[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M75DCGWVG07FTZ8WM414GEMD":3,"skill-same:01M75DCGWVG07FTZ8WM414GEMD":48},{"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":25,"commitSha":26,"skillDirectory":27,"forksCount":28,"repositoryHtmlUrl":29,"repositoryHomepageUrl":30,"ownerHtmlUrl":31,"ownerBlogUrl":32,"ownerDescription":6,"updatedAt":33,"install":34,"resources":47},"01M75DCGWVG07FTZ8WM414GEMD","enhance-prompts",null,"Use when improving general prompts for structure, examples, and constraints.","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\u002Fenhance-prompts\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: enhance-prompts\ndescription: \"Use when improving general prompts for structure, examples, and constraints.\"\nversion: 5.1.0\nargument-hint: \"[path] [--fix]\"\n---\n\n# enhance-prompts\n\nAnalyze prompts for clarity, structure, examples, and output reliability.\n\n## Parse Arguments\n\n```javascript\nconst args = '$ARGUMENTS'.split(' ').filter(Boolean);\nconst targetPath = args.find(a => !a.startsWith('--')) || '.';\nconst fix = args.includes('--fix');\n```\n\n## Differentiation from enhance-agent-prompts\n\n| Skill | Focus | Use When |\n|-------|-------|----------|\n| `enhance-prompts` | Prompt quality (clarity, structure, examples) | General prompts, system prompts, templates |\n| `enhance-agent-prompts` | Agent config (frontmatter, tools, model) | Agent files with YAML frontmatter |\n\n## Workflow\n\n1. **Run Analyzer** - Execute the JavaScript analyzer to get findings:\n   ```bash\n   node -e \"const a = require('.\u002Flib\u002Fenhance\u002Fprompt-analyzer.js'); console.log(JSON.stringify(a.analyzeAllPrompts('.'), null, 2));\"\n   ```\n   For a specific path: `a.analyzeAllPrompts('.\u002Fplugins\u002Fenhance')`\n   For a single file: `a.analyzePrompt('.\u002Fpath\u002Fto\u002Ffile.md')`\n\n2. **Parse Results** - The analyzer returns JSON with `summary` and `findings`\n3. **Filter** - Apply certainty filtering based on --verbose flag\n4. **Report** - Format findings as markdown output\n5. **Fix** - If --fix flag, apply auto-fixes from findings\n\nThe JavaScript analyzer (`lib\u002Fenhance\u002Fprompt-analyzer.js`) implements all detection patterns including AST-based code validation. The patterns below are reference documentation.\n\n---\n\n## Prompt Engineering Knowledge Reference\n\n### System Prompt Structure\n\nEffective system prompts include: Role\u002FIdentity, Capabilities & Constraints, Instruction Priority, Output Format, Behavioral Directives, Examples, Error Handling.\n\n**Minimal Template:**\n```xml\n\u003Csystem>\nYou are [ROLE]. [PURPOSE].\nKey constraints: [CONSTRAINTS]\nOutput format: [FORMAT]\nWhen uncertain: [HANDLING]\n\u003C\u002Fsystem>\n```\n\n### XML Tags (Claude-Specific)\n\nClaude is fine-tuned for XML tags. Use: `\u003Crole>`, `\u003Cconstraints>`, `\u003Coutput_format>`, `\u003Cexamples>`, `\u003Cinstructions>`, `\u003Ccontext>`\n\n```xml\n\u003Cconstraints>\n- Maximum response length: 500 words\n- Use only Python 3.10+ syntax\n\u003C\u002Fconstraints>\n```\n\n### Few-Shot Examples\n\n- 2-5 examples is optimal (research-backed)\n- Include edge cases and ensure format consistency\n- Start zero-shot, add examples only if needed\n- Show both good AND bad examples when relevant\n\n### Chain-of-Thought (CoT)\n\n| Use CoT | Don't Use CoT |\n|---------|---------------|\n| Complex multi-step reasoning | Simple factual questions |\n| Math and logic problems | Classification tasks |\n| Code debugging | When model has built-in reasoning |\n\n**Key:** Modern models (Claude 4.x, o1\u002Fo3) perform CoT internally. \"Think step by step\" is redundant.\n\n### Role Prompting\n\n**Helps:** Creative tasks, tone\u002Fstyle, roleplay\n**Doesn't help:** Accuracy tasks, factual retrieval, complex reasoning\n\nBetter: \"Approach systematically, showing work\" vs \"You are an expert\"\n\n### Instruction Hierarchy\n\nPriority: System > Developer > User > Retrieved Content\n\nInclude explicit priority in prompts with multiple constraint sources.\n\n### Negative Prompting\n\nPositive alternatives are more effective than negatives:\n\n| Less Effective | More Effective |\n|----------------|----------------|\n| \"Don't use markdown\" | \"Use prose paragraphs\" |\n| \"Don't be vague\" | \"Use specific language\" |\n\n### Structured Output\n\n- Prompt-based: ~35.9% reliability\n- Schema enforcement: 100% reliability\n- Always provide schema example and validate output\n\n### Context Window Optimization\n\n**Lost-in-the-Middle:** Models weigh beginning and end more heavily.\n\nPlace critical constraints at start, examples in middle, error handling at end.\n\n### Extended Thinking\n\nHigh-level instructions (\"Think deeply\") outperform step-by-step guidance. \"Think step-by-step\" is redundant with modern models.\n\n### Anti-Patterns Quick Reference\n\n| Anti-Pattern | Problem | Fix |\n|--------------|---------|-----|\n| Vague references | \"The above code\" loses context | Quote specifically |\n| Negative-only | \"Don't do X\" without alternative | State what TO do |\n| Aggressive emphasis | \"CRITICAL: MUST\" | Use normal language |\n| Redundant CoT | Wastes tokens | Let model manage |\n| Critical info buried | Lost-in-the-middle | Place at start\u002Fend |\n\n---\n\n## Detection Patterns\n\n### 1. Clarity Issues (HIGH Certainty)\n\n**Vague Instructions:** \"usually\", \"sometimes\", \"try to\", \"if possible\", \"might\", \"could\"\n\n**Negative-Only Constraints:** \"don't\", \"never\", \"avoid\" without stating what TO do\n\n**Aggressive Emphasis:** Excessive CAPS (CRITICAL, IMPORTANT), multiple !!\n\n### 2. Structure Issues (HIGH\u002FMEDIUM Certainty)\n\n**Missing XML Structure:** Complex prompts (>800 tokens) without XML tags\n\n**Inconsistent Sections:** Mixed heading styles, skipped levels (H1→H3)\n\n**Critical Info Buried:** Important instructions in middle 40%, constraints after examples\n\n### 3. Example Issues (HIGH\u002FMEDIUM Certainty)\n\n**Missing Examples:** Complex tasks without few-shot, format requests without example\n\n**Suboptimal Count:** Only 1 example (optimal: 2-5), more than 7 (bloat)\n\n**Missing Contrast:** No good\u002Fbad labeling, no edge cases\n\n### 4. Context Issues (MEDIUM Certainty)\n\n**Missing WHY:** Rules without explanation\n\n**Missing Priority:** Multiple constraint sections without conflict resolution\n\n### 5. Output Format Issues (HIGH\u002FMEDIUM Certainty)\n\n**Missing Format:** Substantial prompts without format specification\n\n**JSON Without Schema:** Requests JSON but no example structure\n\n### 6. Anti-Patterns (HIGH\u002FMEDIUM\u002FLOW Certainty)\n\n**Redundant CoT (HIGH):** \"Think step by step\" with modern models\n\n**Overly Prescriptive (MEDIUM):** 10+ numbered steps, micro-managing reasoning\n\n**Prompt Bloat (LOW):** Over 2500 tokens, redundant instructions\n\n**Vague References (HIGH):** \"The above code\", \"as mentioned\"\n\n---\n\n## Auto-Fix Implementations\n\n### 1. Aggressive Emphasis\nReplace CRITICAL→critical, !!→!, remove excessive caps\n\n### 2. Negative-Only to Positive\nSuggest positive alternatives for \"don't\" statements\n\n---\n\n## Output Format\n\n```markdown\n## Prompt Analysis: {prompt-name}\n\n**File**: {path}\n**Type**: {system|agent|skill|template}\n**Token Count**: ~{tokens}\n\n### Summary\n- HIGH: {count} issues\n- MEDIUM: {count} issues\n\n### Clarity Issues ({n})\n| Issue | Location | Fix | Certainty |\n\n### Structure Issues ({n})\n| Issue | Location | Fix | Certainty |\n\n### Example Issues ({n})\n| Issue | Location | Fix | Certainty |\n```\n\n---\n\n## Pattern Statistics\n\n| Category | Patterns | Auto-Fixable |\n|----------|----------|--------------|\n| Clarity | 4 | 1 |\n| Structure | 4 | 0 |\n| Examples | 4 | 0 |\n| Context | 2 | 0 |\n| Output Format | 3 | 0 |\n| Anti-Pattern | 4 | 0 |\n| **Total** | **21** | **1** |\n\n---\n\n\u003Cexamples>\n### Example: Vague Instructions\n\n\u003Cbad_example>\n```markdown\nYou should usually follow best practices when possible.\n```\n**Why it's bad**: Vague qualifiers reduce determinism.\n\u003C\u002Fbad_example>\n\n\u003Cgood_example>\n```markdown\nFollow these practices:\n1. Validate input before processing\n2. Handle null\u002Fundefined explicitly\n```\n**Why it's good**: Specific, actionable instructions.\n\u003C\u002Fgood_example>\n\n### Example: Negative-Only Constraints\n\n\u003Cbad_example>\n```markdown\n- Don't use vague language\n- Never skip validation\n```\n**Why it's bad**: Only states what NOT to do.\n\u003C\u002Fbad_example>\n\n\u003Cgood_example>\n```markdown\n- Use specific, deterministic language\n- Always validate input; return structured errors\n```\n**Why it's good**: Each constraint includes positive action.\n\u003C\u002Fgood_example>\n\n### Example: Redundant Chain-of-Thought\n\n\u003Cbad_example>\n```markdown\nThink through this step by step:\n1. First, analyze the input\n2. Then, identify the key elements\n```\n**Why it's bad**: Modern models do this internally. Wastes tokens.\n\u003C\u002Fbad_example>\n\n\u003Cgood_example>\n```markdown\nAnalyze the input carefully before responding.\n```\n**Why it's good**: High-level guidance without micro-managing.\n\u003C\u002Fgood_example>\n\n### Example: Missing Output Format\n\n\u003Cbad_example>\n```markdown\nRespond with a JSON object containing the analysis results.\n```\n**Why it's bad**: No schema or example.\n\u003C\u002Fbad_example>\n\n\u003Cgood_example>\n```markdown\n## Output Format\n{\"status\": \"success|error\", \"findings\": [{\"severity\": \"HIGH\"}]}\n```\n**Why it's good**: Concrete schema shows exact structure.\n\u003C\u002Fgood_example>\n\n### Example: Critical Info Buried\n\n\u003Cbad_example>\n```markdown\n# Task\n[task]\n## Background\n[500 words...]\n## Important Constraints  \u003C- buried at end\n```\n**Why it's bad**: Lost-in-the-middle effect.\n\u003C\u002Fbad_example>\n\n\u003Cgood_example>\n```markdown\n# Task\n## Critical Constraints  \u003C- at start\n[constraints]\n## Background\n```\n**Why it's good**: Critical info at start where attention is highest.\n\u003C\u002Fgood_example>\n\u003C\u002Fexamples>\n\n---\n\n## Constraints\n\n- Only apply auto-fixes for HIGH certainty issues\n- Preserve original structure and formatting\n- Validate against embedded knowledge reference above\n","# enhance-prompts\n\nAnalyze prompts for clarity, structure, examples, and output reliability.\n\n## Parse Arguments\n\n```javascript\nconst args = '$ARGUMENTS'.split(' ').filter(Boolean);\nconst targetPath = args.find(a => !a.startsWith('--')) || '.';\nconst fix = args.includes('--fix');\n```\n\n## Differentiation from enhance-agent-prompts\n\n| Skill | Focus | Use When |\n|-------|-------|----------|\n| `enhance-prompts` | Prompt quality (clarity, structure, examples) | General prompts, system prompts, templates |\n| `enhance-agent-prompts` | Agent config (frontmatter, tools, model) | Agent files with YAML frontmatter |\n\n## Workflow\n\n1. **Run Analyzer** - Execute the JavaScript analyzer to get findings:\n   ```bash\n   node -e \"const a = require('.\u002Flib\u002Fenhance\u002Fprompt-analyzer.js'); console.log(JSON.stringify(a.analyzeAllPrompts('.'), null, 2));\"\n   ```\n   For a specific path: `a.analyzeAllPrompts('.\u002Fplugins\u002Fenhance')`\n   For a single file: `a.analyzePrompt('.\u002Fpath\u002Fto\u002Ffile.md')`\n\n2. **Parse Results** - The analyzer returns JSON with `summary` and `findings`\n3. **Filter** - Apply certainty filtering based on --verbose flag\n4. **Report** - Format findings as markdown output\n5. **Fix** - If --fix flag, apply auto-fixes from findings\n\nThe JavaScript analyzer (`lib\u002Fenhance\u002Fprompt-analyzer.js`) implements all detection patterns including AST-based code validation. The patterns below are reference documentation.\n\n---\n\n## Prompt Engineering Knowledge Reference\n\n### System Prompt Structure\n\nEffective system prompts include: Role\u002FIdentity, Capabilities & Constraints, Instruction Priority, Output Format, Behavioral Directives, Examples, Error Handling.\n\n**Minimal Template:**\n```xml\n\u003Csystem>\nYou are [ROLE]. [PURPOSE].\nKey constraints: [CONSTRAINTS]\nOutput format: [FORMAT]\nWhen uncertain: [HANDLING]\n\u003C\u002Fsystem>\n```\n\n### XML Tags (Claude-Specific)\n\nClaude is fine-tuned for XML tags. Use: `\u003Crole>`, `\u003Cconstraints>`, `\u003Coutput_format>`, `\u003Cexamples>`, `\u003Cinstructions>`, `\u003Ccontext>`\n\n```xml\n\u003Cconstraints>\n- Maximum response length: 500 words\n- Use only Python 3.10+ syntax\n\u003C\u002Fconstraints>\n```\n\n### Few-Shot Examples\n\n- 2-5 examples is optimal (research-backed)\n- Include edge cases and ensure format consistency\n- Start zero-shot, add examples only if needed\n- Show both good AND bad examples when relevant\n\n### Chain-of-Thought (CoT)\n\n| Use CoT | Don't Use CoT |\n|---------|---------------|\n| Complex multi-step reasoning | Simple factual questions |\n| Math and logic problems | Classification tasks |\n| Code debugging | When model has built-in reasoning |\n\n**Key:** Modern models (Claude 4.x, o1\u002Fo3) perform CoT internally. \"Think step by step\" is redundant.\n\n### Role Prompting\n\n**Helps:** Creative tasks, tone\u002Fstyle, roleplay\n**Doesn't help:** Accuracy tasks, factual retrieval, complex reasoning\n\nBetter: \"Approach systematically, showing work\" vs \"You are an expert\"\n\n### Instruction Hierarchy\n\nPriority: System > Developer > User > Retrieved Content\n\nInclude explicit priority in prompts with multiple constraint sources.\n\n### Negative Prompting\n\nPositive alternatives are more effective than negatives:\n\n| Less Effective | More Effective |\n|----------------|----------------|\n| \"Don't use markdown\" | \"Use prose paragraphs\" |\n| \"Don't be vague\" | \"Use specific language\" |\n\n### Structured Output\n\n- Prompt-based: ~35.9% reliability\n- Schema enforcement: 100% reliability\n- Always provide schema example and validate output\n\n### Context Window Optimization\n\n**Lost-in-the-Middle:** Models weigh beginning and end more heavily.\n\nPlace critical constraints at start, examples in middle, error handling at end.\n\n### Extended Thinking\n\nHigh-level instructions (\"Think deeply\") outperform step-by-step guidance. \"Think step-by-step\" is redundant with modern models.\n\n### Anti-Patterns Quick Reference\n\n| Anti-Pattern | Problem | Fix |\n|--------------|---------|-----|\n| Vague references | \"The above code\" loses context | Quote specifically |\n| Negative-only | \"Don't do X\" without alternative | State what TO do |\n| Aggressive emphasis | \"CRITICAL: MUST\" | Use normal language |\n| Redundant CoT | Wastes tokens | Let model manage |\n| Critical info buried | Lost-in-the-middle | Place at start\u002Fend |\n\n---\n\n## Detection Patterns\n\n### 1. Clarity Issues (HIGH Certainty)\n\n**Vague Instructions:** \"usually\", \"sometimes\", \"try to\", \"if possible\", \"might\", \"could\"\n\n**Negative-Only Constraints:** \"don't\", \"never\", \"avoid\" without stating what TO do\n\n**Aggressive Emphasis:** Excessive CAPS (CRITICAL, IMPORTANT), multiple !!\n\n### 2. Structure Issues (HIGH\u002FMEDIUM Certainty)\n\n**Missing XML Structure:** Complex prompts (>800 tokens) without XML tags\n\n**Inconsistent Sections:** Mixed heading styles, skipped levels (H1→H3)\n\n**Critical Info Buried:** Important instructions in middle 40%, constraints after examples\n\n### 3. Example Issues (HIGH\u002FMEDIUM Certainty)\n\n**Missing Examples:** Complex tasks without few-shot, format requests without example\n\n**Suboptimal Count:** Only 1 example (optimal: 2-5), more than 7 (bloat)\n\n**Missing Contrast:** No good\u002Fbad labeling, no edge cases\n\n### 4. Context Issues (MEDIUM Certainty)\n\n**Missing WHY:** Rules without explanation\n\n**Missing Priority:** Multiple constraint sections without conflict resolution\n\n### 5. Output Format Issues (HIGH\u002FMEDIUM Certainty)\n\n**Missing Format:** Substantial prompts without format specification\n\n**JSON Without Schema:** Requests JSON but no example structure\n\n### 6. Anti-Patterns (HIGH\u002FMEDIUM\u002FLOW Certainty)\n\n**Redundant CoT (HIGH):** \"Think step by step\" with modern models\n\n**Overly Prescriptive (MEDIUM):** 10+ numbered steps, micro-managing reasoning\n\n**Prompt Bloat (LOW):** Over 2500 tokens, redundant instructions\n\n**Vague References (HIGH):** \"The above code\", \"as mentioned\"\n\n---\n\n## Auto-Fix Implementations\n\n### 1. Aggressive Emphasis\nReplace CRITICAL→critical, !!→!, remove excessive caps\n\n### 2. Negative-Only to Positive\nSuggest positive alternatives for \"don't\" statements\n\n---\n\n## Output Format\n\n```markdown\n## Prompt Analysis: {prompt-name}\n\n**File**: {path}\n**Type**: {system|agent|skill|template}\n**Token Count**: ~{tokens}\n\n### Summary\n- HIGH: {count} issues\n- MEDIUM: {count} issues\n\n### Clarity Issues ({n})\n| Issue | Location | Fix | Certainty |\n\n### Structure Issues ({n})\n| Issue | Location | Fix | Certainty |\n\n### Example Issues ({n})\n| Issue | Location | Fix | Certainty |\n```\n\n---\n\n## Pattern Statistics\n\n| Category | Patterns | Auto-Fixable |\n|----------|----------|--------------|\n| Clarity | 4 | 1 |\n| Structure | 4 | 0 |\n| Examples | 4 | 0 |\n| Context | 2 | 0 |\n| Output Format | 3 | 0 |\n| Anti-Pattern | 4 | 0 |\n| **Total** | **21** | **1** |\n\n---\n\n\u003Cexamples>\n### Example: Vague Instructions\n\n\u003Cbad_example>\n```markdown\nYou should usually follow best practices when possible.\n```\n**Why it's bad**: Vague qualifiers reduce determinism.\n\u003C\u002Fbad_example>\n\n\u003Cgood_example>\n```markdown\nFollow these practices:\n1. Validate input before processing\n2. Handle null\u002Fundefined explicitly\n```\n**Why it's good**: Specific, actionable instructions.\n\u003C\u002Fgood_example>\n\n### Example: Negative-Only Constraints\n\n\u003Cbad_example>\n```markdown\n- Don't use vague language\n- Never skip validation\n```\n**Why it's bad**: Only states what NOT to do.\n\u003C\u002Fbad_example>\n\n\u003Cgood_example>\n```markdown\n- Use specific, deterministic language\n- Always validate input; return structured errors\n```\n**Why it's good**: Each constraint includes positive action.\n\u003C\u002Fgood_example>\n\n### Example: Redundant Chain-of-Thought\n\n\u003Cbad_example>\n```markdown\nThink through this step by step:\n1. First, analyze the input\n2. Then, identify the key elements\n```\n**Why it's bad**: Modern models do this internally. Wastes tokens.\n\u003C\u002Fbad_example>\n\n\u003Cgood_example>\n```markdown\nAnalyze the input carefully before responding.\n```\n**Why it's good**: High-level guidance without micro-managing.\n\u003C\u002Fgood_example>\n\n### Example: Missing Output Format\n\n\u003Cbad_example>\n```markdown\nRespond with a JSON object containing the analysis results.\n```\n**Why it's bad**: No schema or example.\n\u003C\u002Fbad_example>\n\n\u003Cgood_example>\n```markdown\n## Output Format\n{\"status\": \"success|error\", \"findings\": [{\"severity\": \"HIGH\"}]}\n```\n**Why it's good**: Concrete schema shows exact structure.\n\u003C\u002Fgood_example>\n\n### Example: Critical Info Buried\n\n\u003Cbad_example>\n```markdown\n# Task\n[task]\n## Background\n[500 words...]\n## Important Constraints  \u003C- buried at end\n```\n**Why it's bad**: Lost-in-the-middle effect.\n\u003C\u002Fbad_example>\n\n\u003Cgood_example>\n```markdown\n# Task\n## Critical Constraints  \u003C- at start\n[constraints]\n## Background\n```\n**Why it's good**: Critical info at start where attention is highest.\n\u003C\u002Fgood_example>\n\u003C\u002Fexamples>\n\n---\n\n## Constraints\n\n- Only apply auto-fixes for HIGH certainty issues\n- Preserve original structure and formatting\n- Validate against embedded knowledge reference above\n",{"name":5,"version":23,"description":7,"argument-hint":24},"5.1.0","[path] [--fix]","main","f37de8f681f0c0ca0e0ebab6e5fddf764ca7553d","skills\u002Fenhance-prompts",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":35,"prompt":45,"zipAvailable":46},[36,39,42],{"tool":37,"command":38},"npx","npx skills add agisota\u002Fold-one --skill enhance-prompts",{"tool":40,"command":41},"bunx","bunx skills add agisota\u002Fold-one --skill enhance-prompts",{"tool":43,"command":44},"pnpm","pnpm dlx skills add agisota\u002Fold-one --skill enhance-prompts","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fagisota\u002Fold-one\u002Fblob\u002Fmain\u002Fskills\u002Fenhance-prompts\u002FSKILL.md",true,[],[49,56,63,72,79,86],{"skillNo":50,"name":51,"nameZh":6,"description":52,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":53,"categories":54,"keywords":55,"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":57,"name":58,"nameZh":6,"description":59,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":60,"categories":61,"keywords":62,"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":64,"name":65,"nameZh":6,"description":66,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":67,"licenseFileUrl":68,"sourceHtmlUrl":69,"categories":70,"keywords":71,"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":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"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":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"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":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"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",[],[]]