[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M77071G5XK2PN9ARR9CCXGEM":3,"skill-same:01M77071G5XK2PN9ARR9CCXGEM":60},{"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":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":37,"commitSha":38,"skillDirectory":39,"forksCount":40,"repositoryHtmlUrl":41,"repositoryHomepageUrl":6,"ownerHtmlUrl":42,"ownerBlogUrl":43,"ownerDescription":44,"updatedAt":45,"install":46,"resources":59},"01M77071G5XK2PN9ARR9CCXGEM","claude-code-pro",null,"Token-efficient Claude Code workflow. Other skills burn tokens polling tmux every 30s —  this one uses completion callbacks and only checks when notified. Observable tmux sessions, smart dispatch rules (know when NOT to spawn Claude Code), and structured JSON monitoring. Saves 80%+ supervision tokens vs polling-based approaches. Use when: multi-file coding tasks that need background execution. NOT for: simple single-file fixes (just read+edit directly — that's the point). Requires: tmux, claude CLI.","javimosch\u002Fopen-claw-skills","javimosch","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F12900508?v=4","01M6D3F2AS6PV75ET9PZ1QGP8J","Javier Leandro Arancibia","01M75B8NCTAJG9WH5YNZH7C3D8",0,"MIT","https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fswaylq\u002Fclaude-code-pro\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: claude-code-pro\ndescription: >\n  Token-efficient Claude Code workflow. Other skills burn tokens polling tmux every 30s — \n  this one uses completion callbacks and only checks when notified. Observable tmux sessions,\n  smart dispatch rules (know when NOT to spawn Claude Code), and structured JSON monitoring.\n  Saves 80%+ supervision tokens vs polling-based approaches.\n  Use when: multi-file coding tasks that need background execution.\n  NOT for: simple single-file fixes (just read+edit directly — that's the point).\n  Requires: tmux, claude CLI.\nmetadata:\n  {\n    \"openclaw\":\n      {\n        \"emoji\": \"⚡\",\n        \"os\": [\"darwin\", \"linux\"],\n        \"requires\": { \"bins\": [\"tmux\", \"bash\"], \"anyBins\": [\"claude\"] },\n      },\n  }\n---\n\n# Claude Code Pro ⚡\n\nProduction-grade Claude Code workflow that doesn't waste your tokens.\n\n## The Problem with Other Skills\n\nMost Claude Code tmux skills work like this:\n```\nStart task → Poll every 30s → Poll → Poll → Poll → Done\n                 🔥 tokens      🔥       🔥       🔥\n```\n\nEach poll reads 100-200 lines of terminal output, feeds it to your agent, and burns tokens deciding \"is it done yet?\" A 20-minute task = 40 polls = thousands of wasted tokens.\n\n## How This Skill Works\n\n```\nStart task (with callback) → Wait → 📩 Notification → Read result (50 lines)\n                               😴 zero tokens          ⚡ one read\n```\n\n**The task itself tells you when it's done.** Your agent sleeps until notified. One lightweight check confirms the result. That's it.\n\n### Token Savings Breakdown\n\n| Approach | 20-min task | Tokens burned |\n|----------|-------------|---------------|\n| Poll every 30s | 40 reads × ~500 tokens | **~20,000** |\n| Poll every 60s | 20 reads × ~500 tokens | **~10,000** |\n| **This skill** | 1 notification + 1 read | **~500** |\n\n**80-97% token savings** on supervision alone.\n\n## Smart Dispatch: Know When NOT to Start\n\nBefore spawning Claude Code, ask:\n\n| Situation | Action |\n|-----------|--------|\n| \u003C 3 files involved | **Don't start CC.** Just read + edit directly. |\n| Single bug fix | **Don't start CC.** Faster to fix inline. |\n| Need extensive context exploration | ✅ Start CC |\n| Multi-file refactor | ✅ Start CC |\n| New feature (5+ files) | ✅ Start CC |\n\nThe fastest token savings come from not spawning a session at all.\n\n## Quick Start\n\n```bash\n# Start a task — note the callback at the end\nbash {baseDir}\u002Fscripts\u002Fstart.sh --label auth-refactor --workdir ~\u002Fproject --task \"Refactor auth module to use JWT.\n\nWhen completely finished, run: openclaw system event --text \\\"Done: JWT auth refactor complete\\\" --mode now\"\n```\n\nThat's the key line: `openclaw system event --text \"Done: ...\" --mode now`. The task notifies your agent on completion. No polling needed.\n\n### Task from file (complex requirements)\n\n```bash\nbash {baseDir}\u002Fscripts\u002Fstart.sh --label my-feature --workdir ~\u002Fproject \\\n  --task-file \u002Fpath\u002Fto\u002Frequirements.md --mode auto\n```\n\nWrite detailed requirements once upfront → fewer mid-task corrections → fewer tokens.\n\n## Monitor (Only When Needed)\n\n```bash\n# Lightweight check — 50 lines, minimal tokens\nbash {baseDir}\u002Fscripts\u002Fmonitor.sh --session my-task --lines 50\n\n# JSON mode — structured, even fewer tokens for agent parsing\nbash {baseDir}\u002Fscripts\u002Fmonitor.sh --session my-task --json\n\n# Send follow-up (use sparingly — write requirements upfront instead)\nbash {baseDir}\u002Fscripts\u002Fsend.sh --session my-task --text \"Also add unit tests\"\n\n# Compact context when running long\nbash {baseDir}\u002Fscripts\u002Fsend.sh --session my-task --compact\n```\n\n## Manage Sessions\n\n```bash\n# List all active sessions\nbash {baseDir}\u002Fscripts\u002Flist.sh          # human-readable\nbash {baseDir}\u002Fscripts\u002Flist.sh --json   # structured\n\n# Stop sessions\nbash {baseDir}\u002Fscripts\u002Fstop.sh --session my-task\nbash {baseDir}\u002Fscripts\u002Fstop.sh --all\n```\n\n## Attach (Human SSH Access)\n\n```bash\ntmux -L cc attach -t cc-\u003Clabel>\n```\n\n## Agent Workflow\n\n```\n1. DECIDE — Is this a 3+ file task? No → just edit. Yes → continue.\n2. START — start.sh with detailed task + completion callback\n3. WAIT — Do other work. Zero tokens spent watching.\n4. NOTIFIED — Receive \"Done: ...\" event\n5. CHECK — monitor.sh --lines 50 to confirm result\n6. CLEANUP — stop.sh to end session\n```\n\n**Fallback:** If no notification after 15 minutes, one lightweight poll with `--json`.\n\n## Completion Callback Template\n\nAlways append to your task prompt:\n\n```\nWhen completely finished, run this command to notify:\nopenclaw system event --text \"Done: [brief description]\" --mode now\n```\n\nThis is what makes the whole approach work. The task signals completion; your agent doesn't need to guess.\n\n## Modes\n\n| Mode | Flag | Behavior |\n|------|------|----------|\n| auto | `--mode auto` | Full permissions, runs freely (default) |\n\n## Design Choices\n\n- **Isolated tmux socket** (`-L cc`) — doesn't interfere with your tmux sessions\n- **`cc-` prefix** on all sessions — easy to list\u002Ffilter\n- **Bracketed paste** for multi-line prompts — no escaping issues\n- **JSON output** from list\u002Fmonitor — agent-friendly, fewer tokens to parse\n\n## Files\n\n| Script | Purpose |\n|--------|---------|\n| `scripts\u002Fstart.sh` | Launch CC in tmux with task |\n| `scripts\u002Fmonitor.sh` | Lightweight output capture |\n| `scripts\u002Fsend.sh` | Send prompts \u002F compact \u002F approve |\n| `scripts\u002Flist.sh` | List active sessions |\n| `scripts\u002Fstop.sh` | Kill sessions |\n","# Claude Code Pro ⚡\n\nProduction-grade Claude Code workflow that doesn't waste your tokens.\n\n## The Problem with Other Skills\n\nMost Claude Code tmux skills work like this:\n```\nStart task → Poll every 30s → Poll → Poll → Poll → Done\n                 🔥 tokens      🔥       🔥       🔥\n```\n\nEach poll reads 100-200 lines of terminal output, feeds it to your agent, and burns tokens deciding \"is it done yet?\" A 20-minute task = 40 polls = thousands of wasted tokens.\n\n## How This Skill Works\n\n```\nStart task (with callback) → Wait → 📩 Notification → Read result (50 lines)\n                               😴 zero tokens          ⚡ one read\n```\n\n**The task itself tells you when it's done.** Your agent sleeps until notified. One lightweight check confirms the result. That's it.\n\n### Token Savings Breakdown\n\n| Approach | 20-min task | Tokens burned |\n|----------|-------------|---------------|\n| Poll every 30s | 40 reads × ~500 tokens | **~20,000** |\n| Poll every 60s | 20 reads × ~500 tokens | **~10,000** |\n| **This skill** | 1 notification + 1 read | **~500** |\n\n**80-97% token savings** on supervision alone.\n\n## Smart Dispatch: Know When NOT to Start\n\nBefore spawning Claude Code, ask:\n\n| Situation | Action |\n|-----------|--------|\n| \u003C 3 files involved | **Don't start CC.** Just read + edit directly. |\n| Single bug fix | **Don't start CC.** Faster to fix inline. |\n| Need extensive context exploration | ✅ Start CC |\n| Multi-file refactor | ✅ Start CC |\n| New feature (5+ files) | ✅ Start CC |\n\nThe fastest token savings come from not spawning a session at all.\n\n## Quick Start\n\n```bash\n# Start a task — note the callback at the end\nbash {baseDir}\u002Fscripts\u002Fstart.sh --label auth-refactor --workdir ~\u002Fproject --task \"Refactor auth module to use JWT.\n\nWhen completely finished, run: openclaw system event --text \\\"Done: JWT auth refactor complete\\\" --mode now\"\n```\n\nThat's the key line: `openclaw system event --text \"Done: ...\" --mode now`. The task notifies your agent on completion. No polling needed.\n\n### Task from file (complex requirements)\n\n```bash\nbash {baseDir}\u002Fscripts\u002Fstart.sh --label my-feature --workdir ~\u002Fproject \\\n  --task-file \u002Fpath\u002Fto\u002Frequirements.md --mode auto\n```\n\nWrite detailed requirements once upfront → fewer mid-task corrections → fewer tokens.\n\n## Monitor (Only When Needed)\n\n```bash\n# Lightweight check — 50 lines, minimal tokens\nbash {baseDir}\u002Fscripts\u002Fmonitor.sh --session my-task --lines 50\n\n# JSON mode — structured, even fewer tokens for agent parsing\nbash {baseDir}\u002Fscripts\u002Fmonitor.sh --session my-task --json\n\n# Send follow-up (use sparingly — write requirements upfront instead)\nbash {baseDir}\u002Fscripts\u002Fsend.sh --session my-task --text \"Also add unit tests\"\n\n# Compact context when running long\nbash {baseDir}\u002Fscripts\u002Fsend.sh --session my-task --compact\n```\n\n## Manage Sessions\n\n```bash\n# List all active sessions\nbash {baseDir}\u002Fscripts\u002Flist.sh          # human-readable\nbash {baseDir}\u002Fscripts\u002Flist.sh --json   # structured\n\n# Stop sessions\nbash {baseDir}\u002Fscripts\u002Fstop.sh --session my-task\nbash {baseDir}\u002Fscripts\u002Fstop.sh --all\n```\n\n## Attach (Human SSH Access)\n\n```bash\ntmux -L cc attach -t cc-\u003Clabel>\n```\n\n## Agent Workflow\n\n```\n1. DECIDE — Is this a 3+ file task? No → just edit. Yes → continue.\n2. START — start.sh with detailed task + completion callback\n3. WAIT — Do other work. Zero tokens spent watching.\n4. NOTIFIED — Receive \"Done: ...\" event\n5. CHECK — monitor.sh --lines 50 to confirm result\n6. CLEANUP — stop.sh to end session\n```\n\n**Fallback:** If no notification after 15 minutes, one lightweight poll with `--json`.\n\n## Completion Callback Template\n\nAlways append to your task prompt:\n\n```\nWhen completely finished, run this command to notify:\nopenclaw system event --text \"Done: [brief description]\" --mode now\n```\n\nThis is what makes the whole approach work. The task signals completion; your agent doesn't need to guess.\n\n## Modes\n\n| Mode | Flag | Behavior |\n|------|------|----------|\n| auto | `--mode auto` | Full permissions, runs freely (default) |\n\n## Design Choices\n\n- **Isolated tmux socket** (`-L cc`) — doesn't interfere with your tmux sessions\n- **`cc-` prefix** on all sessions — easy to list\u002Ffilter\n- **Bracketed paste** for multi-line prompts — no escaping issues\n- **JSON output** from list\u002Fmonitor — agent-friendly, fewer tokens to parse\n\n## Files\n\n| Script | Purpose |\n|--------|---------|\n| `scripts\u002Fstart.sh` | Launch CC in tmux with task |\n| `scripts\u002Fmonitor.sh` | Lightweight output capture |\n| `scripts\u002Fsend.sh` | Send prompts \u002F compact \u002F approve |\n| `scripts\u002Flist.sh` | List active sessions |\n| `scripts\u002Fstop.sh` | Kill sessions |\n",{"name":5,"metadata":24,"description":36},{"openclaw":25},{"os":26,"emoji":29,"requires":30},[27,28],"darwin","linux","⚡",{"bins":31,"anyBins":34},[32,33],"tmux","bash",[35],"claude","Token-efficient Claude Code workflow. Other skills burn tokens polling tmux every 30s —  this one uses completion callbacks and only checks when notified. Observable tmux sessions, smart dispatch rules (know when NOT to spawn Claude Code), and structured JSON monitoring. Saves 80%+ supervision tokens vs polling-based approaches. Use when: multi-file coding tasks that need background execution. NOT for: simple single-file fixes (just read+edit directly — that's the point). Requires: tmux, claude CLI.\n","main","f9d3fe7cf9ac8f1ea63a0d96e98e1f510a3814db","skills\u002Fswaylq\u002Fclaude-code-pro",1,"https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills","https:\u002F\u002Fgithub.com\u002Fjavimosch","intrane.fr","Building robust, open-source infrastructure for the commons. AI-leveraged, self-hosted, built to last.","2026-06-07 03:34:58",{"source":8,"skillName":5,"commands":47,"prompt":57,"zipAvailable":58},[48,51,54],{"tool":49,"command":50},"npx","npx skills add javimosch\u002Fopen-claw-skills --skill claude-code-pro",{"tool":52,"command":53},"bunx","bunx skills add javimosch\u002Fopen-claw-skills --skill claude-code-pro",{"tool":55,"command":56},"pnpm","pnpm dlx skills add javimosch\u002Fopen-claw-skills --skill claude-code-pro","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fswaylq\u002Fclaude-code-pro\u002FSKILL.md",true,[],[61,69,76,83,90,97],{"skillNo":62,"name":63,"nameZh":6,"description":64,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":65,"categories":66,"keywords":67,"publishedAt":68},"01M778GGXG2VQ0YF31W2MKGMQZ","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\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fzzadrian\u002Fcrowd-prompting\u002FSKILL.md",[],[],"2026-11-15 14:19:17",{"skillNo":70,"name":71,"nameZh":6,"description":72,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":75,"publishedAt":68},"01M778G7BH8SBJ9FJ6C3G7CB1K","ceaser","Interact with the Ceaser privacy protocol on Base L2 using the ceaser-mcp MCP tools. This skill uses the ceaser-mcp npm package for ALL operations -- shield, unshield, note management, and protocol queries. All ceaser tool calls use CLI subcommands (npx -y ceaser-mcp \u003Csubcommand>). Ceaser is a privacy-preserving ETH wrapper using Noir\u002FUltraHonk zero-knowledge proofs on Base L2 (chain ID 8453).","https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fzyra-v21\u002Fceaser\u002FSKILL.md",[],[],{"skillNo":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"publishedAt":68},"01M778FYCJQZWFKKX5FYMK3S47","ceaser-send","Fully automated private ETH transfer via Ceaser Protocol on Base L2 using the ceaser-mcp MCP tools. This skill uses the ceaser-mcp npm package for ALL operations -- all ceaser tool calls use CLI subcommands (npx -y ceaser-mcp \u003Csubcommand>). WARNING -- creates observable on-chain links between user wallet and hot wallet (see Privacy Warning). Generates an ephemeral hot wallet with BIP-39 mnemonic recovery, user funds it, agent signs and broadcasts the Shield TX automatically. Exactly one manual step required (funding the hot wallet with ETH). Uses Noir\u002FUltraHonk zero-knowledge proofs.","https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fzyra-v21\u002Fceaser-send\u002FSKILL.md",[],[],{"skillNo":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"publishedAt":68},"01M778FQQNSEYA3HJKZBPQ4M9Z","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\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fzyori\u002Fdilemm-ai\u002FSKILL.md",[],[],{"skillNo":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":96,"publishedAt":68},"01M778FGVZX7QA2TF9BFMM37FY","moldium","Post and manage content on the Moldium blog platform. Triggered by \"post to Moldium\", \"write a blog post\", \"publish an article\", etc.","https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fzyom45\u002Fmoldium\u002FSKILL.md",[],[],{"skillNo":98,"name":99,"nameZh":6,"description":100,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":101,"categories":102,"keywords":103,"publishedAt":68},"01M778F88D8PQ9MQ0KNW2TJ8ZH","arxiv-paper-reviews","Interact with arXiv Crawler API to fetch papers, read reviews, submit comments, search papers, and import papers. Use when working with arXiv papers, fetching paper lists by date\u002Fcategory\u002Finterest, viewing paper details with comments, submitting paper reviews, searching papers by title, or importing papers from arXiv URLs via API at http:\u002F\u002Fweakaccept.top:8000\u002F.","https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fzxrys\u002Farxiv-paper-reviews\u002FSKILL.md",[],[]]