n\n#### Quick Start\n\n```bash\npython3 scripts\u002Fsetup-channel.py \\\n  --name research \\\n  --context \"Deep research and competitive analysis\"\n```\n\n#### Workflow\n\n1. Run setup script:\n```bash\npython3 scripts\u002Fsetup-channel.py \\\n  --name \u003Cchannel-name> \\\n  --context \"\u003Cchannel-purpose>\" \\\n  [--category-id \u003Cdiscord-category-id>]\n```\n\n2. Apply gateway config (command shown by script):\n```bash\nopenclaw gateway config.patch --raw '{\"channels\": {...}}'\n```\n\n#### Options\n\n**With category:**\n```bash\npython3 scripts\u002Fsetup-channel.py \\\n  --name research \\\n  --context \"Deep research and competitive analysis\" \\\n  --category-id \"1234567890\"\n```\n\n**Use existing channel:**\n```bash\npython3 scripts\u002Fsetup-channel.py \\\n  --name personal-finance \\\n  --id 1466184336901537897 \\\n  --context \"Personal finance management\"\n```\n\n### Channel Renaming\n\n#### Quick Start\n\n```bash\npython3 scripts\u002Frename-channel.py \\\n  --id 1234567890 \\\n  --old-name old-name \\\n  --new-name new-name\n```\n\n#### Workflow\n\n1. Run rename script:\n```bash\npython3 scripts\u002Frename-channel.py \\\n  --id \u003Cchannel-id> \\\n  --old-name \u003Cold-name> \\\n  --new-name \u003Cnew-name> \\\n  [--workspace \u003Cworkspace-dir>]\n```\n\n2. Apply gateway config if systemPrompt needs updating (shown by script)\n\n3. Commit workspace file changes (if `--workspace` used)\n\n#### With Workspace Search\n\n```bash\npython3 scripts\u002Frename-channel.py \\\n  --id 1234567890 \\\n  --old-name old-name \\\n  --new-name new-name \\\n  --workspace \"$HOME\u002Fmy-workspace\"\n```\n\nThis will:\n- Rename Discord channel via API\n- Update gateway config systemPrompt\n- Search and update workspace files\n- Report files changed for git commit\n\n## Complete Multi-Agent Setup\n\n**Full workflow from scratch:**\n\n```bash\n# 1. Create Discord channel\npython3 scripts\u002Fsetup-channel.py \\\n  --name research \\\n  --context \"Deep research and competitive analysis\" \\\n  --category-id \"1234567890\"\n\n# (Note the channel ID from output)\n\n# 2. Apply gateway config for channel\nopenclaw gateway config.patch --raw '{\"channels\": {...}}'\n\n# 3. Create agent bound to that channel\nscripts\u002Fcreate-agent.sh \\\n  --name \"Watson\" \\\n  --id \"watson\" \\\n  --emoji \"?\" \\\n  --specialty \"Deep research and competitive analysis\" \\\n  --model \"anthropic\u002Fclaude-opus-4-5\" \\\n  --workspace \"$HOME\u002Fagents\u002Fwatson\" \\\n  --discord-channel \"1234567890\"\n\n# Done! Agent is created and bound to the channel\n```\n\n## Configuration\n\n### Discord Category ID\n\n**Option 1: Command line**\n```bash\npython3 scripts\u002Fsetup-channel.py \\\n  --name channel-name \\\n  --context \"Purpose\" \\\n  --category-id \"1234567890\"\n```\n\n**Option 2: Environment variable**\n```bash\nexport DISCORD_CATEGORY_ID=\"1234567890\"\npython3 scripts\u002Fsetup-channel.py --name channel-name --context \"Purpose\"\n```\n\n### Finding Discord IDs\n\n**Enable Developer Mode:**\n- Settings → Advanced → Developer Mode\n\n**Copy IDs:**\n- Right-click channel → Copy ID\n- Right-click category → Copy ID\n\n## Scripts Reference\n\n### create-agent.sh\n\n**Arguments:**\n- `--name` (required) - Agent name\n- `--id` (required) - Agent ID (lowercase, hyphenated)\n- `--emoji` (required) - Agent emoji\n- `--specialty` (required) - What the agent does\n- `--model` (required) - LLM to use (provider\u002Fmodel-name)\n- `--workspace` (required) - Where to create agent files\n- `--discord-channel` (optional) - Discord channel ID to bind\n\n**Output:**\n- Creates agent workspace\n- Generates SOUL.md and HEARTBEAT.md\n- Updates gateway config\n- Optionally creates daily memory cron\n\n### setup-channel.py\n\n**Arguments:**\n- `--name` (required) - Channel name\n- `--context` (required) - Channel purpose\u002Fcontext\n- `--id` (optional) - Existing channel ID\n- `--category-id` (optional) - Discord category ID\n\n**Output:**\n- Creates Discord channel (if doesn't exist)\n- Generates gateway config.patch command\n\n### rename-channel.py\n\n**Arguments:**\n- `--id` (required) - Channel ID\n- `--old-name` (required) - Current channel name\n- `--new-name` (required) - New channel name\n- `--workspace` (optional) - Workspace directory to search\n\n**Output:**\n- Renames Discord channel\n- Updates gateway systemPrompt (if needed)\n- Lists updated files (if workspace search enabled)\n\n## Gateway Integration\n\nThis skill integrates with OpenClaw's gateway configuration:\n\n**Agents:**\n```json\n{\n  \"agents\": {\n    \"list\": [\n      {\n        \"id\": \"watson\",\n        \"name\": \"Watson\",\n        \"workspace\": \"\u002Fpath\u002Fto\u002Fagents\u002Fwatson\",\n        \"model\": {\n          \"primary\": \"anthropic\u002Fclaude-opus-4-5\"\n        },\n        \"identity\": {\n          \"name\": \"Watson\",\n          \"emoji\": \"?\"\n        }\n      }\n    ]\n  }\n}\n```\n\n**Bindings:**\n```json\n{\n  \"bindings\": [\n    {\n      \"agentId\": \"watson\",\n      \"match\": {\n        \"channel\": \"discord\",\n        \"peer\": {\n          \"kind\": \"channel\",\n          \"id\": \"1234567890\"\n        }\n      }\n    }\n  ]\n}\n```\n\n**Channels:**\n```json\n{\n  \"channels\": {\n    \"discord\": {\n      \"guilds\": {\n        \"YOUR_GUILD_ID\": {\n          \"channels\": {\n            \"1234567890\": {\n              \"allow\": true,\n              \"requireMention\": false,\n              \"systemPrompt\": \"Deep research and competitive analysis\"\n            }\n          }\n        }\n      }\n    }\n  }\n}\n```\n\n## Agent Coordination\n\nYour main agent coordinates with specialized agents using OpenClaw's built-in session management tools.\n\n### List Active Agents\n\nSee all active agents and their recent activity:\n\n```typescript\nsessions_list({\n  kinds: [\"agent\"],\n  limit: 10,\n  messageLimit: 3  \u002F\u002F Show last 3 messages per agent\n})\n```\n\n### Send Messages to Agents\n\n**Direct communication:**\n```typescript\nsessions_send({\n  label: \"watson\",  \u002F\u002F Agent ID\n  message: \"Research the competitive landscape for X\"\n})\n```\n\n**Wait for response:**\n```typescript\nsessions_send({\n  label: \"watson\",\n  message: \"What did you find about X?\",\n  timeoutSeconds: 300  \u002F\u002F Wait up to 5 minutes\n})\n```\n\n### Spawn Sub-Agent Tasks\n\nFor complex work, spawn a sub-agent in an isolated session:\n\n```typescript\nsessions_spawn({\n  agentId: \"watson\",  \u002F\u002F Optional: use specific agent\n  task: \"Research competitive landscape for X and write a report\",\n  model: \"anthropic\u002Fclaude-opus-4-5\",  \u002F\u002F Optional: override model\n  runTimeoutSeconds: 3600,  \u002F\u002F 1 hour max\n  cleanup: \"delete\"  \u002F\u002F Delete session after completion\n})\n```\n\nThe sub-agent will:\n1. Execute the task in isolation\n2. Announce completion back to your session\n3. Self-delete (if `cleanup: \"delete\"`)\n\n### Check Agent History\n\nReview what an agent has been working on:\n\n```typescript\nsessions_history({\n  sessionKey: \"watson-session-key\",\n  limit: 50\n})\n```\n\n### Coordination Patterns\n\n**1. Direct delegation (Discord-bound agents):**\n- User messages agent's Discord channel\n- Agent responds directly in that channel\n- Main agent doesn't need to coordinate\n\n**2. Programmatic delegation (main agent → sub-agent):**\n```typescript\n\u002F\u002F Main agent delegates task\nsessions_send({\n  label: \"watson\",\n  message: \"Research X and update memory\u002Fresearch-X.md\"\n})\n\n\u002F\u002F Watson works independently, updates files\n\u002F\u002F Main agent checks later or Watson reports back\n```\n\n**3. Spawn for complex tasks:**\n```typescript\n\u002F\u002F For longer-running, isolated work\nsessions_spawn({\n  agentId: \"watson\",\n  task: \"Deep dive: analyze competitors A, B, C. Write report to reports\u002Fcompetitors.md\",\n  runTimeoutSeconds: 7200,\n  cleanup: \"keep\"  \u002F\u002F Keep session for review\n})\n```\n\n**4. Agent-to-agent communication:**\nAgents can send messages to each other:\n```typescript\n\u002F\u002F In Watson's context\nsessions_send({\n  label: \"picasso\",\n  message: \"Create an infographic from data in reports\u002Fresearch.md\"\n})\n```\n\n### Best Practices\n\n**When to use Discord bindings:**\n- ✅ Domain-specific agents (research, health, images)\n- ✅ User wants direct access to agent\n- ✅ Agent should respond to channel activity\n\n**When to use sessions_send:**\n- ✅ Programmatic coordination\n- ✅ Main agent delegates to specialists\n- ✅ Need response in same session\n\n**When to use sessions_spawn:**\n- ✅ Long-running tasks (>5 minutes)\n- ✅ Complex multi-step work\n- ✅ Want isolation from main session\n- ✅ Background processing\n\n### Example: Research Workflow\n\n```typescript\n\u002F\u002F Main agent receives request: \"Research competitor X\"\n\n\u002F\u002F 1. Check if Watson is active\nconst agents = sessions_list({ kinds: [\"agent\"] })\n\n\u002F\u002F 2. Delegate to Watson\nsessions_send({\n  label: \"watson\",\n  message: \"Research competitor X: products, pricing, market position. Write findings to memory\u002Fresearch-X.md\"\n})\n\n\u002F\u002F 3. Watson works independently:\n\u002F\u002F    - Searches web\n\u002F\u002F    - Analyzes data\n\u002F\u002F    - Updates memory file\n\u002F\u002F    - Reports back when done\n\n\u002F\u002F 4. Main agent retrieves results\nconst results = Read(\"agents\u002Fwatson\u002Fmemory\u002Fresearch-X.md\")\n\n\u002F\u002F 5. Share with user\n\"Research complete! Watson found: [summary]\"\n```\n\n### Communication Flow\n\n**Main Agent (You) ↔ Specialized Agents:**\n\n```\nUser Request\n    ↓\nMain Agent (Claire)\n    ↓\nsessions_send(\"watson\", \"Research X\")\n    ↓\nWatson Agent\n    ↓\n- Uses web_search\n- Uses web_fetch\n- Updates memory files\n    ↓\nResponds to main session\n    ↓\nMain Agent synthesizes and replies\n```\n\n**Discord-Bound Agents:**\n\n```\nUser posts in #research channel\n    ↓\nWatson Agent (bound to channel)\n    ↓\n- Sees message directly\n- Responds in channel\n- No main agent involvement\n```\n\n**Hybrid Approach:**\n\n```\nUser: \"Research X\" (main channel)\n    ↓\nMain Agent delegates to Watson\n    ↓\nWatson researches and reports back\n    ↓\nMain Agent: \"Done! Watson found...\"\n    ↓\nUser: \"Show me more details\"\n    ↓\nMain Agent: \"@watson post your full findings in #research\"\n    ↓\nWatson posts detailed report in #research channel\n```\n\n## Troubleshooting\n\n**Agent Creation Issues:**\n\n**\"Agent not appearing in Discord\"**\n- Verify channel ID is correct\n- Check gateway config bindings section\n- Restart gateway: `openclaw gateway restart`\n\n**\"Model errors\"**\n- Verify model name format: `provider\u002Fmodel-name`\n- Check model is available in gateway config\n\n**Channel Management Issues:**\n\n**\"Failed to create channel\"**\n- Check bot has \"Manage Channels\" permission\n- Verify bot token in OpenClaw config\n- Ensure category ID is correct (if specified)\n\n**\"Category not found\"**\n- Verify category ID is correct\n- Check bot has access to category\n- Try without category ID (creates uncategorized)\n\n**\"Channel already exists\"**\n- Use `--id \u003Cchannel-id>` to configure existing channel\n- Or script will auto-detect and configure it\n\n## Use Cases\n\n- **Domain specialists** - Research, health, finance, coding agents\n- **Creative agents** - Image generation, writing, design\n- **Task automation** - Scheduled monitoring, reports, alerts\n- **Multi-agent systems** - Coordinated team of specialized agents\n- **Discord organization** - Structured channels for different agent domains\n\n## Advanced: Multi-Agent Coordination\n\nFor larger multi-agent systems:\n\n**Coordination Patterns:**\n- Main agent delegates tasks to specialists\n- Agents report progress and request help\n- Shared knowledge base for common information\n- Cross-agent communication via `sessions_send`\n\n**Task Management:**\n- Integrate with task tracking systems\n- Route work based on agent specialty\n- Track assignments and completions\n\n**Documentation:**\n- Maintain agent roster in main workspace\n- Document delegation patterns\n- Keep runbooks for common workflows\n\n## Best Practices\n\n1. **Organize channels in categories** - Group related agent channels\n2. **Use descriptive channel names** - Clear purpose from the name\n3. **Set specific system prompts** - Give each channel clear context\n4. **Document agent responsibilities** - Keep SOUL.md updated\n5. **Set up memory cron jobs** - For agents with ongoing work\n6. **Test agents individually** - Before integrating into team\n7. **Update gateway config safely** - Always use config.patch, never manual edits\n\n## Requirements\n\n**Bot Permissions:**\n- `Manage Channels` - To create\u002Frename channels\n- `View Channels` - To read channel list\n- `Send Messages` - To post in channels\n\n**System:**\n- OpenClaw installed and configured\n- Node.js\u002Fnpm via nvm\n- Python 3.6+ (standard library only)\n- Discord bot token (for channel management)\n\n## See Also\n\n- OpenClaw documentation: https:\u002F\u002Fdocs.openclaw.ai\n- Multi-agent patterns: https:\u002F\u002Fdocs.openclaw.ai\u002Fagents\n- Discord bot setup: https:\u002F\u002Fdocs.openclaw.ai\u002Fchannels\u002Fdiscord\n","# Agent Council\n\nComplete toolkit for creating and managing autonomous AI agents with Discord integration for OpenClaw.\n\n## What This Skill Does\n\n**Agent Creation:**\n- Creates autonomous AI agents with self-contained workspaces\n- Generates SOUL.md (personality & responsibilities)\n- Generates HEARTBEAT.md (cron execution logic)\n- Sets up memory system (hybrid architecture)\n- Configures gateway automatically\n- Binds agents to Discord channels (optional)\n- Sets up daily memory cron jobs (optional)\n\n**Discord Channel Management:**\n- Creates Discord channels via API\n- Configures OpenClaw gateway allowlists\n- Sets channel-specific system prompts\n- Renames channels and updates references\n- Optional workspace file search\n\n## Installation\n\n```bash\n# Install from ClawHub\nclawhub install agent-council\n\n# Or manual install\ncp -r . ~\u002F.openclaw\u002Fskills\u002Fagent-council\u002F\nopenclaw gateway config.patch --raw '{\n  \"skills\": {\n    \"entries\": {\n      \"agent-council\": {\"enabled\": true}\n    }\n  }\n}'\n```\n\n## Part 1: Agent Creation\n\n### Quick Start\n\n```bash\nscripts\u002Fcreate-agent.sh \\\n  --name \"Watson\" \\\n  --id \"watson\" \\\n  --emoji \"?\" \\\n  --specialty \"Research and analysis specialist\" \\\n  --model \"anthropic\u002Fclaude-opus-4-5\" \\\n  --workspace \"$HOME\u002Fagents\u002Fwatson\" \\\n  --discord-channel \"1234567890\"\n```\n\n### Workflow\n\n#### 1. Gather Requirements\n\nAsk the user:\n- **Agent name** (e.g., \"Watson\")\n- **Agent ID** (lowercase, hyphenated, e.g., \"watson\")\n- **Emoji** (e.g., \"?\")\n- **Specialty** (what the agent does)\n- **Model** (which LLM to use)\n- **Workspace** (where to create agent files)\n- **Discord channel ID** (optional)\n\n#### 2. Run Creation Script\n\n```bash\nscripts\u002Fcreate-agent.sh \\\n  --name \"Agent Name\" \\\n  --id \"agent-id\" \\\n  --emoji \"?\" \\\n  --specialty \"What this agent does\" \\\n  --model \"provider\u002Fmodel-name\" \\\n  --workspace \"\u002Fpath\u002Fto\u002Fworkspace\" \\\n  --discord-channel \"1234567890\"  # Optional\n```\n\nThe script automatically:\n- ✅ Creates workspace with memory subdirectory\n- ✅ Generates SOUL.md and HEARTBEAT.md\n- ✅ Updates gateway config (preserves existing agents)\n- ✅ Adds Discord channel binding (if specified)\n- ✅ Restarts gateway to apply changes\n- ✅ Prompts for daily memory cron setup\n\n#### 3. Customize Agent\n\nAfter creation:\n- **SOUL.md** - Refine personality, responsibilities, boundaries\n- **HEARTBEAT.md** - Add periodic checks and cron logic\n- **Workspace files** - Add agent-specific configuration\n\n### Agent Architecture\n\n**Self-contained structure:**\n```\nagents\u002F\n├── watson\u002F\n│   ├── SOUL.md              # Personality and responsibilities\n│   ├── HEARTBEAT.md         # Cron execution logic\n│   ├── memory\u002F              # Agent-specific memory\n│   │   ├── 2026-02-01.md   # Daily memory logs\n│   │   └── 2026-02-02.md\n│   └── .openclaw\u002F\n│       └── skills\u002F          # Agent-specific skills (optional)\n```\n\n**Memory system:**\n- Agent-specific memory: `\u003Cworkspace>\u002Fmemory\u002FYYYY-MM-DD.md`\n- Shared memory access: Agents can read shared workspace\n- Daily updates: Optional cron job for summaries\n\n**Cron jobs:**\nIf your agent needs scheduled tasks:\n1. Create HEARTBEAT.md with execution logic\n2. Add cron jobs with `--session \u003Cagent-id>`\n3. Document in SOUL.md\n\n### Examples\n\n**Research agent:**\n```bash\nscripts\u002Fcreate-agent.sh \\\n  --name \"Watson\" \\\n  --id \"watson\" \\\n  --emoji \"?\" \\\n  --specialty \"Deep research and competitive analysis\" \\\n  --model \"anthropic\u002Fclaude-opus-4-5\" \\\n  --workspace \"$HOME\u002Fagents\u002Fwatson\" \\\n  --discord-channel \"1234567890\"\n```\n\n**Image generation agent:**\n```bash\nscripts\u002Fcreate-agent.sh \\\n  --name \"Picasso\" \\\n  --id \"picasso\" \\\n  --emoji \"?\" \\\n  --specialty \"Image generation and editing specialist\" \\\n  --model \"google\u002Fgemini-3-flash-preview\" \\\n  --workspace \"$HOME\u002Fagents\u002Fpicasso\" \\\n  --discord-channel \"9876543210\"\n```\n\n**Health tracking agent:**\n```bash\nscripts\u002Fcreate-agent.sh \\\n  --name \"Nurse Joy\" \\\n  --id \"nurse-joy\" \\\n  --emoji \"?\" \\\n  --specialty \"Health tracking and wellness monitoring\" \\\n  --model \"anthropic\u002Fclaude-opus-4-5\" \\\n  --workspace \"$HOME\u002Fagents\u002Fnurse-joy\" \\\n  --discord-channel \"5555555555\"\n```\n\n## Part 2: Discord Channel Management\n\n### Channel Creation\n\n#### Quick Start\n\n```bash\npython3 scripts\u002Fsetup-channel.py \\\n  --name research \\\n  --context \"Deep research and competitive analysis\"\n```\n\n#### Workflow\n\n1. Run setup script:\n```bash\npython3 scripts\u002Fsetup-channel.py \\\n  --name \u003Cchannel-name> \\\n  --context \"\u003Cchannel-purpose>\" \\\n  [--category-id \u003Cdiscord-category-id>]\n```\n\n2. Apply gateway config (command shown by script):\n```bash\nopenclaw gateway config.patch --raw '{\"channels\": {...}}'\n```\n\n#### Options\n\n**With category:**\n```bash\npython3 scripts\u002Fsetup-channel.py \\\n  --name research \\\n  --context \"Deep research and competitive analysis\" \\\n  --category-id \"1234567890\"\n```\n\n**Use existing channel:**\n```bash\npython3 scripts\u002Fsetup-channel.py \\\n  --name personal-finance \\\n  --id 1466184336901537897 \\\n  --context \"Personal finance management\"\n```\n\n### Channel Renaming\n\n#### Quick Start\n\n```bash\npython3 scripts\u002Frename-channel.py \\\n  --id 1234567890 \\\n  --old-name old-name \\\n  --new-name new-name\n```\n\n#### Workflow\n\n1. Run rename script:\n```bash\npython3 scripts\u002Frename-channel.py \\\n  --id \u003Cchannel-id> \\\n  --old-name \u003Cold-name> \\\n  --new-name \u003Cnew-name> \\\n  [--workspace \u003Cworkspace-dir>]\n```\n\n2. Apply gateway config if systemPrompt needs updating (shown by script)\n\n3. Commit workspace file changes (if `--workspace` used)\n\n#### With Workspace Search\n\n```bash\npython3 scripts\u002Frename-channel.py \\\n  --id 1234567890 \\\n  --old-name old-name \\\n  --new-name new-name \\\n  --workspace \"$HOME\u002Fmy-workspace\"\n```\n\nThis will:\n- Rename Discord channel via API\n- Update gateway config systemPrompt\n- Search and update workspace files\n- Report files changed for git commit\n\n## Complete Multi-Agent Setup\n\n**Full workflow from scratch:**\n\n```bash\n# 1. Create Discord channel\npython3 scripts\u002Fsetup-channel.py \\\n  --name research \\\n  --context \"Deep research and competitive analysis\" \\\n  --category-id \"1234567890\"\n\n# (Note the channel ID from output)\n\n# 2. Apply gateway config for channel\nopenclaw gateway config.patch --raw '{\"channels\": {...}}'\n\n# 3. Create agent bound to that channel\nscripts\u002Fcreate-agent.sh \\\n  --name \"Watson\" \\\n  --id \"watson\" \\\n  --emoji \"?\" \\\n  --specialty \"Deep research and competitive analysis\" \\\n  --model \"anthropic\u002Fclaude-opus-4-5\" \\\n  --workspace \"$HOME\u002Fagents\u002Fwatson\" \\\n  --discord-channel \"1234567890\"\n\n# Done! Agent is created and bound to the channel\n```\n\n## Configuration\n\n### Discord Category ID\n\n**Option 1: Command line**\n```bash\npython3 scripts\u002Fsetup-channel.py \\\n  --name channel-name \\\n  --context \"Purpose\" \\\n  --category-id \"1234567890\"\n```\n\n**Option 2: Environment variable**\n```bash\nexport DISCORD_CATEGORY_ID=\"1234567890\"\npython3 scripts\u002Fsetup-channel.py --name channel-name --context \"Purpose\"\n```\n\n### Finding Discord IDs\n\n**Enable Developer Mode:**\n- Settings → Advanced → Developer Mode\n\n**Copy IDs:**\n- Right-click channel → Copy ID\n- Right-click category → Copy ID\n\n## Scripts Reference\n\n### create-agent.sh\n\n**Arguments:**\n- `--name` (required) - Agent name\n- `--id` (required) - Agent ID (lowercase, hyphenated)\n- `--emoji` (required) - Agent emoji\n- `--specialty` (required) - What the agent does\n- `--model` (required) - LLM to use (provider\u002Fmodel-name)\n- `--workspace` (required) - Where to create agent files\n- `--discord-channel` (optional) - Discord channel ID to bind\n\n**Output:**\n- Creates agent workspace\n- Generates SOUL.md and HEARTBEAT.md\n- Updates gateway config\n- Optionally creates daily memory cron\n\n### setup-channel.py\n\n**Arguments:**\n- `--name` (required) - Channel name\n- `--context` (required) - Channel purpose\u002Fcontext\n- `--id` (optional) - Existing channel ID\n- `--category-id` (optional) - Discord category ID\n\n**Output:**\n- Creates Discord channel (if doesn't exist)\n- Generates gateway config.patch command\n\n### rename-channel.py\n\n**Arguments:**\n- `--id` (required) - Channel ID\n- `--old-name` (required) - Current channel name\n- `--new-name` (required) - New channel name\n- `--workspace` (optional) - Workspace directory to search\n\n**Output:**\n- Renames Discord channel\n- Updates gateway systemPrompt (if needed)\n- Lists updated files (if workspace search enabled)\n\n## Gateway Integration\n\nThis skill integrates with OpenClaw's gateway configuration:\n\n**Agents:**\n```json\n{\n  \"agents\": {\n    \"list\": [\n      {\n        \"id\": \"watson\",\n        \"name\": \"Watson\",\n        \"workspace\": \"\u002Fpath\u002Fto\u002Fagents\u002Fwatson\",\n        \"model\": {\n          \"primary\": \"anthropic\u002Fclaude-opus-4-5\"\n        },\n        \"identity\": {\n          \"name\": \"Watson\",\n          \"emoji\": \"?\"\n        }\n      }\n    ]\n  }\n}\n```\n\n**Bindings:**\n```json\n{\n  \"bindings\": [\n    {\n      \"agentId\": \"watson\",\n      \"match\": {\n        \"channel\": \"discord\",\n        \"peer\": {\n          \"kind\": \"channel\",\n          \"id\": \"1234567890\"\n        }\n      }\n    }\n  ]\n}\n```\n\n**Channels:**\n```json\n{\n  \"channels\": {\n    \"discord\": {\n      \"guilds\": {\n        \"YOUR_GUILD_ID\": {\n          \"channels\": {\n            \"1234567890\": {\n              \"allow\": true,\n              \"requireMention\": false,\n              \"systemPrompt\": \"Deep research and competitive analysis\"\n            }\n          }\n        }\n      }\n    }\n  }\n}\n```\n\n## Agent Coordination\n\nYour main agent coordinates with specialized agents using OpenClaw's built-in session management tools.\n\n### List Active Agents\n\nSee all active agents and their recent activity:\n\n```typescript\nsessions_list({\n  kinds: [\"agent\"],\n  limit: 10,\n  messageLimit: 3  \u002F\u002F Show last 3 messages per agent\n})\n```\n\n### Send Messages to Agents\n\n**Direct communication:**\n```typescript\nsessions_send({\n  label: \"watson\",  \u002F\u002F Agent ID\n  message: \"Research the competitive landscape for X\"\n})\n```\n\n**Wait for response:**\n```typescript\nsessions_send({\n  label: \"watson\",\n  message: \"What did you find about X?\",\n  timeoutSeconds: 300  \u002F\u002F Wait up to 5 minutes\n})\n```\n\n### Spawn Sub-Agent Tasks\n\nFor complex work, spawn a sub-agent in an isolated session:\n\n```typescript\nsessions_spawn({\n  agentId: \"watson\",  \u002F\u002F Optional: use specific agent\n  task: \"Research competitive landscape for X and write a report\",\n  model: \"anthropic\u002Fclaude-opus-4-5\",  \u002F\u002F Optional: override model\n  runTimeoutSeconds: 3600,  \u002F\u002F 1 hour max\n  cleanup: \"delete\"  \u002F\u002F Delete session after completion\n})\n```\n\nThe sub-agent will:\n1. Execute the task in isolation\n2. Announce completion back to your session\n3. Self-delete (if `cleanup: \"delete\"`)\n\n### Check Agent History\n\nReview what an agent has been working on:\n\n```typescript\nsessions_history({\n  sessionKey: \"watson-session-key\",\n  limit: 50\n})\n```\n\n### Coordination Patterns\n\n**1. Direct delegation (Discord-bound agents):**\n- User messages agent's Discord channel\n- Agent responds directly in that channel\n- Main agent doesn't need to coordinate\n\n**2. Programmatic delegation (main agent → sub-agent):**\n```typescript\n\u002F\u002F Main agent delegates task\nsessions_send({\n  label: \"watson\",\n  message: \"Research X and update memory\u002Fresearch-X.md\"\n})\n\n\u002F\u002F Watson works independently, updates files\n\u002F\u002F Main agent checks later or Watson reports back\n```\n\n**3. Spawn for complex tasks:**\n```typescript\n\u002F\u002F For longer-running, isolated work\nsessions_spawn({\n  agentId: \"watson\",\n  task: \"Deep dive: analyze competitors A, B, C. Write report to reports\u002Fcompetitors.md\",\n  runTimeoutSeconds: 7200,\n  cleanup: \"keep\"  \u002F\u002F Keep session for review\n})\n```\n\n**4. Agent-to-agent communication:**\nAgents can send messages to each other:\n```typescript\n\u002F\u002F In Watson's context\nsessions_send({\n  label: \"picasso\",\n  message: \"Create an infographic from data in reports\u002Fresearch.md\"\n})\n```\n\n### Best Practices\n\n**When to use Discord bindings:**\n- ✅ Domain-specific agents (research, health, images)\n- ✅ User wants direct access to agent\n- ✅ Agent should respond to channel activity\n\n**When to use sessions_send:**\n- ✅ Programmatic coordination\n- ✅ Main agent delegates to specialists\n- ✅ Need response in same session\n\n**When to use sessions_spawn:**\n- ✅ Long-running tasks (>5 minutes)\n- ✅ Complex multi-step work\n- ✅ Want isolation from main session\n- ✅ Background processing\n\n### Example: Research Workflow\n\n```typescript\n\u002F\u002F Main agent receives request: \"Research competitor X\"\n\n\u002F\u002F 1. Check if Watson is active\nconst agents = sessions_list({ kinds: [\"agent\"] })\n\n\u002F\u002F 2. Delegate to Watson\nsessions_send({\n  label: \"watson\",\n  message: \"Research competitor X: products, pricing, market position. Write findings to memory\u002Fresearch-X.md\"\n})\n\n\u002F\u002F 3. Watson works independently:\n\u002F\u002F    - Searches web\n\u002F\u002F    - Analyzes data\n\u002F\u002F    - Updates memory file\n\u002F\u002F    - Reports back when done\n\n\u002F\u002F 4. Main agent retrieves results\nconst results = Read(\"agents\u002Fwatson\u002Fmemory\u002Fresearch-X.md\")\n\n\u002F\u002F 5. Share with user\n\"Research complete! Watson found: [summary]\"\n```\n\n### Communication Flow\n\n**Main Agent (You) ↔ Specialized Agents:**\n\n```\nUser Request\n    ↓\nMain Agent (Claire)\n    ↓\nsessions_send(\"watson\", \"Research X\")\n    ↓\nWatson Agent\n    ↓\n- Uses web_search\n- Uses web_fetch\n- Updates memory files\n    ↓\nResponds to main session\n    ↓\nMain Agent synthesizes and replies\n```\n\n**Discord-Bound Agents:**\n\n```\nUser posts in #research channel\n    ↓\nWatson Agent (bound to channel)\n    ↓\n- Sees message directly\n- Responds in channel\n- No main agent involvement\n```\n\n**Hybrid Approach:**\n\n```\nUser: \"Research X\" (main channel)\n    ↓\nMain Agent delegates to Watson\n    ↓\nWatson researches and reports back\n    ↓\nMain Agent: \"Done! Watson found...\"\n    ↓\nUser: \"Show me more details\"\n    ↓\nMain Agent: \"@watson post your full findings in #research\"\n    ↓\nWatson posts detailed report in #research channel\n```\n\n## Troubleshooting\n\n**Agent Creation Issues:**\n\n**\"Agent not appearing in Discord\"**\n- Verify channel ID is correct\n- Check gateway config bindings section\n- Restart gateway: `openclaw gateway restart`\n\n**\"Model errors\"**\n- Verify model name format: `provider\u002Fmodel-name`\n- Check model is available in gateway config\n\n**Channel Management Issues:**\n\n**\"Failed to create channel\"**\n- Check bot has \"Manage Channels\" permission\n- Verify bot token in OpenClaw config\n- Ensure category ID is correct (if specified)\n\n**\"Category not found\"**\n- Verify category ID is correct\n- Check bot has access to category\n- Try without category ID (creates uncategorized)\n\n**\"Channel already exists\"**\n- Use `--id \u003Cchannel-id>` to configure existing channel\n- Or script will auto-detect and configure it\n\n## Use Cases\n\n- **Domain specialists** - Research, health, finance, coding agents\n- **Creative agents** - Image generation, writing, design\n- **Task automation** - Scheduled monitoring, reports, alerts\n- **Multi-agent systems** - Coordinated team of specialized agents\n- **Discord organization** - Structured channels for different agent domains\n\n## Advanced: Multi-Agent Coordination\n\nFor larger multi-agent systems:\n\n**Coordination Patterns:**\n- Main agent delegates tasks to specialists\n- Agents report progress and request help\n- Shared knowledge base for common information\n- Cross-agent communication via `sessions_send`\n\n**Task Management:**\n- Integrate with task tracking systems\n- Route work based on agent specialty\n- Track assignments and completions\n\n**Documentation:**\n- Maintain agent roster in main workspace\n- Document delegation patterns\n- Keep runbooks for common workflows\n\n## Best Practices\n\n1. **Organize channels in categories** - Group related agent channels\n2. **Use descriptive channel names** - Clear purpose from the name\n3. **Set specific system prompts** - Give each channel clear context\n4. **Document agent responsibilities** - Keep SOUL.md updated\n5. **Set up memory cron jobs** - For agents with ongoing work\n6. **Test agents individually** - Before integrating into team\n7. **Update gateway config safely** - Always use config.patch, never manual edits\n\n## Requirements\n\n**Bot Permissions:**\n- `Manage Channels` - To create\u002Frename channels\n- `View Channels` - To read channel list\n- `Send Messages` - To post in channels\n\n**System:**\n- OpenClaw installed and configured\n- Node.js\u002Fnpm via nvm\n- Python 3.6+ (standard library only)\n- Discord bot token (for channel management)\n\n## See Also\n\n- OpenClaw documentation: https:\u002F\u002Fdocs.openclaw.ai\n- Multi-agent patterns: https:\u002F\u002Fdocs.openclaw.ai\u002Fagents\n- Discord bot setup: https:\u002F\u002Fdocs.openclaw.ai\u002Fchannels\u002Fdiscord\n",{"name":5,"description":7},"main","e7e336ac628c3e3bd771aff1aaa469c93778f94a","skills\u002Fitsahedge\u002Fagent-council",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":53,"prompt":63,"zipAvailable":64},[54,57,60],{"tool":55,"command":56},"npx","npx skills add kbarbel640-del\u002Fskills --skill agent-council",{"tool":58,"command":59},"bunx","bunx skills add kbarbel640-del\u002Fskills --skill agent-council",{"tool":61,"command":62},"pnpm","pnpm dlx skills add kbarbel640-del\u002Fskills --skill agent-council","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fitsahedge\u002Fagent-council\u002FSKILL.md",true,[66,72,76,82,86],{"path":67,"resourceType":68,"resourceTypeDesc":69,"sizeBytes":70,"sourceHtmlUrl":71},"_meta.json","REFERENCE","参考文档",281,"https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fitsahedge\u002Fagent-council\u002F_meta.json",{"path":73,"resourceType":68,"resourceTypeDesc":69,"sizeBytes":74,"sourceHtmlUrl":75},"README.md",13091,"https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fitsahedge\u002Fagent-council\u002FREADME.md",{"path":77,"resourceType":78,"resourceTypeDesc":79,"sizeBytes":80,"sourceHtmlUrl":81},"scripts\u002Fcreate-agent.sh","SCRIPT","脚本",8748,"https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fitsahedge\u002Fagent-council\u002Fscripts\u002Fcreate-agent.sh",{"path":83,"resourceType":78,"resourceTypeDesc":79,"sizeBytes":84,"sourceHtmlUrl":85},"scripts\u002Frename_channel.py",6791,"https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fitsahedge\u002Fagent-council\u002Fscripts\u002Frename_channel.py",{"path":87,"resourceType":78,"resourceTypeDesc":79,"sizeBytes":88,"sourceHtmlUrl":89},"scripts\u002Fsetup_channel.py",6130,"https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fitsahedge\u002Fagent-council\u002Fscripts\u002Fsetup_channel.py",[91,121,144,165,171,191],{"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":40},"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",[103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,38],"crowd prompting","prompting","api","with","tokens","domain","world","prompts","operations","instructions","text","tool","system","improve","productivity","marketplace","https","content",{"skillNo":122,"name":123,"nameZh":6,"description":124,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":125,"categories":126,"keywords":128,"publishedAt":40},"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",[127],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},[129,105,130,131,132,133,134,135,136,137,33,138,139,140,141,142,143,110,25],"dilemm ai","arena","analyze","browser","openclaw agent","create","automation","browser automation","bot","design","strategy","headless","compete","submit","matchmaking",{"skillNo":145,"name":146,"nameZh":6,"description":147,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":148,"categories":149,"keywords":153,"publishedAt":40},"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",[150],{"categoryNo":151,"categoryName":152,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000021","资料检索与研究",[154,155,156,157,158,159,160,106,161,142,25,162,105,163,164],"arxiv paper reviews","reviews","arxiv","paper","crawler","papers","comments","fetch","read","http","via",{"skillNo":166,"name":146,"nameZh":6,"description":147,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":167,"categories":168,"keywords":170,"publishedAt":40},"01M6G8HQJ7N7WMY6YV7D7SSJ16","https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fzxrys\u002Farxiv-paper-reviews\u002FSKILL.md",[169],{"categoryNo":151,"categoryName":152,"taxonomyType":20,"taxonomyTypeDesc":21},[157,156,155,154,164,159,160,106,158,142,25,161,162,105,163],{"skillNo":172,"name":173,"nameZh":6,"description":174,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":175,"categories":176,"keywords":177,"publishedAt":40},"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",[],[178,179,180,181,182,183,184,185,186,187,188,189,190],"git","summary","git summary","commits","repository","win32","status","linux","contributors","true","quick","get","branches",{"skillNo":192,"name":193,"nameZh":6,"description":194,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":195,"categories":196,"keywords":201,"publishedAt":40},"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",[197,198],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},{"categoryNo":199,"categoryName":200,"taxonomyType":100,"taxonomyTypeDesc":101},"01JBSEEDCAT000000000000037","律师与法务",[202,203,204,205,106,206,207,45,208,162,209,210,211,212,213,119,214,215,216],"agent constitution","constitution","contracts","tree","query","base","log","check","Rules","projects","compliance","actions","state","governance","github"]