[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M75F1353PCH32CG4P8SC4R6J":3,"skill-same:01M75F1353PCH32CG4P8SC4R6J":47},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":24,"commitSha":25,"skillDirectory":26,"forksCount":27,"repositoryHtmlUrl":28,"repositoryHomepageUrl":29,"ownerHtmlUrl":30,"ownerBlogUrl":31,"ownerDescription":6,"updatedAt":32,"install":33,"resources":46},"01M75F1353PCH32CG4P8SC4R6J","learner",null,"Extract a learned skill from the current conversation","agisota\u002Fold-one","agisota","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F121413592?v=4","01M75B4BRNT67EC1NDRT8QZEP2","01M75B4BS7QR9VP580MSCPTS3X",3,"MIT","https:\u002F\u002Fgithub.com\u002Fagisota\u002Fold-one\u002Fblob\u002Fmain\u002Fskills\u002Flearner\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: learner\ndescription: Extract a learned skill from the current conversation\nlevel: 7\n---\n\n# Learner Skill\n\nThis is a Level 7 (self-improving) skill. It has two distinct sections:\n- **Expertise**: Domain knowledge about what makes a good skill. Updated automatically as patterns are discovered.\n- **Workflow**: Stable extraction procedure. Rarely changes.\n\nOnly the Expertise section should be updated during improvement cycles.\n\n---\n\n## Expertise\n\n> This section contains domain knowledge that improves over time.\n> It can be updated by the learner itself when new patterns are discovered.\n\n### Core Principle\n\nReusable skills are not code snippets to copy-paste, but **principles and decision-making heuristics** that teach Claude HOW TO THINK about a class of problems.\n\n**The difference:**\n- BAD (mimicking): \"When you see ConnectionResetError, add this try\u002Fexcept block\"\n- GOOD (reusable skill): \"In async network code, any I\u002FO operation can fail independently due to client\u002Fserver lifecycle mismatches. The principle: wrap each I\u002FO operation separately, because failure between operations is the common case, not the exception.\"\n\n### Quality Gate\n\nBefore extracting a skill, ALL three must be true:\n- \"Could someone Google this in 5 minutes?\" → NO\n- \"Is this specific to THIS codebase?\" → YES\n- \"Did this take real debugging effort to discover?\" → YES\n\n### Recognition Signals\n\nExtract ONLY after:\n- Solving a tricky bug that required deep investigation\n- Discovering a non-obvious workaround specific to this codebase\n- Finding a hidden gotcha that wastes time when forgotten\n- Uncovering undocumented behavior that affects this project\n\n### What Makes a USEFUL Skill\n\n1. **Non-Googleable**: Something you couldn't easily find via search\n   - BAD: \"How to read files in TypeScript\" ❌\n   - GOOD: \"This codebase uses custom path resolution in ESM that requires fileURLToPath + specific relative paths\" ✓\n\n2. **Context-Specific**: References actual files, error messages, or patterns from THIS codebase\n   - BAD: \"Use try\u002Fcatch for error handling\" ❌\n   - GOOD: \"The aiohttp proxy in server.py:42 crashes on ClientDisconnectedError - wrap StreamResponse in try\u002Fexcept\" ✓\n\n3. **Actionable with Precision**: Tells you exactly WHAT to do and WHERE\n   - BAD: \"Handle edge cases\" ❌\n   - GOOD: \"When seeing 'Cannot find module' in dist\u002F, check tsconfig.json moduleResolution matches package.json type field\" ✓\n\n4. **Hard-Won**: Took significant debugging effort to discover\n   - BAD: Generic programming patterns ❌\n   - GOOD: \"Race condition in worker.ts - the Promise.all at line 89 needs await before the map callback returns\" ✓\n\n### Anti-Patterns (DO NOT EXTRACT)\n\n- Generic programming patterns (use documentation instead)\n- Refactoring techniques (these are universal)\n- Library usage examples (use library docs)\n- Type definitions or boilerplate\n- Anything a junior dev could Google in 5 minutes\n\n---\n\n## Workflow\n\n> This section contains the stable extraction procedure.\n> It should NOT be updated during improvement cycles.\n\n### Step 1: Gather Required Information\n\n- **Problem Statement**: The SPECIFIC error, symptom, or confusion that occurred\n  - Include actual error messages, file paths, line numbers\n  - Example: \"TypeError in src\u002Fhooks\u002Fsession.ts:45 when sessionId is undefined after restart\"\n\n- **Solution**: The EXACT fix, not general advice\n  - Include code snippets, file paths, configuration changes\n  - Example: \"Add null check before accessing session.user, regenerate session on 401\"\n\n- **Triggers**: Keywords that would appear when hitting this problem again\n  - Use error message fragments, file names, symptom descriptions\n  - Example: [\"sessionId undefined\", \"session.ts TypeError\", \"401 session\"]\n\n- **Scope**: Almost always Project-level unless it's a truly universal insight\n\n### Step 2: Quality Validation\n\nThe system REJECTS skills that are:\n- Too generic (no file paths, line numbers, or specific error messages)\n- Easily Googleable (standard patterns, library usage)\n- Vague solutions (no code snippets or precise instructions)\n- Poor triggers (generic words that match everything)\n\n### Step 3: Classify as Expertise or Workflow\n\nBefore saving, determine if the learning is:\n- **Expertise** (domain knowledge, pattern, gotcha) → Save as `{topic}-expertise.md`\n- **Workflow** (operational procedure, step sequence) → Save as `{topic}-workflow.md`\n\nThis classification ensures expertise can be updated independently without destabilizing workflows.\n\n### Step 4: Save Location\n\n- **User-level**: `${CLAUDE_CONFIG_DIR:-~\u002F.claude}\u002Fskills\u002Fomc-learned\u002F\u003Cskill-name>.md` - Rare. Only for truly portable insights.\n- **Project-level**: `.omc\u002Fskills\u002F\u003Cskill-name>.md` - Default. Version-controlled with repo.\n\n### Required File Format\n\nEvery learned skill file MUST start with YAML frontmatter so learned-skill flat-file discovery can load it.\nDo **not** write plain markdown without frontmatter.\n\nMinimum required frontmatter:\n\n```yaml\n---\nname: \u003Cskill-name>\ndescription: \u003Cone-line description>\ntriggers:\n  - \u003Ctrigger-1>\n  - \u003Ctrigger-2>\n---\n```\n\n### Skill Body Template\n\n```markdown\n---\nname: \u003Cskill-name>\ndescription: \u003Cone-line description>\ntriggers:\n  - \u003Ctrigger-1>\n  - \u003Ctrigger-2>\n---\n\n# [Skill Name]\n\n## The Insight\nWhat is the underlying PRINCIPLE you discovered? Not the code, but the mental model.\n\n## Why This Matters\nWhat goes wrong if you don't know this? What symptom led you here?\n\n## Recognition Pattern\nHow do you know when this skill applies? What are the signs?\n\n## The Approach\nThe decision-making heuristic, not just code. How should Claude THINK about this?\n\n## Example (Optional)\nIf code helps, show it - but as illustration of the principle, not copy-paste material.\n```\n\n**Key**: A skill is REUSABLE if Claude can apply it to NEW situations, not just identical ones.\n\n## Related Commands\n\n- \u002Foh-my-claudecode:note - Save quick notes that survive compaction (less formal than skills)\n- \u002Foh-my-claudecode:ralph - Start a development loop with learning capture\n","# Learner Skill\n\nThis is a Level 7 (self-improving) skill. It has two distinct sections:\n- **Expertise**: Domain knowledge about what makes a good skill. Updated automatically as patterns are discovered.\n- **Workflow**: Stable extraction procedure. Rarely changes.\n\nOnly the Expertise section should be updated during improvement cycles.\n\n---\n\n## Expertise\n\n> This section contains domain knowledge that improves over time.\n> It can be updated by the learner itself when new patterns are discovered.\n\n### Core Principle\n\nReusable skills are not code snippets to copy-paste, but **principles and decision-making heuristics** that teach Claude HOW TO THINK about a class of problems.\n\n**The difference:**\n- BAD (mimicking): \"When you see ConnectionResetError, add this try\u002Fexcept block\"\n- GOOD (reusable skill): \"In async network code, any I\u002FO operation can fail independently due to client\u002Fserver lifecycle mismatches. The principle: wrap each I\u002FO operation separately, because failure between operations is the common case, not the exception.\"\n\n### Quality Gate\n\nBefore extracting a skill, ALL three must be true:\n- \"Could someone Google this in 5 minutes?\" → NO\n- \"Is this specific to THIS codebase?\" → YES\n- \"Did this take real debugging effort to discover?\" → YES\n\n### Recognition Signals\n\nExtract ONLY after:\n- Solving a tricky bug that required deep investigation\n- Discovering a non-obvious workaround specific to this codebase\n- Finding a hidden gotcha that wastes time when forgotten\n- Uncovering undocumented behavior that affects this project\n\n### What Makes a USEFUL Skill\n\n1. **Non-Googleable**: Something you couldn't easily find via search\n   - BAD: \"How to read files in TypeScript\" ❌\n   - GOOD: \"This codebase uses custom path resolution in ESM that requires fileURLToPath + specific relative paths\" ✓\n\n2. **Context-Specific**: References actual files, error messages, or patterns from THIS codebase\n   - BAD: \"Use try\u002Fcatch for error handling\" ❌\n   - GOOD: \"The aiohttp proxy in server.py:42 crashes on ClientDisconnectedError - wrap StreamResponse in try\u002Fexcept\" ✓\n\n3. **Actionable with Precision**: Tells you exactly WHAT to do and WHERE\n   - BAD: \"Handle edge cases\" ❌\n   - GOOD: \"When seeing 'Cannot find module' in dist\u002F, check tsconfig.json moduleResolution matches package.json type field\" ✓\n\n4. **Hard-Won**: Took significant debugging effort to discover\n   - BAD: Generic programming patterns ❌\n   - GOOD: \"Race condition in worker.ts - the Promise.all at line 89 needs await before the map callback returns\" ✓\n\n### Anti-Patterns (DO NOT EXTRACT)\n\n- Generic programming patterns (use documentation instead)\n- Refactoring techniques (these are universal)\n- Library usage examples (use library docs)\n- Type definitions or boilerplate\n- Anything a junior dev could Google in 5 minutes\n\n---\n\n## Workflow\n\n> This section contains the stable extraction procedure.\n> It should NOT be updated during improvement cycles.\n\n### Step 1: Gather Required Information\n\n- **Problem Statement**: The SPECIFIC error, symptom, or confusion that occurred\n  - Include actual error messages, file paths, line numbers\n  - Example: \"TypeError in src\u002Fhooks\u002Fsession.ts:45 when sessionId is undefined after restart\"\n\n- **Solution**: The EXACT fix, not general advice\n  - Include code snippets, file paths, configuration changes\n  - Example: \"Add null check before accessing session.user, regenerate session on 401\"\n\n- **Triggers**: Keywords that would appear when hitting this problem again\n  - Use error message fragments, file names, symptom descriptions\n  - Example: [\"sessionId undefined\", \"session.ts TypeError\", \"401 session\"]\n\n- **Scope**: Almost always Project-level unless it's a truly universal insight\n\n### Step 2: Quality Validation\n\nThe system REJECTS skills that are:\n- Too generic (no file paths, line numbers, or specific error messages)\n- Easily Googleable (standard patterns, library usage)\n- Vague solutions (no code snippets or precise instructions)\n- Poor triggers (generic words that match everything)\n\n### Step 3: Classify as Expertise or Workflow\n\nBefore saving, determine if the learning is:\n- **Expertise** (domain knowledge, pattern, gotcha) → Save as `{topic}-expertise.md`\n- **Workflow** (operational procedure, step sequence) → Save as `{topic}-workflow.md`\n\nThis classification ensures expertise can be updated independently without destabilizing workflows.\n\n### Step 4: Save Location\n\n- **User-level**: `${CLAUDE_CONFIG_DIR:-~\u002F.claude}\u002Fskills\u002Fomc-learned\u002F\u003Cskill-name>.md` - Rare. Only for truly portable insights.\n- **Project-level**: `.omc\u002Fskills\u002F\u003Cskill-name>.md` - Default. Version-controlled with repo.\n\n### Required File Format\n\nEvery learned skill file MUST start with YAML frontmatter so learned-skill flat-file discovery can load it.\nDo **not** write plain markdown without frontmatter.\n\nMinimum required frontmatter:\n\n```yaml\n---\nname: \u003Cskill-name>\ndescription: \u003Cone-line description>\ntriggers:\n  - \u003Ctrigger-1>\n  - \u003Ctrigger-2>\n---\n```\n\n### Skill Body Template\n\n```markdown\n---\nname: \u003Cskill-name>\ndescription: \u003Cone-line description>\ntriggers:\n  - \u003Ctrigger-1>\n  - \u003Ctrigger-2>\n---\n\n# [Skill Name]\n\n## The Insight\nWhat is the underlying PRINCIPLE you discovered? Not the code, but the mental model.\n\n## Why This Matters\nWhat goes wrong if you don't know this? What symptom led you here?\n\n## Recognition Pattern\nHow do you know when this skill applies? What are the signs?\n\n## The Approach\nThe decision-making heuristic, not just code. How should Claude THINK about this?\n\n## Example (Optional)\nIf code helps, show it - but as illustration of the principle, not copy-paste material.\n```\n\n**Key**: A skill is REUSABLE if Claude can apply it to NEW situations, not just identical ones.\n\n## Related Commands\n\n- \u002Foh-my-claudecode:note - Save quick notes that survive compaction (less formal than skills)\n- \u002Foh-my-claudecode:ralph - Start a development loop with learning capture\n",{"name":5,"level":23,"description":7},7,"main","f37de8f681f0c0ca0e0ebab6e5fddf764ca7553d","skills\u002Flearner",1,"https:\u002F\u002Fgithub.com\u002Fagisota\u002Fold-one","https:\u002F\u002Fagisota.github.io\u002Fold-one\u002F","https:\u002F\u002Fgithub.com\u002Fagisota","pzd.world","2026-07-04 22:32:06",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":45},[35,38,41],{"tool":36,"command":37},"npx","npx skills add agisota\u002Fold-one --skill learner",{"tool":39,"command":40},"bunx","bunx skills add agisota\u002Fold-one --skill learner",{"tool":42,"command":43},"pnpm","pnpm dlx skills add agisota\u002Fold-one --skill learner","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fagisota\u002Fold-one\u002Fblob\u002Fmain\u002Fskills\u002Flearner\u002FSKILL.md",true,[],[48,55,62,71,78,85],{"skillNo":49,"name":50,"nameZh":6,"description":51,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":52,"categories":53,"keywords":54,"publishedAt":18},"01M75KRGZWQWE9JDBS6RX42NWV","zoom-out","Tell the agent to zoom out and give broader context or a higher-level perspective. Use when you're unfamiliar with a section of code or need to understand how it fits into the bigger picture.","https:\u002F\u002Fgithub.com\u002Fagisota\u002Fold-one\u002Fblob\u002Fmain\u002Fskills\u002Fzoom-out\u002FSKILL.md",[],[],{"skillNo":56,"name":57,"nameZh":6,"description":58,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":59,"categories":60,"keywords":61,"publishedAt":18},"01M75KRCZHKE0ZYAQFFYHS0YNP","zeroize-audit","Detects missing zeroization of sensitive data in source code and identifies zeroization removed by compiler optimizations, with assembly-level analysis, and control-flow verification. Use for auditing C\u002FC++\u002FRust code handling secrets, keys, passwords, or other sensitive data.","https:\u002F\u002Fgithub.com\u002Fagisota\u002Fold-one\u002Fblob\u002Fmain\u002Fskills\u002Fzeroize-audit\u002FSKILL.md",[],[],{"skillNo":63,"name":64,"nameZh":6,"description":65,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":66,"licenseFileUrl":67,"sourceHtmlUrl":68,"categories":69,"keywords":70,"publishedAt":18},"01M75KR94KYQ30DTE1P9WNDAE0","yeet","Use only when the user explicitly asks to stage, commit, push, and open a GitHub pull request in one flow using the GitHub CLI (`gh`).","Apache-2.0","https:\u002F\u002Fgithub.com\u002Fagisota\u002Fold-one\u002Fblob\u002Fmain\u002Fskills\u002Fyeet\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fagisota\u002Fold-one\u002Fblob\u002Fmain\u002Fskills\u002Fyeet\u002FSKILL.md",[],[],{"skillNo":72,"name":73,"nameZh":6,"description":74,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":75,"categories":76,"keywords":77,"publishedAt":18},"01M75KR3H13YJ9QHMD49818FA1","yara-rule-authoring","Guides authoring of high-quality YARA-X detection rules for malware identification. Use when writing, reviewing, or optimizing YARA rules. Covers naming conventions, string selection, performance optimization, migration from legacy YARA, and false positive reduction. Triggers on: YARA, YARA-X, malware detection, threat hunting, IOC, signature, crx module, dex module.","https:\u002F\u002Fgithub.com\u002Fagisota\u002Fold-one\u002Fblob\u002Fmain\u002Fskills\u002Fyara-rule-authoring\u002FSKILL.md",[],[],{"skillNo":79,"name":80,"nameZh":6,"description":81,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":82,"categories":83,"keywords":84,"publishedAt":18},"01M75KQMPY8A4Y8XTDD2DT0M9T","x-twitter-growth","X\u002FTwitter growth engine for building audience, crafting viral content, and analyzing engagement. Use when the user wants to grow on X\u002FTwitter, write tweets or threads, analyze their X profile, research competitors on X, plan a posting strategy, or optimize engagement. Complements social-content (generic multi-platform) with X-specific depth: algorithm mechanics, thread engineering, reply strategy, profile optimization, and competitive intelligence via web search.","https:\u002F\u002Fgithub.com\u002Fagisota\u002Fold-one\u002Fblob\u002Fmain\u002Fskills\u002Fx-twitter-growth\u002FSKILL.md",[],[],{"skillNo":86,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":89,"categories":90,"keywords":91,"publishedAt":18},"01M75KQHNZ0ANZNJGZY6M8MDAK","x-api","X\u002FTwitter API integration for posting tweets, threads, reading timelines, search, and analytics. Covers OAuth auth patterns, rate limits, and platform-native content posting. Use when the user wants to interact with X programmatically.","https:\u002F\u002Fgithub.com\u002Fagisota\u002Fold-one\u002Fblob\u002Fmain\u002Fskills\u002Fx-api\u002FSKILL.md",[],[]]