[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7F4PTS66508YJRNK90D2GMC":3,"skill-same:01M7F4PTS66508YJRNK90D2GMC":64},{"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":42,"commitSha":43,"skillDirectory":44,"forksCount":45,"repositoryHtmlUrl":46,"repositoryHomepageUrl":6,"ownerHtmlUrl":47,"ownerBlogUrl":6,"ownerDescription":48,"updatedAt":49,"install":50,"resources":63},"01M7F4PTS66508YJRNK90D2GMC","skill-check",null,"Validate Claude Code skills against the agentskills specification. Catches structural, semantic, and naming issues before users do.","lza6\u002FArmor-piercing-system-prompts","lza6","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F128880206?v=4","01M7EB3K7WPX5T28EJ2NVHE6EG","Chinese-tingfeng","01M7EB3K97E1KQ16QWKJMFNGX8",11,"MIT","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F05-技能与代理开发\u002Fskill-check-antigravity-awesome-skills-main\u002FSKILL.md",[],[],"2026-11-16 10:05:34",false,"---\nname: skill-check\ndescription: \"Validate Claude Code skills against the agentskills specification. Catches structural, semantic, and naming issues before users do.\"\ncategory: development\nrisk: safe\nsource: https:\u002F\u002Fgithub.com\u002Folgasafonova\u002FSkillCheck-Free\ndate_added: \"2026-03-11\"\nauthor: olgasafonova\ntags: [validation, linter, agentskills, skill-authoring, code-quality]\ntools: [claude, cursor, windsurf, codex-cli]\nlicense: MIT\nallowed-tools: Read Glob\ncompatibility: claude-code\n---\n\n# SkillCheck\n\n## Overview\n\nValidate SKILL.md files against the [agentskills specification](https:\u002F\u002Fagentskills.io) and Anthropic best practices. Catches structural errors, semantic contradictions, naming anti-patterns, and quality gaps in a single read-only pass.\n\n## When to Use This Skill\n\n- Use when user says \"check skill\", \"skillcheck\", or \"validate SKILL.md\"\n- Use when reviewing a skill before publishing to a marketplace\n- Use when debugging why a skill doesn't trigger correctly\n- Use when onboarding a team to skill authoring standards\n- Do NOT use for anti-slop detection, security scanning, or token analysis; use [SkillCheck Pro](https:\u002F\u002Fgetskillcheck.com) for those\n\n## How It Works\n\n### Step 1: Parse\n\nRead the target SKILL.md file and extract YAML frontmatter.\n\n### Step 2: Validate\n\nApply all Free tier checks in order:\n\n| Category | Checks | What it catches |\n|----------|--------|----------------|\n| Structure (1.x) | Name format, description WHAT+WHEN, allowed-tools, categories, XML injection | Malformed frontmatter, missing fields |\n| Body (2.x) | Line count, hardcoded paths, stale dates, empty sections, deprecated syntax, MCP tool qualification | Content quality issues |\n| Naming (3.x) | Vague terms, single-word names, gerund suggestions | Poor discoverability |\n| Semantic (4.x) | Contradictions, ambiguous terms, missing output format, wisdom\u002Fplatitudes, misplaced triggers | Logical inconsistencies |\n| Quality (8.x) | Examples, error handling, triggers, output format, prerequisites, negative triggers | Strengths (positive patterns) |\n\n### Step 3: Score\n\nCalculate overall score (0-100). Penalties: critical = -20, warning = -5, suggestion = -1.\n\n### Step 4: Report\n\nReturn structured results: score, grade (Excellent\u002FGood\u002FNeeds Work\u002FPoor), issue list with check IDs, line numbers, messages, and fix suggestions.\n\n## Examples\n\n### Example 1: Validating a skill\n\n```\nUser: check my skill at ~\u002F.claude\u002Fskills\u002Fweekly-report\u002FSKILL.md\n\nSkillCheck output:\n## weekly-report Check Results [FREE]\n\nScore: 85\u002F100 (Good)\n\n### Warnings (2)\n  - 1.2-desc-when (line 3): Description missing WHEN clause\n  - 4.5-desc-no-triggers (line 3): Description lacks triggering conditions\n\n### Suggestions (1)\n  - 3.4-gerund-naming (line 2): Skill name could use gerund form\n\n### Passed Checks: 28\n```\n\n### Example 2: Clean skill passes all checks\n\n```\nUser: skillcheck ~\u002F.claude\u002Fskills\u002Fprocessing-pdfs\u002FSKILL.md\n\nScore: 100\u002F100 (Excellent)\nAll 31 checks passed. No issues found.\n```\n\n## Limitations\n\n- Read-only: does not modify any files\n- Free tier covers structural, semantic, and naming checks only\n- Anti-slop, security, WCAG, token, enterprise, and workflow checks require [SkillCheck Pro](https:\u002F\u002Fgetskillcheck.com)\n- Semantic checks (contradiction detection, wisdom\u002Fplatitude) are heuristic with ~5% false positive rate\n- Does not validate referenced files or scripts; only checks SKILL.md content\n- Single-file validation; does not cross-check against other skills in the same directory\n\n## Best Practices\n\n- Run SkillCheck before submitting skills to any marketplace\n- Fix all critical and warning issues; suggestions are optional\n- Use the check ID (e.g., `1.2-desc-when`) to find the exact rule in the skill body\n- Re-run after fixes to confirm the score improved\n\n## Common Pitfalls\n\n- **Problem:** Score seems low due to many suggestions\n  **Solution:** Suggestions cap at -15 points total. Focus on warnings and criticals first.\n\n- **Problem:** False positive on ambiguous terms inside code blocks\n  **Solution:** SkillCheck skips code blocks and inline code. If you still see false positives, wrap the term in backticks.\n\n- **Problem:** Wisdom\u002Fplatitude check flags legitimate instructions\n  **Solution:** Rephrase generic advice (\"Remember that testing is important\") as concrete directives (\"Run tests before committing\").\n","# SkillCheck\n\n## Overview\n\nValidate SKILL.md files against the [agentskills specification](https:\u002F\u002Fagentskills.io) and Anthropic best practices. Catches structural errors, semantic contradictions, naming anti-patterns, and quality gaps in a single read-only pass.\n\n## When to Use This Skill\n\n- Use when user says \"check skill\", \"skillcheck\", or \"validate SKILL.md\"\n- Use when reviewing a skill before publishing to a marketplace\n- Use when debugging why a skill doesn't trigger correctly\n- Use when onboarding a team to skill authoring standards\n- Do NOT use for anti-slop detection, security scanning, or token analysis; use [SkillCheck Pro](https:\u002F\u002Fgetskillcheck.com) for those\n\n## How It Works\n\n### Step 1: Parse\n\nRead the target SKILL.md file and extract YAML frontmatter.\n\n### Step 2: Validate\n\nApply all Free tier checks in order:\n\n| Category | Checks | What it catches |\n|----------|--------|----------------|\n| Structure (1.x) | Name format, description WHAT+WHEN, allowed-tools, categories, XML injection | Malformed frontmatter, missing fields |\n| Body (2.x) | Line count, hardcoded paths, stale dates, empty sections, deprecated syntax, MCP tool qualification | Content quality issues |\n| Naming (3.x) | Vague terms, single-word names, gerund suggestions | Poor discoverability |\n| Semantic (4.x) | Contradictions, ambiguous terms, missing output format, wisdom\u002Fplatitudes, misplaced triggers | Logical inconsistencies |\n| Quality (8.x) | Examples, error handling, triggers, output format, prerequisites, negative triggers | Strengths (positive patterns) |\n\n### Step 3: Score\n\nCalculate overall score (0-100). Penalties: critical = -20, warning = -5, suggestion = -1.\n\n### Step 4: Report\n\nReturn structured results: score, grade (Excellent\u002FGood\u002FNeeds Work\u002FPoor), issue list with check IDs, line numbers, messages, and fix suggestions.\n\n## Examples\n\n### Example 1: Validating a skill\n\n```\nUser: check my skill at ~\u002F.claude\u002Fskills\u002Fweekly-report\u002FSKILL.md\n\nSkillCheck output:\n## weekly-report Check Results [FREE]\n\nScore: 85\u002F100 (Good)\n\n### Warnings (2)\n  - 1.2-desc-when (line 3): Description missing WHEN clause\n  - 4.5-desc-no-triggers (line 3): Description lacks triggering conditions\n\n### Suggestions (1)\n  - 3.4-gerund-naming (line 2): Skill name could use gerund form\n\n### Passed Checks: 28\n```\n\n### Example 2: Clean skill passes all checks\n\n```\nUser: skillcheck ~\u002F.claude\u002Fskills\u002Fprocessing-pdfs\u002FSKILL.md\n\nScore: 100\u002F100 (Excellent)\nAll 31 checks passed. No issues found.\n```\n\n## Limitations\n\n- Read-only: does not modify any files\n- Free tier covers structural, semantic, and naming checks only\n- Anti-slop, security, WCAG, token, enterprise, and workflow checks require [SkillCheck Pro](https:\u002F\u002Fgetskillcheck.com)\n- Semantic checks (contradiction detection, wisdom\u002Fplatitude) are heuristic with ~5% false positive rate\n- Does not validate referenced files or scripts; only checks SKILL.md content\n- Single-file validation; does not cross-check against other skills in the same directory\n\n## Best Practices\n\n- Run SkillCheck before submitting skills to any marketplace\n- Fix all critical and warning issues; suggestions are optional\n- Use the check ID (e.g., `1.2-desc-when`) to find the exact rule in the skill body\n- Re-run after fixes to confirm the score improved\n\n## Common Pitfalls\n\n- **Problem:** Score seems low due to many suggestions\n  **Solution:** Suggestions cap at -15 points total. Focus on warnings and criticals first.\n\n- **Problem:** False positive on ambiguous terms inside code blocks\n  **Solution:** SkillCheck skips code blocks and inline code. If you still see false positives, wrap the term in backticks.\n\n- **Problem:** Wisdom\u002Fplatitude check flags legitimate instructions\n  **Solution:** Rephrase generic advice (\"Remember that testing is important\") as concrete directives (\"Run tests before committing\").\n",{"name":5,"risk":24,"tags":25,"tools":31,"author":36,"source":37,"license":15,"category":38,"date_added":39,"description":7,"allowed-tools":40,"compatibility":41},"safe",[26,27,28,29,30],"validation","linter","agentskills","skill-authoring","code-quality",[32,33,34,35],"claude","cursor","windsurf","codex-cli","olgasafonova","https:\u002F\u002Fgithub.com\u002Folgasafonova\u002FSkillCheck-Free","development","2026-03-11","Read Glob","claude-code","main","d69096e239f2a89aabc2cd078c47664a9d3b1e11","05-技能与代理开发\u002Fskill-check-antigravity-awesome-skills-main",3,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts","https:\u002F\u002Fgithub.com\u002Flza6","个人vx：Tf00798\r\n个人✈：@TFGY999","2026-10-08 14:29:22",{"source":8,"skillName":5,"commands":51,"prompt":61,"zipAvailable":62},[52,55,58],{"tool":53,"command":54},"npx","npx skills add lza6\u002FArmor-piercing-system-prompts --skill skill-check",{"tool":56,"command":57},"bunx","bunx skills add lza6\u002FArmor-piercing-system-prompts --skill skill-check",{"tool":59,"command":60},"pnpm","pnpm dlx skills add lza6\u002FArmor-piercing-system-prompts --skill skill-check","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F05-技能与代理开发\u002Fskill-check-antigravity-awesome-skills-main\u002FSKILL.md",true,[],[65,72,77,84,91,98],{"skillNo":66,"name":67,"nameZh":6,"description":68,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":69,"categories":70,"keywords":71,"publishedAt":19},"01M7FFG485KY83TD6HSC4YPCMC","obsidian-clipper-template-creator","Guide for creating templates for the Obsidian Web Clipper. Use when you want to create a new clipping template, understand available variables, or format clipped content.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobsidian-clipper-template-creator\u002FSKILL.md",[],[],{"skillNo":73,"name":67,"nameZh":6,"description":68,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":74,"categories":75,"keywords":76,"publishedAt":19},"01M7FFG0T6AZ0STEJPSB3CX84K","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobsidian-clipper-template-creator-antigravity-awesome-skills-main\u002FSKILL.md",[],[],{"skillNo":78,"name":79,"nameZh":6,"description":80,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":81,"categories":82,"keywords":83,"publishedAt":19},"01M7FFFY0QEM14SKWPDYGMXM2P","python-api","Programmatic Object-Detection-Metrics API guidance for BoundingBox, BoundingBoxes, Evaluator, enums, coordinate conversion, AP\u002FmAP semantics, and source-style import diagnostics.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002Fsub-skills\u002Fpython-api\u002FSKILL.md",[],[],{"skillNo":85,"name":86,"nameZh":6,"description":87,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":88,"categories":89,"keywords":90,"publishedAt":19},"01M7FFFVZQZ2GJ0C0TGP7JHD20","file-evaluation","Folder-based PASCAL VOC AP\u002FmAP evaluation from ground-truth and detection text files.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002Fsub-skills\u002Ffile-evaluation\u002FSKILL.md",[],[],{"skillNo":92,"name":93,"nameZh":6,"description":94,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":95,"categories":96,"keywords":97,"publishedAt":19},"01M7FFFSFNYSE77SJ6PE1CK2DA","object-detection-metrics","Guides legacy Object-Detection-Metrics PASCAL VOC AP\u002FmAP evaluation from detection text folders and direct Python API classes.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002FSKILL.md",[],[],{"skillNo":99,"name":100,"nameZh":6,"description":101,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":102,"categories":103,"keywords":104,"publishedAt":19},"01M7FFFP0GCK1RVXBCPQ8APBMT","nx-workspace-patterns","Configure and optimize Nx monorepo workspaces. Use when setting up Nx, configuring project boundaries, optimizing build caching, or implementing affected commands.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fnx-workspace-patterns\u002FSKILL.md",[],[]]