[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6XDSJJY04JHA968G5RFH68H":3,"skill-same:01M6XDSJJY04JHA968G5RFH68H":49},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":24,"linkOnly":25,"markdownContent":26,"markdownBody":27,"frontMatter":28,"refName":29,"commitSha":30,"skillDirectory":31,"forksCount":14,"repositoryHtmlUrl":32,"repositoryHomepageUrl":6,"ownerHtmlUrl":33,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":34,"install":35,"resources":48},"01M6XDSJJY04JHA968G5RFH68H","help",null,"Guide on using oh-my-codex plugin","sapsapshen\u002Fai-memory-router","sapsapshen","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F20347959?v=4","01M6XDQEF1DP50DKF37H81J3J5","shenmian","01M6XDQEJPE41Y3DT2763X8ZJN",0,"MIT","https:\u002F\u002Fgithub.com\u002Fsapsapshen\u002Fai-memory-router\u002Fblob\u002Fmain\u002Fskills-store\u002Fcodex\u002Fhelp\u002FSKILL.md",[],[5,19,20,21,22,23],"codex","codex plugin","plugin","guide","my","2026-11-10 10:12:30",false,"---\nname: help\ndescription: Guide on using oh-my-codex plugin\n---\n\n# How OMX Works\n\n**You don't need to learn any commands!** OMX enhances Codex CLI with intelligent behaviors that activate automatically.\n\n## What Happens Automatically\n\n| When You... | I Automatically... |\n|-------------|-------------------|\n| Give me a complex task | Parallelize and delegate to specialist agents |\n| Ask me to plan something | Start a planning interview |\n| Need something done completely | Persist until verified complete |\n| Work on UI\u002Ffrontend | Activate design sensibility |\n| Say \"stop\" or \"cancel\" | Intelligently stop current operation |\n\n## Magic Keywords (Optional Shortcuts)\n\nYou can include these words naturally in your request for explicit control:\n\n| Keyword | Effect | Example |\n|---------|--------|---------|\n| **ralph** | Persistence mode | \"ralph: fix all the bugs\" |\n| **ralplan** | Iterative planning | \"ralplan this feature\" |\n| **ulw** | Max parallelism | \"ulw refactor the API\" |\n| **plan** | Planning interview | \"plan the new endpoints\" |\n\n**ralph includes ultrawork:** When you activate ralph mode, it automatically includes ultrawork's parallel execution. No need to combine keywords.\n\n## Stopping Things\n\nJust say:\n- \"stop\"\n- \"cancel\"\n- \"abort\"\n\nI'll figure out what to stop based on context.\n\n## First Time Setup\n\nIf you haven't configured OMX yet:\n\n```\n\u002Fomx-setup\n```\n\nThis is the **only command** you need to know. It downloads the configuration and you're done.\n\nIf you only need lightweight directory guidance scaffolding for `AGENTS.md` files, use:\n\n```bash\nomx agents-init .\n```\n\nThat command is intentionally narrower than full setup: it only bootstraps `AGENTS.md` files for the target directory and its immediate child directories.\n\n## For 2.x Users\n\nYour old commands still work! `\u002Fralph`, `\u002Fultrawork`, `\u002Fplan`, etc. all function exactly as before.\n\nBut now you don't NEED them - everything is automatic.\n\n---\n\n## Usage Analysis\n\nAnalyze your oh-my-codex usage and get tailored recommendations to improve your workflow.\n\n> Note: This replaces the former `\u002Flearn-about-omc` skill.\n\n### What It Does\n\n1. Reads token tracking from `~\u002F.omx\u002Fstate\u002Ftoken-tracking.jsonl`\n2. Reads session history from `.omx\u002Fstate\u002Fsession-history.json`\n3. Analyzes agent usage patterns\n4. Identifies underutilized features\n5. Recommends configuration changes\n\n### Step 1: Gather Data\n\n```bash\n# Check for token tracking data\nTOKEN_FILE=\"$HOME\u002F.omx\u002Fstate\u002Ftoken-tracking.jsonl\"\nSESSION_FILE=\".omx\u002Fstate\u002Fsession-history.json\"\nCONFIG_FILE=\"$HOME\u002F.codex\u002F.omx-config.json\"\n\necho \"Analyzing OMX Usage...\"\necho \"\"\n\n# Check what data is available\nHAS_TOKENS=false\nHAS_SESSIONS=false\nHAS_CONFIG=false\n\nif [[ -f \"$TOKEN_FILE\" ]]; then\n  HAS_TOKENS=true\n  TOKEN_COUNT=$(wc -l \u003C \"$TOKEN_FILE\")\n  echo \"Token records found: $TOKEN_COUNT\"\nfi\n\nif [[ -f \"$SESSION_FILE\" ]]; then\n  HAS_SESSIONS=true\n  SESSION_COUNT=$(cat \"$SESSION_FILE\" | jq '.sessions | length' 2>\u002Fdev\u002Fnull || echo \"0\")\n  echo \"Sessions found: $SESSION_COUNT\"\nfi\n\nif [[ -f \"$CONFIG_FILE\" ]]; then\n  HAS_CONFIG=true\n  DEFAULT_MODE=$(cat \"$CONFIG_FILE\" | jq -r '.defaultExecutionMode \u002F\u002F \"not set\"')\n  echo \"Default execution mode: $DEFAULT_MODE\"\nfi\n```\n\n### Step 2: Analyze Agent Usage (if token data exists)\n\n```bash\nif [[ \"$HAS_TOKENS\" == \"true\" ]]; then\n  echo \"\"\n  echo \"TOP AGENTS BY USAGE:\"\n  cat \"$TOKEN_FILE\" | jq -r '.agentName \u002F\u002F \"main\"' | sort | uniq -c | sort -rn | head -10\n\n  echo \"\"\n  echo \"MODEL DISTRIBUTION:\"\n  cat \"$TOKEN_FILE\" | jq -r '.modelName' | sort | uniq -c | sort -rn\nfi\n```\n\n### Step 3: Generate Recommendations\n\nBased on patterns found, output recommendations:\n\n**If high Opus usage (>40%) and no ecomode:**\n- \"Consider using ecomode for routine tasks to save tokens\"\n\n**If no team usage:**\n- \"Try \u002Fteam for coordinated review workflows\"\n\n**If no security-reviewer usage:**\n- \"Use security-reviewer after auth\u002FAPI changes\"\n\n**If defaultExecutionMode not set:**\n- \"Set defaultExecutionMode in \u002Fomx-setup for consistent behavior\"\n\n### Step 4: Output Report\n\nFormat a summary with:\n- Token summary (total, by model)\n- Top agents used\n- Underutilized features\n- Personalized recommendations\n\n### Example Output\n\n```\n? Your OMX Usage Analysis\n\nTOKEN SUMMARY:\n- Total records: 1,234\n- By Reasoning Effort: high 45%, medium 40%, low 15%\n\nTOP AGENTS:\n1. executor (234 uses)\n2. architect (89 uses)\n3. explore (67 uses)\n\nUNDERUTILIZED FEATURES:\n- ecomode: 0 uses (could save ~30% on routine tasks)\n- team: 0 uses (great for coordinated workflows)\n\nRECOMMENDATIONS:\n1. Set defaultExecutionMode: \"ecomode\" to save tokens\n2. Try \u002Fteam for PR review workflows\n3. Use explore agent before architect to save context\n```\n\n### Graceful Degradation\n\nIf no data found:\n\n```\n? Limited Usage Data Available\n\nNo token tracking found. To enable tracking:\n1. Ensure ~\u002F.omx\u002Fstate\u002F directory exists\n2. Run any OMX command to start tracking\n\nTip: Run \u002Fomx-setup to configure OMX properly.\n```\n\n## Need More Help?\n\n- **README**: https:\u002F\u002Fgithub.com\u002FYeachan-Heo\u002Foh-my-codex\n- **Issues**: https:\u002F\u002Fgithub.com\u002FYeachan-Heo\u002Foh-my-codex\u002Fissues\n\n---\n\n*Version: 4.2.3*\n","# How OMX Works\n\n**You don't need to learn any commands!** OMX enhances Codex CLI with intelligent behaviors that activate automatically.\n\n## What Happens Automatically\n\n| When You... | I Automatically... |\n|-------------|-------------------|\n| Give me a complex task | Parallelize and delegate to specialist agents |\n| Ask me to plan something | Start a planning interview |\n| Need something done completely | Persist until verified complete |\n| Work on UI\u002Ffrontend | Activate design sensibility |\n| Say \"stop\" or \"cancel\" | Intelligently stop current operation |\n\n## Magic Keywords (Optional Shortcuts)\n\nYou can include these words naturally in your request for explicit control:\n\n| Keyword | Effect | Example |\n|---------|--------|---------|\n| **ralph** | Persistence mode | \"ralph: fix all the bugs\" |\n| **ralplan** | Iterative planning | \"ralplan this feature\" |\n| **ulw** | Max parallelism | \"ulw refactor the API\" |\n| **plan** | Planning interview | \"plan the new endpoints\" |\n\n**ralph includes ultrawork:** When you activate ralph mode, it automatically includes ultrawork's parallel execution. No need to combine keywords.\n\n## Stopping Things\n\nJust say:\n- \"stop\"\n- \"cancel\"\n- \"abort\"\n\nI'll figure out what to stop based on context.\n\n## First Time Setup\n\nIf you haven't configured OMX yet:\n\n```\n\u002Fomx-setup\n```\n\nThis is the **only command** you need to know. It downloads the configuration and you're done.\n\nIf you only need lightweight directory guidance scaffolding for `AGENTS.md` files, use:\n\n```bash\nomx agents-init .\n```\n\nThat command is intentionally narrower than full setup: it only bootstraps `AGENTS.md` files for the target directory and its immediate child directories.\n\n## For 2.x Users\n\nYour old commands still work! `\u002Fralph`, `\u002Fultrawork`, `\u002Fplan`, etc. all function exactly as before.\n\nBut now you don't NEED them - everything is automatic.\n\n---\n\n## Usage Analysis\n\nAnalyze your oh-my-codex usage and get tailored recommendations to improve your workflow.\n\n> Note: This replaces the former `\u002Flearn-about-omc` skill.\n\n### What It Does\n\n1. Reads token tracking from `~\u002F.omx\u002Fstate\u002Ftoken-tracking.jsonl`\n2. Reads session history from `.omx\u002Fstate\u002Fsession-history.json`\n3. Analyzes agent usage patterns\n4. Identifies underutilized features\n5. Recommends configuration changes\n\n### Step 1: Gather Data\n\n```bash\n# Check for token tracking data\nTOKEN_FILE=\"$HOME\u002F.omx\u002Fstate\u002Ftoken-tracking.jsonl\"\nSESSION_FILE=\".omx\u002Fstate\u002Fsession-history.json\"\nCONFIG_FILE=\"$HOME\u002F.codex\u002F.omx-config.json\"\n\necho \"Analyzing OMX Usage...\"\necho \"\"\n\n# Check what data is available\nHAS_TOKENS=false\nHAS_SESSIONS=false\nHAS_CONFIG=false\n\nif [[ -f \"$TOKEN_FILE\" ]]; then\n  HAS_TOKENS=true\n  TOKEN_COUNT=$(wc -l \u003C \"$TOKEN_FILE\")\n  echo \"Token records found: $TOKEN_COUNT\"\nfi\n\nif [[ -f \"$SESSION_FILE\" ]]; then\n  HAS_SESSIONS=true\n  SESSION_COUNT=$(cat \"$SESSION_FILE\" | jq '.sessions | length' 2>\u002Fdev\u002Fnull || echo \"0\")\n  echo \"Sessions found: $SESSION_COUNT\"\nfi\n\nif [[ -f \"$CONFIG_FILE\" ]]; then\n  HAS_CONFIG=true\n  DEFAULT_MODE=$(cat \"$CONFIG_FILE\" | jq -r '.defaultExecutionMode \u002F\u002F \"not set\"')\n  echo \"Default execution mode: $DEFAULT_MODE\"\nfi\n```\n\n### Step 2: Analyze Agent Usage (if token data exists)\n\n```bash\nif [[ \"$HAS_TOKENS\" == \"true\" ]]; then\n  echo \"\"\n  echo \"TOP AGENTS BY USAGE:\"\n  cat \"$TOKEN_FILE\" | jq -r '.agentName \u002F\u002F \"main\"' | sort | uniq -c | sort -rn | head -10\n\n  echo \"\"\n  echo \"MODEL DISTRIBUTION:\"\n  cat \"$TOKEN_FILE\" | jq -r '.modelName' | sort | uniq -c | sort -rn\nfi\n```\n\n### Step 3: Generate Recommendations\n\nBased on patterns found, output recommendations:\n\n**If high Opus usage (>40%) and no ecomode:**\n- \"Consider using ecomode for routine tasks to save tokens\"\n\n**If no team usage:**\n- \"Try \u002Fteam for coordinated review workflows\"\n\n**If no security-reviewer usage:**\n- \"Use security-reviewer after auth\u002FAPI changes\"\n\n**If defaultExecutionMode not set:**\n- \"Set defaultExecutionMode in \u002Fomx-setup for consistent behavior\"\n\n### Step 4: Output Report\n\nFormat a summary with:\n- Token summary (total, by model)\n- Top agents used\n- Underutilized features\n- Personalized recommendations\n\n### Example Output\n\n```\n? Your OMX Usage Analysis\n\nTOKEN SUMMARY:\n- Total records: 1,234\n- By Reasoning Effort: high 45%, medium 40%, low 15%\n\nTOP AGENTS:\n1. executor (234 uses)\n2. architect (89 uses)\n3. explore (67 uses)\n\nUNDERUTILIZED FEATURES:\n- ecomode: 0 uses (could save ~30% on routine tasks)\n- team: 0 uses (great for coordinated workflows)\n\nRECOMMENDATIONS:\n1. Set defaultExecutionMode: \"ecomode\" to save tokens\n2. Try \u002Fteam for PR review workflows\n3. Use explore agent before architect to save context\n```\n\n### Graceful Degradation\n\nIf no data found:\n\n```\n? Limited Usage Data Available\n\nNo token tracking found. To enable tracking:\n1. Ensure ~\u002F.omx\u002Fstate\u002F directory exists\n2. Run any OMX command to start tracking\n\nTip: Run \u002Fomx-setup to configure OMX properly.\n```\n\n## Need More Help?\n\n- **README**: https:\u002F\u002Fgithub.com\u002FYeachan-Heo\u002Foh-my-codex\n- **Issues**: https:\u002F\u002Fgithub.com\u002FYeachan-Heo\u002Foh-my-codex\u002Fissues\n\n---\n\n*Version: 4.2.3*\n",{"name":5,"description":7},"main","7a38d8e7073e61c16eda85681cb32fb68a8657a5","skills-store\u002Fcodex\u002Fhelp","https:\u002F\u002Fgithub.com\u002Fsapsapshen\u002Fai-memory-router","https:\u002F\u002Fgithub.com\u002Fsapsapshen","2026-04-14 21:12:12",{"source":8,"skillName":5,"commands":36,"prompt":46,"zipAvailable":47},[37,40,43],{"tool":38,"command":39},"npx","npx skills add sapsapshen\u002Fai-memory-router --skill help",{"tool":41,"command":42},"bunx","bunx skills add sapsapshen\u002Fai-memory-router --skill help",{"tool":44,"command":45},"pnpm","pnpm dlx skills add sapsapshen\u002Fai-memory-router --skill help","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fsapsapshen\u002Fai-memory-router\u002Fblob\u002Fmain\u002Fskills-store\u002Fcodex\u002Fhelp\u002FSKILL.md",true,[],[50,60,67,75,81,89],{"skillNo":51,"name":52,"nameZh":6,"description":53,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":54,"licenseFileUrl":55,"sourceHtmlUrl":56,"categories":57,"keywords":58,"publishedAt":59},"01M72R8PZX1ABFHJGTYPA4CAF1","webapp-testing","To test local web applications, write native Python Playwright scripts.","Apache-2.0","https:\u002F\u002Fgithub.com\u002Fsapsapshen\u002Fai-memory-router\u002Fblob\u002Fmain\u002Fskills-store\u002Fglobal\u002Fwebapp-testing\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fsapsapshen\u002Fai-memory-router\u002Fblob\u002Fmain\u002Fskills-store\u002Fglobal\u002Fwebapp-testing\u002FSKILL.md",[],[],"2026-11-10 22:39:42",{"skillNo":61,"name":62,"nameZh":6,"description":63,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":64,"categories":65,"keywords":66,"publishedAt":59},"01M72QG37MMZNDY7X7GXPAK5W6","python-packaging","Comprehensive guide to creating, structuring, and distributing Python packages using modern packaging tools, pyproject.toml, and publishing to PyPI.","https:\u002F\u002Fgithub.com\u002Fsapsapshen\u002Fai-memory-router\u002Fblob\u002Fmain\u002Fskills-store\u002Fglobal\u002Fpython-packaging\u002FSKILL.md",[],[],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":54,"licenseFileUrl":71,"sourceHtmlUrl":72,"categories":73,"keywords":74,"publishedAt":59},"01M72NXR0QMP9G46TW6A2DH59C","canvas-design","These are instructions for creating design philosophies - aesthetic movements that are then EXPRESSED VISUALLY. Output only .md files, .pdf files, and .png files.","https:\u002F\u002Fgithub.com\u002Fsapsapshen\u002Fai-memory-router\u002Fblob\u002Fmain\u002Fskills-store\u002Fglobal\u002Fcanvas-design\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fsapsapshen\u002Fai-memory-router\u002Fblob\u002Fmain\u002Fskills-store\u002Fglobal\u002Fcanvas-design\u002FSKILL.md",[],[],{"skillNo":76,"name":52,"nameZh":6,"description":53,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":54,"licenseFileUrl":77,"sourceHtmlUrl":78,"categories":79,"keywords":80,"publishedAt":59},"01M72N55TK3EEQ4QK4AWDC2KZS","https:\u002F\u002Fgithub.com\u002Fsapsapshen\u002Fai-memory-router\u002Fblob\u002Fmain\u002Fskills-store\u002Fcursor\u002Fwebapp-testing\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fsapsapshen\u002Fai-memory-router\u002Fblob\u002Fmain\u002Fskills-store\u002Fcursor\u002Fwebapp-testing\u002FSKILL.md",[],[],{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":54,"licenseFileUrl":85,"sourceHtmlUrl":86,"categories":87,"keywords":88,"publishedAt":59},"01M72MTWC150CFAP4Y5GSNKF80","slack-gif-creator","A toolkit providing utilities and knowledge for creating animated GIFs optimized for Slack.","https:\u002F\u002Fgithub.com\u002Fsapsapshen\u002Fai-memory-router\u002Fblob\u002Fmain\u002Fskills-store\u002Fcursor\u002Fslack-gif-creator\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fsapsapshen\u002Fai-memory-router\u002Fblob\u002Fmain\u002Fskills-store\u002Fcursor\u002Fslack-gif-creator\u002FSKILL.md",[],[],{"skillNo":90,"name":91,"nameZh":6,"description":92,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":54,"licenseFileUrl":93,"sourceHtmlUrl":94,"categories":95,"keywords":96,"publishedAt":59},"01M72KPT3VVNSP88MNAY466TZT","frontend-design","You are a frontend designer-engineer, not a layout generator.","https:\u002F\u002Fgithub.com\u002Fsapsapshen\u002Fai-memory-router\u002Fblob\u002Fmain\u002Fskills-store\u002Fcursor\u002Ffrontend-design\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fsapsapshen\u002Fai-memory-router\u002Fblob\u002Fmain\u002Fskills-store\u002Fcursor\u002Ffrontend-design\u002FSKILL.md",[],[]]