[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6FT2336BGGSTH5Q005JD11E":3,"skill-same:01M6FT2336BGGSTH5Q005JD11E":64},{"skillNo":4,"name":5,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":6,"repositoryNo":11,"starsCount":12,"licenseSpdxId":13,"licenseFileUrl":6,"sourceHtmlUrl":14,"categories":15,"keywords":21,"publishedAt":23,"linkOnly":24,"markdownContent":25,"markdownBody":25,"frontMatter":26,"refName":27,"commitSha":28,"skillDirectory":29,"forksCount":30,"repositoryHtmlUrl":31,"repositoryHomepageUrl":6,"ownerHtmlUrl":32,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":33,"install":34,"resources":47},"01M6FT2336BGGSTH5Q005JD11E","wreckit-skill",null,"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\u002Fjmanhype\u002Fwreckit-skill\u002FSKILL.md",[16],{"categoryNo":17,"categoryName":18,"taxonomyType":19,"taxonomyTypeDesc":20},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[22],"wreckit skill","2026-11-10 10:12:30",false,"# Wreckit Skill (jmanhype Fork)\n\n> **First time?** Read [SETUP.md](.\u002FSETUP.md) first to install the Wreckit CLI from the jmanhype fork.\n\nConnects Clawdbot to the **jmanhype fork of Wreckit**, the Autonomic Software Factory. This version is optimized for **Cattle Architecture** (Ephemeral Sprite VMs) and high-concurrency loops.\n\n**Script:** `skills\u002Fwreckit\u002Fscripts\u002Frun-wreckit.mjs`\n**Engine:** `wreckit` (Global CLI from jmanhype\u002Fwreckit)\n\n---\n\n## Trigger Phrases\n\nWhen human says:\n\n| Phrase | Action |\n|--------|--------|\n| **\"Wreckit status\"** | List all items and their current states |\n| **\"Wreckit run [ID]\"** | Start the autonomous loop (Default: Cattle Mode) |\n| **\"Wreckit run [ID] mode pet\"** | Run locally without Sprites (Faster, less secure) |\n| **\"Wreckit dream\"** | Autonomous ideation (Self-Roadmapping) |\n| **\"Wreckit doctor\"** | Self-healing diagnostics and repair |\n| **\"Wreckit rollback [ID]\"** | Rollback a direct-merge item to its pre-merge state |\n| **\"Wreckit next\"** | Process the next incomplete item in sequence |\n| **\"Wreckit learn\"** | Extract patterns from completed items and compile skills |\n| **\"Wreckit summarize\"** | Generate visualization videos for completed items |\n| **\"Wreckit geneticist\"** | Analyze failure patterns and optimize system prompts |\n\n---\n\n## The \"Cattle\" Advantage (Default)\nUnlike standard agent loops, this version of Wreckit uses **Ephemeral Sprite VMs**. Every task spins up a fresh Firecracker microVM, executes code in isolation, and vanishes. No state contamination, maximum security.\n\n## The \"Pet\" Mode (Local)\nIf you need raw speed or are debugging locally, say **\"mode pet\"**. This runs the RLM agent directly on the host machine.\n\n---\n\n## Usage Guide\n\n### 1. Checking Status\n> **User:** \"Wreckit status\"\n> **Bot:** Lists all active items (Idea, Planned, In Progress, Done).\n\n### 2. Running a Task\n> **User:** \"Wreckit run 096\"\n> **Bot:** \"Starting Wreckit run for item 096... [Streams logs] ... Done.\"\n\n### 3. Dreaming (Autonomy)\n> **User:** \"Wreckit dream\"\n> **Bot:** Scans your codebase for technical debt and creates new items automatically.\n\n### 4. Rollback\n> **User:** \"Wreckit rollback 096\"\n> **Bot:** Reverts item 096 to its pre-merge state using git operations.\n>\n> **With force:** \"Wreckit rollback 096 force\" - Forces rollback even if item is not in 'done' state.\n\n### 5. Next Item\n> **User:** \"Wreckit next\"\n> **Bot:** Processes the single next runnable item with dependency satisfaction.\n\n### 6. Learn (Pattern Extraction)\n> **User:** \"Wreckit learn all\"\n> **Bot:** Extracts patterns from all completed items and compiles them into skills.\n>\n> **Specific item:** \"Wreckit learn item 096\"\n> **By phase:** \"Wreckit learn phase done\"\n\n### 7. Summarize (Video Generation)\n> **User:** \"Wreckit summarize all\"\n> **Bot:** Generates 30-second feature visualization videos for all completed items.\n>\n> **Specific item:** \"Wreckit summarize item 096\"\n> **By phase:** \"Wreckit summarize phase done\"\n\n### 8. Geneticist (Prompt Optimization)\n> **User:** \"Wreckit geneticist\"\n> **Bot:** Analyzes healing logs from the last 48 hours to identify and fix recurrent error patterns.\n>\n> **Custom window:** \"Wreckit geneticist time-window 24 min-errors 5\"\n\n---\n\n## Advanced Flags\n\n### Global Flags (apply to all commands)\n- **`--cwd \u003Cpath>`** - Override the working directory\n- **`--parallel \u003Cn>`** - Process N items in parallel (default: 1)\n- **`--verbose`** - Enable verbose output\n- **`--dry-run`** - Show what would be done without making changes\n\n### Mode Selection\n- **`--mode cattle`** (default) - Use ephemeral Sprite VMs\n- **`--mode pet`** - Run locally without Sprites\n\n### Command-Specific Flags\n\n#### Rollback\n- **`--force`** - Force rollback even if item is not in 'done' state\n\n#### Learn\n- **`--item \u003Cid>`** - Extract patterns from specific item\n- **`--phase \u003Cstate>`** - Extract patterns from items in specific phase state\n- **`--all`** - Extract patterns from all completed items\n- **`--output \u003Cpath>`** - Output path for skills.json (default: .wreckit\u002Fskills.json)\n- **`--merge \u003Cstrategy>`** - Merge strategy: append|replace|ask (default: append)\n- **`--review`** - Review extracted skills before saving\n\n#### Summarize\n- **`--item \u003Cid>`** - Generate video for specific item\n- **`--phase \u003Cstate>`** - Generate videos for items in specific state\n- **`--all`** - Generate videos for all completed items\n\n#### Geneticist\n- **`--auto-merge`** - Automatically submit PRs for optimized prompts\n- **`--time-window \u003Chours>`** - Analyze healing logs from last N hours (default: 48)\n- **`--min-errors \u003Ccount>`** - Threshold for recurrent pattern detection (default: 3)\n\n---\n\n## Configuration\n\nThis skill assumes `wreckit` is installed globally or available in the path.\nIf running in Docker, ensure the container has access to the project directory.\n\n### Parallel Processing\nWhen using `--parallel` flag with commands that process multiple items (like `learn --all` or `summarize --all`), the wrapper will process N items concurrently. For bot safety, default is 1 (sequential processing).\n\n### Working Directory Override\nUse `--cwd` to specify a different project directory than the current working directory. This is useful for managing multiple projects or operating in a containerized environment.\n",{},"main","e7e336ac628c3e3bd771aff1aaa469c93778f94a","skills\u002Fjmanhype\u002Fwreckit-skill",0,"https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills","https:\u002F\u002Fgithub.com\u002Fkbarbel640-del","2026-08-23 22:39:37",{"source":7,"skillName":5,"commands":35,"prompt":45,"zipAvailable":46},[36,39,42],{"tool":37,"command":38},"npx","npx skills add kbarbel640-del\u002Fskills --skill wreckit-skill",{"tool":40,"command":41},"bunx","bunx skills add kbarbel640-del\u002Fskills --skill wreckit-skill",{"tool":43,"command":44},"pnpm","pnpm dlx skills add kbarbel640-del\u002Fskills --skill wreckit-skill","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fjmanhype\u002Fwreckit-skill\u002FSKILL.md",true,[48,54,60],{"path":49,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":52,"sourceHtmlUrl":53},"_meta.json","REFERENCE","参考文档",274,"https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fjmanhype\u002Fwreckit-skill\u002F_meta.json",{"path":55,"resourceType":56,"resourceTypeDesc":57,"sizeBytes":58,"sourceHtmlUrl":59},"scripts\u002Frun-wreckit.mjs","SCRIPT","脚本",5011,"https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fjmanhype\u002Fwreckit-skill\u002Fscripts\u002Frun-wreckit.mjs",{"path":61,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":62,"sourceHtmlUrl":63},"SETUP.md",1288,"https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fjmanhype\u002Fwreckit-skill\u002FSETUP.md",[65,96,121,142,148,168],{"skillNo":66,"name":67,"nameZh":6,"description":68,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":6,"repositoryNo":11,"starsCount":12,"licenseSpdxId":13,"licenseFileUrl":6,"sourceHtmlUrl":69,"categories":70,"keywords":76,"publishedAt":23},"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",[71],{"categoryNo":72,"categoryName":73,"taxonomyType":74,"taxonomyTypeDesc":75},"01JBSEEDCAT000000000000036","内容创作者","PROFESSION","适用职业",[77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95],"crowd prompting","prompting","api","with","tokens","domain","world","prompts","operations","instructions","text","tool","system","improve","productivity","marketplace","https","content","ai agents",{"skillNo":97,"name":98,"nameZh":6,"description":99,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":6,"repositoryNo":11,"starsCount":12,"licenseSpdxId":13,"licenseFileUrl":6,"sourceHtmlUrl":100,"categories":101,"keywords":103,"publishedAt":23},"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",[102],{"categoryNo":17,"categoryName":18,"taxonomyType":19,"taxonomyTypeDesc":20},[104,79,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,84,120],"dilemm ai","arena","analyze","browser","openclaw agent","create","automation","browser automation","bot","openclaw","design","strategy","headless","compete","submit","matchmaking","use",{"skillNo":122,"name":123,"nameZh":6,"description":124,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":6,"repositoryNo":11,"starsCount":12,"licenseSpdxId":13,"licenseFileUrl":6,"sourceHtmlUrl":125,"categories":126,"keywords":130,"publishedAt":23},"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",[127],{"categoryNo":128,"categoryName":129,"taxonomyType":19,"taxonomyTypeDesc":20},"01JBSEEDCAT000000000000021","资料检索与研究",[131,132,133,134,135,136,137,80,138,118,120,139,79,140,141],"arxiv paper reviews","reviews","arxiv","paper","crawler","papers","comments","fetch","read","http","via",{"skillNo":143,"name":123,"nameZh":6,"description":124,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":6,"repositoryNo":11,"starsCount":12,"licenseSpdxId":13,"licenseFileUrl":6,"sourceHtmlUrl":144,"categories":145,"keywords":147,"publishedAt":23},"01M6G8HQJ7N7WMY6YV7D7SSJ16","https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fzxrys\u002Farxiv-paper-reviews\u002FSKILL.md",[146],{"categoryNo":128,"categoryName":129,"taxonomyType":19,"taxonomyTypeDesc":20},[134,133,132,131,141,136,137,80,135,118,120,138,139,79,140],{"skillNo":149,"name":150,"nameZh":6,"description":151,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":6,"repositoryNo":11,"starsCount":12,"licenseSpdxId":13,"licenseFileUrl":6,"sourceHtmlUrl":152,"categories":153,"keywords":154,"publishedAt":23},"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",[],[155,156,157,158,159,160,161,162,163,164,165,166,167],"git","summary","git summary","commits","repository","win32","status","linux","contributors","true","quick","get","branches",{"skillNo":169,"name":170,"nameZh":6,"description":171,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":6,"repositoryNo":11,"starsCount":12,"licenseSpdxId":13,"licenseFileUrl":6,"sourceHtmlUrl":172,"categories":173,"keywords":178,"publishedAt":23},"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",[174,175],{"categoryNo":17,"categoryName":18,"taxonomyType":19,"taxonomyTypeDesc":20},{"categoryNo":176,"categoryName":177,"taxonomyType":74,"taxonomyTypeDesc":75},"01JBSEEDCAT000000000000037","律师与法务",[179,180,181,182,80,183,184,27,185,139,186,187,188,189,190,93,191,192,193],"agent constitution","constitution","contracts","tree","query","base","log","check","Rules","projects","compliance","actions","state","governance","github"]