{ "schemaVersion": "1.0", "item": { "slug": "god-mode-skill", "name": "God Mode Skill", "source": "tencent", "type": "skill", "category": "开发巄具", "sourceUrl": "https://clawhub.ai/wetzja04-dot/god-mode-skill", "canonicalUrl": "https://clawhub.ai/wetzja04-dot/god-mode-skill", "targetPlatform": "OpenClaw" }, "install": { "downloadMode": "redirect", "downloadUrl": "/downloads/god-mode-skill", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=god-mode-skill", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "installMethod": "Manual import", "extraction": "Extract archive", "prerequisites": [ "OpenClaw" ], "packageFormat": "ZIP package", "includedAssets": [ "CHANGELOG.md", "HANDOVER.md", "PUBLISH.md", "README.md", "SESSION-NOTES.md", "SKILL.md" ], "primaryDoc": "SKILL.md", "quickSetup": [ "Download the package from Yavira.", "Extract the archive and review SKILL.md first.", "Import or place the package into your OpenClaw setup." ], "agentAssist": { "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.", "steps": [ "Download the package from Yavira.", "Extract it into a folder your agent can access.", "Paste one of the prompts below and point your agent at the extracted folder." ], "prompts": [ { "label": "New install", "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Then review README.md for any prerequisites, environment setup, or post-install checks. Tell me what you changed and call out any manual steps you could not complete." }, { "label": "Upgrade existing", "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Then review README.md for any prerequisites, environment setup, or post-install checks. Summarize what changed and any follow-up checks I should run." } ] }, "sourceHealth": { "source": "tencent", "status": "healthy", "reason": "direct_download_ok", "recommendedAction": "download", "checkedAt": "2026-04-30T16:55:25.780Z", "expiresAt": "2026-05-07T16:55:25.780Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network", "contentDisposition": "attachment; filename=\"network-1.0.0.zip\"", "redirectLocation": null, "bodySnippet": null }, "scope": "source", "summary": "Source download looks usable.", "detail": "Yavira can redirect you to the upstream package for this source.", "primaryActionLabel": "Download for OpenClaw", "primaryActionHref": "/downloads/god-mode-skill" }, "validation": { "installChecklist": [ "Use the Yavira download entry.", "Review SKILL.md after the package is downloaded.", "Confirm the extracted package contains the expected setup assets." ], "postInstallChecks": [ "Confirm the extracted package includes the expected docs or setup files.", "Validate the skill or prompts are available in your target agent workspace.", "Capture any manual follow-up steps the agent could not complete." ] }, "downloadPageUrl": "https://openagent3.xyz/downloads/god-mode-skill", "agentPageUrl": "https://openagent3.xyz/skills/god-mode-skill/agent", "manifestUrl": "https://openagent3.xyz/skills/god-mode-skill/agent.json", "briefUrl": "https://openagent3.xyz/skills/god-mode-skill/agent.md" }, "agentAssist": { "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.", "steps": [ "Download the package from Yavira.", "Extract it into a folder your agent can access.", "Paste one of the prompts below and point your agent at the extracted folder." ], "prompts": [ { "label": "New install", "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Then review README.md for any prerequisites, environment setup, or post-install checks. Tell me what you changed and call out any manual steps you could not complete." }, { "label": "Upgrade existing", "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Then review README.md for any prerequisites, environment setup, or post-install checks. Summarize what changed and any follow-up checks I should run." } ] }, "documentation": { "source": "clawhub", "primaryDoc": "SKILL.md", "sections": [ { "title": "god-mode Skill", "body": "Conversational project oversight and AI agent coaching for OpenClaw." }, { "title": "Overview", "body": "god-mode lets users ask about their projects in plain English. You run the commands and explain the results conversationally.\n\nWhat users can ask:\n\n\"Set up god-mode for my repos\"\n\"What's happening across my projects?\"\n\"Which repos need attention?\"\n\"Analyze my agents.md\"\n\"What should I work on today?\"\n\nWhat you provide:\n\nMulti-project status summaries (GitHub + Azure DevOps)\nPlain-English explanations of commit activity, PRs, issues\nLLM-powered agent instruction analysis\nRecommendations for improving their AGENTS.md\n\nPerfect for:\n\nDevelopers juggling multiple repos who want conversational oversight\nTeams using AI coding assistants (Claude, Copilot, etc.)\nAnyone who wants data-driven improvements to their AGENTS.md" }, { "title": "For OpenClaw Users (Conversational)", "body": "Just tell me what you want! I'll run the god-mode commands for you.\n\nExample conversations:\n\nYou: \"Set up god-mode for my tada repository\"\nMe: Sure! I'll set up god-mode and add your tada repo.\n[runs god setup and god projects add github:YourUsername/tada]\nDone! Your repo is configured. Want me to sync the data?\n\nYou: \"Yes, and show me what's happening\"\nMe: [runs god sync and god status]\nHere's your overview:\n\ntada: 30 commits this week, last activity 3 days ago\n0 open PRs, 0 issues\n\nYour most active project! Commits are all features and bug fixes.\n\nYou: \"Analyze my agents.md for tada\"\nMe: [runs god agents analyze github:YourUsername/tada]\nI've analyzed your AGENTS.md against 155 commits. Here's what I found:\nGAPS:\n\nTesting practices (high impact) - 68 bug fixes but no testing guidance\nVoice API debugging - 12 commits mention \"voice\" but no troubleshooting\n\nSTRENGTHS:\n\nTypeScript strictness is working - zero type-related fixes\n\nWant me to add testing guidance to your AGENTS.md?\n\nWhat you can ask me:\n\n\"Set up god-mode for [repo]\"\n\"Show me all my projects\"\n\"What's happening across my repos?\"\n\"Analyze my agents.md\"\n\"Which repos need attention?\"\n\"What should I work on today?\"\n\nI'll handle all the commands and explain the results in plain English." }, { "title": "For CLI Users (Direct Commands)", "body": "If you prefer running commands yourself:\n\n# Setup\ngod setup\n\n# Add a project\ngod projects add github:username/repo\n\n# Sync and view\ngod sync\ngod status" }, { "title": "god status [project]", "body": "Show overview of all projects, or details for one:\n\ngod status # All projects\ngod status myproject # One project in detail" }, { "title": "god sync [project] [--force]", "body": "Fetch/update data from repositories:\n\ngod sync # Incremental sync all\ngod sync myproject # Just one project\ngod sync --force # Full refresh (ignore cache)" }, { "title": "god projects", "body": "Manage configured projects:\n\ngod projects # List all\ngod projects add github:user/repo # Add project\ngod projects remove myproject # Remove project" }, { "title": "god review [--month YYYY-MM]", "body": "Generate monthly activity reviews:\n\ngod review # Last month's activity\ngod review --month 2026-01 # Specific month\ngod review --json # JSON output\n\nWhat it shows:\n\nTotal commits across all projects\nMost active repositories\nPull request activity (merged, active, closed)\nDetailed breakdown by project with date ranges\nPerfect for monthly retrospectives and planning\n\nExample output:\n\nMonthly Review: 2026-01\n šŸ“Š 286 commits across 7 projects\n šŸ‘„ 10 unique contributors\n \nMost Active Projects:\n tada - 155 commits\n ContentEngine - 63 commits\n brain - 27 commits\n\nUse cases:\n\nMonthly team stand-ups\nPersonal retrospectives (\"What did I actually work on?\")\nQuarterly planning (\"Which projects got attention?\")\nAutomated monthly summaries via cron" }, { "title": "god agents analyze ", "body": "Analyze agents.md against commit history using LLM:\n\ngod agents analyze myproject\n\nWhat it does:\n\nFetches your AGENTS.md from the repository\nAnalyzes commit patterns (types, pain points, frequently changed files)\nCalls an LLM (Claude/GPT) to find gaps and suggest improvements\nDisplays recommendations interactively\nOptionally applies changes to your AGENTS.md\n\nLLM Configuration:\n\ngod-mode automatically detects and uses the best available LLM:\n\nOpenClaw (default when running as skill) - Uses your OpenClaw agent\nAnthropic - Set ANTHROPIC_API_KEY=\"sk-ant-...\"\nOpenAI - Set OPENAI_API_KEY=\"sk-...\"\nOpenRouter - Set OPENROUTER_API_KEY=\"sk-or-...\"\nManual - Outputs prompt if no LLM available\n\nWhen running in OpenClaw:\n\nThe analysis prompt is displayed to your OpenClaw agent\nYou (or your agent) provides the JSON analysis directly in the conversation\nMuch simpler than managing separate API keys!\n\nOpenClaw Workflow:\n\nWhen you run god agents analyze in OpenClaw:\n\nAnalysis starts:\nšŸ”­ Analyzing github:InfantLab/tada\nāœ… Found AGENTS.md (remote)\nāœ… 155 commits analyzed\nšŸ¤– Using OpenClaw's LLM\n\n\n\nI (OpenClaw agent) receive the analysis prompt showing:\n\nYour complete AGENTS.md content\nCommit pattern summary (45 features, 68 bug fixes, etc.)\nMost changed files/directories\nPain points and commit samples\n\n\n\nI analyze and provide JSON response:\n{\n \"gaps\": [\n {\n \"area\": \"Testing\",\n \"observation\": \"68 bug fixes but no testing guidance in AGENTS.md\",\n \"impact\": \"high\",\n \"suggestion\": \"Add testing section with coverage targets\"\n }\n ],\n \"strengths\": [...],\n \"recommendations\": [...]\n}\n\n\n\ngod-mode displays results and offers to apply changes to your AGENTS.md\n\n\nYou choose which recommendations to accept, and god-mode updates the file\n\nStandalone Workflow (outside OpenClaw):\n\nIf you set ANTHROPIC_API_KEY or OPENAI_API_KEY, god-mode calls the API directly:\n\nexport ANTHROPIC_API_KEY=\"sk-ant-...\"\ngod agents analyze myproject # Fully automated" }, { "title": "god agents generate (Coming Soon)", "body": "Bootstrap agents.md for a new project by analyzing repo structure." }, { "title": "god logs [options]", "body": "View activity logs:\n\ngod logs # Last 50 lines\ngod logs -n 100 # Last 100 lines\ngod logs -f # Follow log output\ngod logs --path # Show log file location\ngod logs --clear # Clear all logs\n\nAll god-mode activity is logged to ~/.god-mode/logs/activity.log with timestamps for transparency and debugging." }, { "title": "Configuration", "body": "Config file: ~/.config/god-mode/config.yaml\n\nprojects:\n - id: github:user/repo\n name: My Project # Display name\n priority: high # high/medium/low\n tags: [work, api]\n local: ~/code/myrepo # Local clone path\n\nsync:\n initialDays: 90 # First sync lookback\n commitsCacheMinutes: 60\n\nanalysis:\n agentFiles: # Files to search for\n - agents.md\n - AGENTS.md\n - CLAUDE.md\n - .github/copilot-instructions.md" }, { "title": "Data Storage", "body": "All data stored locally in ~/.god-mode/:\n\ncache.db - SQLite database (commits, PRs, issues, analyses)\ncontexts/ - Saved workspace contexts (v0.2)" }, { "title": "Authentication", "body": "god-mode uses your existing CLI authentication:\n\nProviderCLISetupGitHubghgh auth loginAzureazaz loginGitLabglabglab auth login\n\nNo tokens stored by god-mode. We delegate to CLIs you already trust." }, { "title": "Requirements", "body": "gh - GitHub CLI (for GitHub repos)\nsqlite3 - Database\njq - JSON processing" }, { "title": "Morning Check-In", "body": "god status\n# See all projects at a glance\n# Notice any stale PRs or quiet projects" }, { "title": "Before Switching Projects", "body": "god status myproject\n# See recent activity, open PRs, issues\n# Remember where you left off" }, { "title": "Improving Your AI Assistant", "body": "god agents analyze myproject\n# Get suggestions based on your actual commit patterns\n# Apply recommendations to your agents.md" }, { "title": "Weekly Review", "body": "god status\n# Review activity across all projects\n# Identify projects needing attention" }, { "title": "Agent Guide (For OpenClaw Agents)", "body": "When the user asks about their projects, here's what to do:" }, { "title": "\"Set up god-mode\" / \"Track my [repo]\"", "body": "Run god setup (checks dependencies)\nRun god projects add github:username/repo\nRun god sync to fetch data\nSummarize what you found" }, { "title": "\"Show me my projects\" / \"What's happening?\"", "body": "Run god status\nTranslate output to conversational summary:\n\n\"Your most active repo is X with Y commits this week\"\n\"Z repo hasn't had activity in N days\"\n\"You have M open PRs across all projects\"" }, { "title": "\"Analyze my agents.md\"", "body": "Run god agents analyze github:username/repo\nYou'll receive the analysis prompt with:\n\nTheir complete AGENTS.md\nCommit pattern analysis (155 commits, 68 bug fixes, etc.)\nPain points and frequently changed files\n\n\nProvide JSON analysis in this format:\n{\n \"gaps\": [\n {\"area\": \"Testing\", \"observation\": \"68 bug fixes but no test guidance\", \"impact\": \"high\", \"suggestion\": \"Add testing section\"}\n ],\n \"strengths\": [\n {\"area\": \"TypeScript\", \"observation\": \"Zero type errors in 155 commits\"}\n ],\n \"recommendations\": [\n {\"priority\": 1, \"section\": \"## Testing\", \"content\": \"- Write unit tests for new code\\n- Run tests before commits\"}\n ],\n \"summary\": \"Strong TypeScript practices, needs testing guidance\"\n}\n\n\nSummarize the analysis conversationally\nOffer to apply recommendations" }, { "title": "\"Which repos need attention?\"", "body": "Run god status\nLook for:\n\nStale PRs (>3 days old)\nNo activity in >5 days\nOpen issues piling up\n\n\nSuggest what to focus on" }, { "title": "Automated Workflows", "body": "Daily Briefing (Heartbeat):\n\n# HEARTBEAT.md\n- Run `god status` and summarize:\n - Projects with stale PRs (>3 days)\n - Projects with no activity (>5 days)\n - Open PRs needing review\n\nMonthly Review (Cron - 1st of month):\n\nschedule:\n kind: cron\n expr: \"0 9 1 * *\" # 9am on 1st of each month\n tz: \"America/New_York\"\npayload:\n kind: agentTurn\n message: |\n Run god review for last month and summarize:\n - Which projects were most active?\n - Any projects that went quiet?\n - Major accomplishments from commit messages\n - Recommendations for next month\nsessionTarget: isolated\n\nWeekly Analysis (Cron):\n\nschedule: \"0 9 * * 1\" # Monday 9am\ntask: |\n Run `god agents analyze` on high-priority projects.\n If gaps found, notify with suggestions." }, { "title": "How do I use god-mode?", "body": "In OpenClaw: Just ask me! \"Show me my projects\", \"Analyze my agents.md\", etc. I'll run the commands and explain the results.\n\nCLI: Run commands directly: god status, god sync, god agents analyze" }, { "title": "Do I need to set up anything first?", "body": "First time: Tell me to \"set up god-mode for [your repo]\" and I'll handle it. Or run god setup and god projects add github:your/repo yourself.\n\nAuthentication: Make sure gh auth login is done (GitHub CLI authentication)." }, { "title": "Do I need an API key?", "body": "No! When you ask me to analyze your agents.md, I receive the analysis prompt and provide the JSON response directly. No separate API key needed.\n\nStandalone: If using god-mode outside OpenClaw, you can set ANTHROPIC_API_KEY or OPENAI_API_KEY for automated analysis." }, { "title": "How often does it sync data?", "body": "When you ask: I run god sync when you ask about your projects. First sync fetches 90 days of history. Subsequent syncs are incremental (only new data).\n\nManual: You can run god sync anytime, or god sync --force for a full refresh." }, { "title": "What data gets stored?", "body": "Locally only: Commits, PRs, issues, and analysis results in ~/.god-mode/cache.db. Activity logs in ~/.god-mode/logs/activity.log. Nothing sent to external servers (except when calling LLM APIs if configured)." }, { "title": "Does it work with private repos?", "body": "Yes! Uses your gh CLI authentication, so it has access to whatever your GitHub account can access." }, { "title": "\"gh: command not found\"", "body": "Install GitHub CLI: https://cli.github.com/" }, { "title": "\"Not logged in to GitHub\"", "body": "Run: gh auth login" }, { "title": "\"No projects configured\"", "body": "Add a project: god projects add github:user/repo" }, { "title": "Stale data", "body": "Force refresh: god sync --force" }, { "title": "Agent analysis returns empty {}", "body": "This is normal in OpenClaw mode - the prompt is displayed for the OpenClaw agent to analyze. The agent provides the JSON response in conversation, not as return value.\n\nOpenClaw Community Skill\nLicense: MIT\nRepository: https://github.com/InfantLab/god-mode-skill" } ], "body": "god-mode Skill\n\nConversational project oversight and AI agent coaching for OpenClaw.\n\nOverview\n\ngod-mode lets users ask about their projects in plain English. You run the commands and explain the results conversationally.\n\nWhat users can ask:\n\n\"Set up god-mode for my repos\"\n\"What's happening across my projects?\"\n\"Which repos need attention?\"\n\"Analyze my agents.md\"\n\"What should I work on today?\"\n\nWhat you provide:\n\nMulti-project status summaries (GitHub + Azure DevOps)\nPlain-English explanations of commit activity, PRs, issues\nLLM-powered agent instruction analysis\nRecommendations for improving their AGENTS.md\n\nPerfect for:\n\nDevelopers juggling multiple repos who want conversational oversight\nTeams using AI coding assistants (Claude, Copilot, etc.)\nAnyone who wants data-driven improvements to their AGENTS.md\nGetting Started\nFor OpenClaw Users (Conversational)\n\nJust tell me what you want! I'll run the god-mode commands for you.\n\nExample conversations:\n\nYou: \"Set up god-mode for my tada repository\"\n\nMe: Sure! I'll set up god-mode and add your tada repo. [runs god setup and god projects add github:YourUsername/tada] Done! Your repo is configured. Want me to sync the data?\n\nYou: \"Yes, and show me what's happening\"\n\nMe: [runs god sync and god status]\n\nHere's your overview:\n\ntada: 30 commits this week, last activity 3 days ago\n0 open PRs, 0 issues\n\nYour most active project! Commits are all features and bug fixes.\n\nYou: \"Analyze my agents.md for tada\"\n\nMe: [runs god agents analyze github:YourUsername/tada]\n\nI've analyzed your AGENTS.md against 155 commits. Here's what I found:\n\nGAPS:\n\nTesting practices (high impact) - 68 bug fixes but no testing guidance\nVoice API debugging - 12 commits mention \"voice\" but no troubleshooting\n\nSTRENGTHS:\n\nTypeScript strictness is working - zero type-related fixes\n\nWant me to add testing guidance to your AGENTS.md?\n\nWhat you can ask me:\n\n\"Set up god-mode for [repo]\"\n\"Show me all my projects\"\n\"What's happening across my repos?\"\n\"Analyze my agents.md\"\n\"Which repos need attention?\"\n\"What should I work on today?\"\n\nI'll handle all the commands and explain the results in plain English.\n\nFor CLI Users (Direct Commands)\n\nIf you prefer running commands yourself:\n\n# Setup\ngod setup\n\n# Add a project\ngod projects add github:username/repo\n\n# Sync and view\ngod sync\ngod status\n\nCommands\ngod status [project]\n\nShow overview of all projects, or details for one:\n\ngod status # All projects\ngod status myproject # One project in detail\n\ngod sync [project] [--force]\n\nFetch/update data from repositories:\n\ngod sync # Incremental sync all\ngod sync myproject # Just one project\ngod sync --force # Full refresh (ignore cache)\n\ngod projects\n\nManage configured projects:\n\ngod projects # List all\ngod projects add github:user/repo # Add project\ngod projects remove myproject # Remove project\n\ngod review [--month YYYY-MM]\n\nGenerate monthly activity reviews:\n\ngod review # Last month's activity\ngod review --month 2026-01 # Specific month\ngod review --json # JSON output\n\n\nWhat it shows:\n\nTotal commits across all projects\nMost active repositories\nPull request activity (merged, active, closed)\nDetailed breakdown by project with date ranges\nPerfect for monthly retrospectives and planning\n\nExample output:\n\nMonthly Review: 2026-01\n šŸ“Š 286 commits across 7 projects\n šŸ‘„ 10 unique contributors\n \nMost Active Projects:\n tada - 155 commits\n ContentEngine - 63 commits\n brain - 27 commits\n\n\nUse cases:\n\nMonthly team stand-ups\nPersonal retrospectives (\"What did I actually work on?\")\nQuarterly planning (\"Which projects got attention?\")\nAutomated monthly summaries via cron\ngod agents analyze \n\nAnalyze agents.md against commit history using LLM:\n\ngod agents analyze myproject\n\n\nWhat it does:\n\nFetches your AGENTS.md from the repository\nAnalyzes commit patterns (types, pain points, frequently changed files)\nCalls an LLM (Claude/GPT) to find gaps and suggest improvements\nDisplays recommendations interactively\nOptionally applies changes to your AGENTS.md\n\nLLM Configuration:\n\ngod-mode automatically detects and uses the best available LLM:\n\nOpenClaw (default when running as skill) - Uses your OpenClaw agent\nAnthropic - Set ANTHROPIC_API_KEY=\"sk-ant-...\"\nOpenAI - Set OPENAI_API_KEY=\"sk-...\"\nOpenRouter - Set OPENROUTER_API_KEY=\"sk-or-...\"\nManual - Outputs prompt if no LLM available\n\nWhen running in OpenClaw:\n\nThe analysis prompt is displayed to your OpenClaw agent\nYou (or your agent) provides the JSON analysis directly in the conversation\nMuch simpler than managing separate API keys!\n\nOpenClaw Workflow:\n\nWhen you run god agents analyze in OpenClaw:\n\nAnalysis starts:\n\nšŸ”­ Analyzing github:InfantLab/tada\nāœ… Found AGENTS.md (remote)\nāœ… 155 commits analyzed\nšŸ¤– Using OpenClaw's LLM\n\n\nI (OpenClaw agent) receive the analysis prompt showing:\n\nYour complete AGENTS.md content\nCommit pattern summary (45 features, 68 bug fixes, etc.)\nMost changed files/directories\nPain points and commit samples\n\nI analyze and provide JSON response:\n\n{\n \"gaps\": [\n {\n \"area\": \"Testing\",\n \"observation\": \"68 bug fixes but no testing guidance in AGENTS.md\",\n \"impact\": \"high\",\n \"suggestion\": \"Add testing section with coverage targets\"\n }\n ],\n \"strengths\": [...],\n \"recommendations\": [...]\n}\n\n\ngod-mode displays results and offers to apply changes to your AGENTS.md\n\nYou choose which recommendations to accept, and god-mode updates the file\n\nStandalone Workflow (outside OpenClaw):\n\nIf you set ANTHROPIC_API_KEY or OPENAI_API_KEY, god-mode calls the API directly:\n\nexport ANTHROPIC_API_KEY=\"sk-ant-...\"\ngod agents analyze myproject # Fully automated\n\ngod agents generate (Coming Soon)\n\nBootstrap agents.md for a new project by analyzing repo structure.\n\ngod logs [options]\n\nView activity logs:\n\ngod logs # Last 50 lines\ngod logs -n 100 # Last 100 lines\ngod logs -f # Follow log output\ngod logs --path # Show log file location\ngod logs --clear # Clear all logs\n\n\nAll god-mode activity is logged to ~/.god-mode/logs/activity.log with timestamps for transparency and debugging.\n\nConfiguration\n\nConfig file: ~/.config/god-mode/config.yaml\n\nprojects:\n - id: github:user/repo\n name: My Project # Display name\n priority: high # high/medium/low\n tags: [work, api]\n local: ~/code/myrepo # Local clone path\n\nsync:\n initialDays: 90 # First sync lookback\n commitsCacheMinutes: 60\n\nanalysis:\n agentFiles: # Files to search for\n - agents.md\n - AGENTS.md\n - CLAUDE.md\n - .github/copilot-instructions.md\n\nData Storage\n\nAll data stored locally in ~/.god-mode/:\n\ncache.db - SQLite database (commits, PRs, issues, analyses)\ncontexts/ - Saved workspace contexts (v0.2)\nAuthentication\n\ngod-mode uses your existing CLI authentication:\n\nProvider\tCLI\tSetup\nGitHub\tgh\tgh auth login\nAzure\taz\taz login\nGitLab\tglab\tglab auth login\n\nNo tokens stored by god-mode. We delegate to CLIs you already trust.\n\nRequirements\ngh - GitHub CLI (for GitHub repos)\nsqlite3 - Database\njq - JSON processing\nExamples\nMorning Check-In\ngod status\n# See all projects at a glance\n# Notice any stale PRs or quiet projects\n\nBefore Switching Projects\ngod status myproject\n# See recent activity, open PRs, issues\n# Remember where you left off\n\nImproving Your AI Assistant\ngod agents analyze myproject\n# Get suggestions based on your actual commit patterns\n# Apply recommendations to your agents.md\n\nWeekly Review\ngod status\n# Review activity across all projects\n# Identify projects needing attention\n\nAgent Guide (For OpenClaw Agents)\n\nWhen the user asks about their projects, here's what to do:\n\n\"Set up god-mode\" / \"Track my [repo]\"\nRun god setup (checks dependencies)\nRun god projects add github:username/repo\nRun god sync to fetch data\nSummarize what you found\n\"Show me my projects\" / \"What's happening?\"\nRun god status\nTranslate output to conversational summary:\n\"Your most active repo is X with Y commits this week\"\n\"Z repo hasn't had activity in N days\"\n\"You have M open PRs across all projects\"\n\"Analyze my agents.md\"\nRun god agents analyze github:username/repo\nYou'll receive the analysis prompt with:\nTheir complete AGENTS.md\nCommit pattern analysis (155 commits, 68 bug fixes, etc.)\nPain points and frequently changed files\nProvide JSON analysis in this format:\n{\n \"gaps\": [\n {\"area\": \"Testing\", \"observation\": \"68 bug fixes but no test guidance\", \"impact\": \"high\", \"suggestion\": \"Add testing section\"}\n ],\n \"strengths\": [\n {\"area\": \"TypeScript\", \"observation\": \"Zero type errors in 155 commits\"}\n ],\n \"recommendations\": [\n {\"priority\": 1, \"section\": \"## Testing\", \"content\": \"- Write unit tests for new code\\n- Run tests before commits\"}\n ],\n \"summary\": \"Strong TypeScript practices, needs testing guidance\"\n}\n\nSummarize the analysis conversationally\nOffer to apply recommendations\n\"Which repos need attention?\"\nRun god status\nLook for:\nStale PRs (>3 days old)\nNo activity in >5 days\nOpen issues piling up\nSuggest what to focus on\nAutomated Workflows\n\nDaily Briefing (Heartbeat):\n\n# HEARTBEAT.md\n- Run `god status` and summarize:\n - Projects with stale PRs (>3 days)\n - Projects with no activity (>5 days)\n - Open PRs needing review\n\n\nMonthly Review (Cron - 1st of month):\n\nschedule:\n kind: cron\n expr: \"0 9 1 * *\" # 9am on 1st of each month\n tz: \"America/New_York\"\npayload:\n kind: agentTurn\n message: |\n Run god review for last month and summarize:\n - Which projects were most active?\n - Any projects that went quiet?\n - Major accomplishments from commit messages\n - Recommendations for next month\nsessionTarget: isolated\n\n\nWeekly Analysis (Cron):\n\nschedule: \"0 9 * * 1\" # Monday 9am\ntask: |\n Run `god agents analyze` on high-priority projects.\n If gaps found, notify with suggestions.\n\nCommon Questions\nHow do I use god-mode?\n\nIn OpenClaw: Just ask me! \"Show me my projects\", \"Analyze my agents.md\", etc. I'll run the commands and explain the results.\n\nCLI: Run commands directly: god status, god sync, god agents analyze\n\nDo I need to set up anything first?\n\nFirst time: Tell me to \"set up god-mode for [your repo]\" and I'll handle it. Or run god setup and god projects add github:your/repo yourself.\n\nAuthentication: Make sure gh auth login is done (GitHub CLI authentication).\n\nDo I need an API key?\n\nNo! When you ask me to analyze your agents.md, I receive the analysis prompt and provide the JSON response directly. No separate API key needed.\n\nStandalone: If using god-mode outside OpenClaw, you can set ANTHROPIC_API_KEY or OPENAI_API_KEY for automated analysis.\n\nHow often does it sync data?\n\nWhen you ask: I run god sync when you ask about your projects. First sync fetches 90 days of history. Subsequent syncs are incremental (only new data).\n\nManual: You can run god sync anytime, or god sync --force for a full refresh.\n\nWhat data gets stored?\n\nLocally only: Commits, PRs, issues, and analysis results in ~/.god-mode/cache.db. Activity logs in ~/.god-mode/logs/activity.log. Nothing sent to external servers (except when calling LLM APIs if configured).\n\nDoes it work with private repos?\n\nYes! Uses your gh CLI authentication, so it has access to whatever your GitHub account can access.\n\nTroubleshooting\n\"gh: command not found\"\n\nInstall GitHub CLI: https://cli.github.com/\n\n\"Not logged in to GitHub\"\n\nRun: gh auth login\n\n\"No projects configured\"\n\nAdd a project: god projects add github:user/repo\n\nStale data\n\nForce refresh: god sync --force\n\nAgent analysis returns empty {}\n\nThis is normal in OpenClaw mode - the prompt is displayed for the OpenClaw agent to analyze. The agent provides the JSON response in conversation, not as return value.\n\nOpenClaw Community Skill\nLicense: MIT\nRepository: https://github.com/InfantLab/god-mode-skill" }, "trust": { "sourceLabel": "tencent", "provenanceUrl": "https://clawhub.ai/wetzja04-dot/god-mode-skill", "publisherUrl": "https://clawhub.ai/wetzja04-dot/god-mode-skill", "owner": "wetzja04-dot", "version": "1.0.0", "license": null, "verificationStatus": "Indexed source record" }, "links": { "detailUrl": "https://openagent3.xyz/skills/god-mode-skill", "downloadUrl": "https://openagent3.xyz/downloads/god-mode-skill", "agentUrl": "https://openagent3.xyz/skills/god-mode-skill/agent", "manifestUrl": "https://openagent3.xyz/skills/god-mode-skill/agent.json", "briefUrl": "https://openagent3.xyz/skills/god-mode-skill/agent.md" } }