[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7432BVYTHCCRMK5XDXBWF7Z":3,"skill-same:01M7432BVYTHCCRMK5XDXBWF7Z":79},{"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":16,"sourceHtmlUrl":17,"categories":18,"keywords":19,"publishedAt":20,"linkOnly":21,"markdownContent":22,"markdownBody":23,"frontMatter":24,"refName":40,"commitSha":41,"skillDirectory":42,"forksCount":43,"repositoryHtmlUrl":44,"repositoryHomepageUrl":45,"ownerHtmlUrl":46,"ownerBlogUrl":47,"ownerDescription":48,"updatedAt":49,"install":50,"resources":63},"01M7432BVYTHCCRMK5XDXBWF7Z","skill-creator",null,"This skill should be used when the user asks to create a new skill, build a skill, make a custom skill, develop a CLI skill, or wants to extend the CLI with new capabilities. Automates the entire skill creation workflow from brainstorming to installation.","bg-szy\u002FTOP-SKILLS","bg-szy","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F106576190?v=4","01M73A4E8KPV67SFXRY8XZGNBX","ShuZhiyong","01M73A4E96MQ294MHM74TZBVQD",6,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fbg-szy\u002FTOP-SKILLS\u002Fblob\u002Fmaster\u002Fskills\u002Fmarketplace\u002Fskill-creator__skills-sickn33-skill-creator\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fbg-szy\u002FTOP-SKILLS\u002Fblob\u002Fmaster\u002Fskills\u002Fmarketplace\u002Fskill-creator__skills-sickn33-skill-creator\u002FSKILL.md",[],[],"2026-11-11 15:11:14",false,"---\nname: skill-creator\ndescription: \"This skill should be used when the user asks to create a new skill, build a skill, make a custom skill, develop a CLI skill, or wants to extend the CLI with new capabilities. Automates the entire skill creation workflow from brainstorming to installation.\"\nversion: 1.3.0\nauthor: Eric Andrade\ncreated: 2025-02-01\nupdated: 2026-02-04\nplatforms: [github-copilot-cli, claude-code, codex]\ncategory: meta\ntags: [automation, scaffolding, skill-creation, meta-skill]\nrisk: safe\n---\n\n# skill-creator\n\n## Purpose\n\nTo create new CLI skills following Anthropic's official best practices with zero manual configuration. This skill automates brainstorming, template application, validation, and installation processes while maintaining progressive disclosure patterns and writing style standards.\n\n## When to Use This Skill\n\nThis skill should be used when:\n- User wants to extend CLI functionality with custom capabilities\n- User needs to create a skill following official standards\n- User wants to automate repetitive CLI tasks with a reusable skill\n- User needs to package domain knowledge into a skill format\n- User wants both local and global skill installation options\n\n## Core Capabilities\n\n1. **Interactive Brainstorming** - Collaborative session to define skill purpose and scope\n2. **Prompt Enhancement** - Optional integration with prompt-engineer skill for refinement\n3. **Template Application** - Automatic file generation from standardized templates\n4. **Validation** - YAML, content, and style checks against Anthropic standards\n5. **Installation** - Local repository or global installation with symlinks\n6. **Progress Tracking** - Visual gauge showing completion status at each step\n\n## Step 0: Discovery\n\nBefore starting skill creation, gather runtime information:\n\n```bash\n# Detect available platforms\nCOPILOT_INSTALLED=false\nCLAUDE_INSTALLED=false\nCODEX_INSTALLED=false\n\nif command -v gh &>\u002Fdev\u002Fnull && gh copilot --version &>\u002Fdev\u002Fnull 2>&1; then\n    COPILOT_INSTALLED=true\nfi\n\nif [[ -d \"$HOME\u002F.claude\" ]]; then\n    CLAUDE_INSTALLED=true\nfi\n\nif [[ -d \"$HOME\u002F.codex\" ]]; then\n    CODEX_INSTALLED=true\nfi\n\n# Determine working directory\nREPO_ROOT=$(git rev-parse --show-toplevel 2>\u002Fdev\u002Fnull || pwd)\nSKILLS_REPO=\"$REPO_ROOT\"\n\n# Check if in cli-ai-skills repository\nif [[ ! -d \"$SKILLS_REPO\u002F.github\u002Fskills\" ]]; then\n    echo \"⚠️  Not in cli-ai-skills repository. Creating standalone skill.\"\n    STANDALONE=true\nfi\n\n# Get user info from git config\nAUTHOR=$(git config user.name || echo \"Unknown\")\nEMAIL=$(git config user.email || echo \"\")\n```\n\n**Key Information Needed:**\n- Which platforms to target (Copilot, Claude, Codex, or all three)\n- Installation preference (local, global, or both)\n- Skill name and purpose\n- Skill type (general, code, documentation, analysis)\n\n## Main Workflow\n\n### Progress Tracking Guidelines\n\nThroughout the workflow, display a visual progress bar before starting each phase to keep the user informed. The progress bar format is:\n\n```\n[████████████░░░░░░] 60% - Step 3\u002F5: Creating SKILL.md\n```\n\n**Format specifications:**\n- 20 characters wide (use █ for filled, ░ for empty)\n- Percentage based on current step (Step 1=20%, Step 2=40%, Step 3=60%, Step 4=80%, Step 5=100%)\n- Step counter showing current\u002Ftotal (e.g., \"Step 3\u002F5\")\n- Brief description of current phase\n\n**Display the progress bar using:**\n```bash\necho \"[████░░░░░░░░░░░░░░] 20% - Step 1\u002F5: Brainstorming & Planning\"\n```\n\n### Phase 1: Brainstorming & Planning\n\n**Progress:** Display before starting this phase:\n```bash\necho \"[████░░░░░░░░░░░░░░] 20% - Step 1\u002F5: Brainstorming & Planning\"\n```\n\nDisplay progress:\n```\n╔══════════════════════════════════════════════════════════════╗\n║     🛠️  SKILL CREATOR - Creating New Skill                  ║\n╠══════════════════════════════════════════════════════════════╣\n║ → Phase 1: Brainstorming                 [10%]               ║\n║ ○ Phase 2: Prompt Refinement                                 ║\n║ ○ Phase 3: File Generation                                   ║\n║ ○ Phase 4: Validation                                        ║\n║ ○ Phase 5: Installation                                      ║\n╠══════════════════════════════════════════════════════════════╣\n║ Progress: ███░░░░░░░░░░░░░░░░░░░░░░░░░░░  10%              ║\n╚══════════════════════════════════════════════════════════════╝\n```\n\n**Ask the user:**\n\n1. **What should this skill do?** (Free-form description)\n   - Example: \"Help users debug Python code by analyzing stack traces\"\n   \n2. **When should it trigger?** (Provide 3-5 trigger phrases)\n   - Example: \"debug Python error\", \"analyze stack trace\", \"fix Python exception\"\n\n3. **What type of skill is this?**\n   - [ ] General purpose (default template)\n   - [ ] Code generation\u002Fmodification\n   - [ ] Documentation creation\u002Fmaintenance\n   - [ ] Analysis\u002Finvestigation\n\n4. **Which platforms should support this skill?**\n   - [ ] GitHub Copilot CLI\n   - [ ] Claude Code\n    - [ ] Codex\n    - [ ] All three (recommended)\n\n5. **Provide a one-sentence description** (will appear in metadata)\n   - Example: \"Analyzes Python stack traces and suggests fixes\"\n\n**Capture responses and prepare for next phase.**\n\n### Phase 2: Prompt Enhancement (Optional)\n\n**Progress:** Display before starting this phase:\n```bash\necho \"[████████░░░░░░░░░░] 40% - Step 2\u002F5: Prompt Enhancement\"\n```\n\nUpdate progress:\n```\n╔══════════════════════════════════════════════════════════════╗\n║ ✓ Phase 1: Brainstorming                                     ║\n║ → Phase 2: Prompt Refinement             [30%]               ║\n╠══════════════════════════════════════════════════════════════╣\n║ Progress: █████████░░░░░░░░░░░░░░░░░░░░░  30%              ║\n╚══════════════════════════════════════════════════════════════╝\n```\n\n**Ask the user:**\n\"Would you like to refine the skill description using the prompt-engineer skill?\"\n- [ ] Yes - Use prompt-engineer to enhance clarity and structure\n- [ ] No - Proceed with current description\n\nIf **Yes**:\n1. Check if prompt-engineer skill is available\n2. Invoke with current description as input\n3. Review enhanced output with user\n4. Ask: \"Accept enhanced version or keep original?\"\n\nIf **No** or prompt-engineer unavailable:\n- Proceed with original user input\n\n### Phase 3: File Generation\n\n**Progress:** Display before starting this phase:\n```bash\necho \"[████████████░░░░░░] 60% - Step 3\u002F5: File Generation\"\n```\n\nUpdate progress:\n```\n╔══════════════════════════════════════════════════════════════╗\n║ ✓ Phase 1: Brainstorming                                     ║\n║ ✓ Phase 2: Prompt Refinement                                 ║\n║ → Phase 3: File Generation               [50%]               ║\n╠══════════════════════════════════════════════════════════════╣\n║ Progress: ███████████████░░░░░░░░░░░░░░░  50%              ║\n╚══════════════════════════════════════════════════════════════╝\n```\n\n**Generate skill structure:**\n\n```bash\n# Convert skill name to kebab-case\nSKILL_NAME=$(echo \"$USER_INPUT\" | tr '[:upper:]' '[:lower:]' | tr ' ' '-')\n\n# Create directories\nif [[ \"$PLATFORM\" =~ \"copilot\" ]]; then\n    mkdir -p \".github\u002Fskills\u002F$SKILL_NAME\"\u002F{references,examples,scripts}\nfi\n\nif [[ \"$PLATFORM\" =~ \"claude\" ]]; then\n    mkdir -p \".claude\u002Fskills\u002F$SKILL_NAME\"\u002F{references,examples,scripts}\nfi\n\nif [[ \"$PLATFORM\" =~ \"codex\" ]]; then\n    mkdir -p \".codex\u002Fskills\u002F$SKILL_NAME\"\u002F{references,examples,scripts}\nfi\n```\n\n**Apply templates:**\n\n1. **SKILL.md** - Use appropriate template:\n   - `skill-template-copilot.md`, `skill-template-claude.md`, or `skill-template-codex.md`\n   - Substitute placeholders:\n     - `{{SKILL_NAME}}` → kebab-case name\n     - `{{DESCRIPTION}}` → one-line description\n     - `{{TRIGGERS}}` → comma-separated trigger phrases\n     - `{{PURPOSE}}` → detailed purpose from brainstorming\n     - `{{AUTHOR}}` → from git config\n     - `{{DATE}}` → current date (YYYY-MM-DD)\n     - `{{VERSION}}` → \"1.0.0\"\n\n2. **README.md** - Use `readme-template.md`:\n   - User-facing documentation (300-500 words)\n   - Include installation instructions\n   - Add usage examples\n\n3. **References\u002F** (optional but recommended):\n   - Create `detailed-guide.md` for extended documentation (2k-5k words)\n   - Move lengthy content here to keep SKILL.md under 2k words\n\n**File creation commands:**\n\n```bash\n# Apply template with substitution\nsed \"s\u002F{{SKILL_NAME}}\u002F$SKILL_NAME\u002Fg; \\\n     s\u002F{{DESCRIPTION}}\u002F$DESCRIPTION\u002Fg; \\\n     s\u002F{{AUTHOR}}\u002F$AUTHOR\u002Fg; \\\n     s\u002F{{DATE}}\u002F$(date +%Y-%m-%d)\u002Fg\" \\\n    resources\u002Ftemplates\u002Fskill-template-copilot.md \\\n    > \".github\u002Fskills\u002F$SKILL_NAME\u002FSKILL.md\"\n\n# Create README\nsed \"s\u002F{{SKILL_NAME}}\u002F$SKILL_NAME\u002Fg\" \\\n    resources\u002Ftemplates\u002Freadme-template.md \\\n    > \".github\u002Fskills\u002F$SKILL_NAME\u002FREADME.md\"\n\n# Apply template for Codex if selected\nif [[ \"$PLATFORM\" =~ \"codex\" ]]; then\n    sed \"s\u002F{{SKILL_NAME}}\u002F$SKILL_NAME\u002Fg; \\\n         s\u002F{{DESCRIPTION}}\u002F$DESCRIPTION\u002Fg; \\\n         s\u002F{{AUTHOR}}\u002F$AUTHOR\u002Fg; \\\n         s\u002F{{DATE}}\u002F$(date +%Y-%m-%d)\u002Fg\" \\\n        resources\u002Ftemplates\u002Fskill-template-codex.md \\\n        > \".codex\u002Fskills\u002F$SKILL_NAME\u002FSKILL.md\"\n    \n    sed \"s\u002F{{SKILL_NAME}}\u002F$SKILL_NAME\u002Fg\" \\\n        resources\u002Ftemplates\u002Freadme-template.md \\\n        > \".codex\u002Fskills\u002F$SKILL_NAME\u002FREADME.md\"\nfi\n```\n\n**Display created structure:**\n```\n✅ Created:\n   .github\u002Fskills\u002Fyour-skill-name\u002F (if Copilot selected)\n   .claude\u002Fskills\u002Fyour-skill-name\u002F (if Claude selected)\n   .codex\u002Fskills\u002Fyour-skill-name\u002F (if Codex selected)\n   ├── SKILL.md (832 lines)\n   ├── README.md (347 lines)\n   ├── references\u002F\n   ├── examples\u002F\n   └── scripts\u002F\n```\n\n### Phase 4: Validation\n\n**Progress:** Display before starting this phase:\n```bash\necho \"[████████████████░░] 80% - Step 4\u002F5: Validation\"\n```\n\nUpdate progress:\n```\n╔══════════════════════════════════════════════════════════════╗\n║ ✓ Phase 3: File Generation                                   ║\n║ → Phase 4: Validation                    [70%]               ║\n╠══════════════════════════════════════════════════════════════╣\n║ Progress: █████████████████████░░░░░░░░░  70%              ║\n╚══════════════════════════════════════════════════════════════╝\n```\n\n**Run validation scripts:**\n\n```bash\n# Validate YAML frontmatter\nscripts\u002Fvalidate-skill-yaml.sh \".github\u002Fskills\u002F$SKILL_NAME\"\n\n# Validate content quality\nscripts\u002Fvalidate-skill-content.sh \".github\u002Fskills\u002F$SKILL_NAME\"\n```\n\n**Expected output:**\n```\n🔍 Validating YAML frontmatter...\n✅ YAML frontmatter valid!\n\n🔍 Validating content...\n✅ Word count excellent: 1847 words\n✅ Content validation complete!\n```\n\n**If validation fails:**\n- Display specific errors\n- Offer to fix automatically (common issues)\n- Ask user to manually correct complex issues\n\n**Common auto-fixes:**\n- Convert second-person to imperative form\n- Reformat description to third-person\n- Add missing required fields\n\n### Phase 5: Installation\n\n**Progress:** Display before starting this phase:\n```bash\necho \"[████████████████████] 100% - Step 5\u002F5: Installation\"\n```\n\nUpdate progress:\n```\n╔══════════════════════════════════════════════════════════════╗\n║ ✓ Phase 4: Validation                                        ║\n║ → Phase 5: Installation                  [90%]               ║\n╠══════════════════════════════════════════════════════════════╣\n║ Progress: ██████████████████████████░░░░░  90%              ║\n╚══════════════════════════════════════════════════════════════╝\n```\n\n**Ask the user:**\n\"How would you like to install this skill?\"\n\n- [ ] **Repository only** - Files created in `.github\u002Fskills\u002F` (works when in repo)\n- [ ] **Global installation** - Create symlinks in `~\u002F.copilot\u002Fskills\u002F` (works everywhere)\n- [ ] **Both** - Repository + global symlinks (recommended, auto-updates with git pull)\n- [ ] **Skip installation** - Just create files\n\n**If global installation selected:**\n\n```bash\n# Detect which platforms to install for\nINSTALL_TARGETS=()\n\nif [[ \"$COPILOT_INSTALLED\" == \"true\" ]] && [[ \"$PLATFORM\" =~ \"copilot\" ]]; then\n    INSTALL_TARGETS+=(\"copilot\")\nfi\n\nif [[ \"$CLAUDE_INSTALLED\" == \"true\" ]] && [[ \"$PLATFORM\" =~ \"claude\" ]]; then\n    INSTALL_TARGETS+=(\"claude\")\nfi\n\nif [[ \"$CODEX_INSTALLED\" == \"true\" ]] && [[ \"$PLATFORM\" =~ \"codex\" ]]; then\n    INSTALL_TARGETS+=(\"codex\")\nfi\n\n# Ask user to confirm detected platforms\necho \"Detected platforms: ${INSTALL_TARGETS[*]}\"\necho \"Install for these platforms? [Y\u002Fn]\"\n```\n\n**Installation process:**\n\n```bash\n# GitHub Copilot CLI\nif [[ \" ${INSTALL_TARGETS[*]} \" =~ \" copilot \" ]]; then\n    ln -sf \"$SKILLS_REPO\u002F.github\u002Fskills\u002F$SKILL_NAME\" \\\n           \"$HOME\u002F.copilot\u002Fskills\u002F$SKILL_NAME\"\n    echo \"✅ Installed for GitHub Copilot CLI\"\nfi\n\n# Claude Code\nif [[ \" ${INSTALL_TARGETS[*]} \" =~ \" claude \" ]]; then\n    ln -sf \"$SKILLS_REPO\u002F.claude\u002Fskills\u002F$SKILL_NAME\" \\\n           \"$HOME\u002F.claude\u002Fskills\u002F$SKILL_NAME\"\n    echo \"✅ Installed for Claude Code\"\nfi\n\n# Codex\nif [[ \" ${INSTALL_TARGETS[*]} \" =~ \" codex \" ]]; then\n    ln -sf \"$SKILLS_REPO\u002F.codex\u002Fskills\u002F$SKILL_NAME\" \\\n           \"$HOME\u002F.codex\u002Fskills\u002F$SKILL_NAME\"\n    echo \"✅ Installed for Codex\"\nfi\n```\n\n**Verify installation:**\n\n```bash\n# Check symlinks\nls -la ~\u002F.copilot\u002Fskills\u002F$SKILL_NAME 2>\u002Fdev\u002Fnull\nls -la ~\u002F.claude\u002Fskills\u002F$SKILL_NAME 2>\u002Fdev\u002Fnull\nls -la ~\u002F.codex\u002Fskills\u002F$SKILL_NAME 2>\u002Fdev\u002Fnull\n```\n\n### Phase 6: Completion\n\n**Progress:** Display completion message:\n```bash\necho \"[████████████████████] 100% - ✓ Skill created successfully!\"\n```\n\nUpdate progress:\n```\n╔══════════════════════════════════════════════════════════════╗\n║ ✓ Phase 5: Installation                                      ║\n║ ✅ SKILL CREATION COMPLETE!                                  ║\n╠══════════════════════════════════════════════════════════════╣\n║ Progress: ██████████████████████████████  100%              ║\n╚══════════════════════════════════════════════════════════════╝\n```\n\n**Display summary:**\n\n```\n🎉 Skill created successfully!\n\n📦 Skill Name: your-skill-name\n📁 Location: .github\u002Fskills\u002Fyour-skill-name\u002F\n🔗 Installed: Global (Copilot + Claude)\n\n📋 Files Created:\n   ✅ SKILL.md (1,847 words)\n   ✅ README.md (423 words)\n   ✅ references\u002F (empty, ready for extended docs)\n   ✅ examples\u002F (empty, ready for code samples)\n   ✅ scripts\u002F (empty, ready for utilities)\n\n🚀 Next Steps:\n   1. Test the skill: Try trigger phrases in CLI\n   2. Add examples: Create working code samples in examples\u002F\n   3. Extend docs: Add detailed guides to references\u002F\n   4. Commit changes: git add .github\u002Fskills\u002Fyour-skill-name && git commit\n   5. Share: Push to repository for team use\n\n💡 Pro Tips:\n   - Keep SKILL.md under 2,000 words (currently: 1,847)\n   - Move detailed content to references\u002F folder\n   - Add executable scripts to scripts\u002F folder\n   - Update README.md with real usage examples\n   - Run validation before committing: scripts\u002Fvalidate-skill-yaml.sh\n```\n\n## Error Handling\n\n### Platform Detection Issues\n\nIf platforms cannot be detected:\n```\n⚠️  Unable to detect GitHub Copilot CLI or Claude Code\n    \nWould you like to:\n1. Install for repository only (works when in repo)\n2. Specify platform manually\n3. Skip installation\n```\n\n### Template Not Found\n\nIf templates are missing:\n```\n❌ Error: Template not found at resources\u002Ftemplates\u002F\n\nThis skill requires the cli-ai-skills repository structure.\n\nOptions:\n1. Clone cli-ai-skills: git clone \u003Crepo-url>\n2. Create minimal skill structure manually\n3. Exit and set up templates first\n```\n\n### Validation Failures\n\nIf content doesn't meet standards:\n```\n⚠️  Validation Issues Found:\n\n1. YAML: Description not in third-person format\n   Expected: \"This skill should be used when...\"\n   Found: \"Use this skill when...\"\n   \n2. Content: Word count too high (5,342 words, max 5,000)\n   Suggestion: Move detailed sections to references\u002F\n\nFix automatically? [Y\u002Fn]\n```\n\n### Installation Conflicts\n\nIf symlink already exists:\n```\n⚠️  Skill already installed at ~\u002F.copilot\u002Fskills\u002Fyour-skill-name\n\nOptions:\n1. Overwrite existing installation\n2. Rename new skill\n3. Skip installation\n4. Install to different location\n```\n\n## Bundled Resources\n\nThis skill includes additional resources in subdirectories:\n\n### references\u002F\n\nDetailed documentation loaded when needed:\n- `anthropic-best-practices.md` - Official Anthropic skill development guidelines\n- `writing-style-guide.md` - Writing standards and examples\n- `progressive-disclosure.md` - Content organization patterns\n- `validation-checklist.md` - Pre-commit quality checks\n\n### examples\u002F\n\nWorking examples demonstrating skill usage:\n- `basic-skill-creation.md` - Simple skill creation walkthrough\n- `advanced-skill-bundled-resources.md` - Complex skill with references\u002F\n- `global-installation.md` - Installing skills system-wide\n\n### scripts\u002F\n\nExecutable utilities for skill maintenance:\n- `validate-all-skills.sh` - Batch validation of all skills in repository\n- `update-skill-version.sh` - Bump version and update changelog\n- `generate-skill-index.sh` - Auto-generate skills catalog\n\n## Technical Implementation Notes\n\n**Template Substitution:**\n- Use `sed` for simple replacements\n- Preserve YAML formatting exactly\n- Handle multi-line descriptions with proper escaping\n\n**Symlink Strategy:**\n- Always use absolute paths: `ln -sf \u002Ffull\u002Fpath\u002Fto\u002Fsource ~\u002F.copilot\u002Fskills\u002Fname`\n- Verify symlink before considering installation complete\n- Benefits: Auto-updates when repository is pulled\n\n**Validation Integration:**\n- Run validation before installation\n- Block installation if critical errors found\n- Warnings are informational only\n\n**Git Integration:**\n- Extract author from `git config user.name`\n- Use repository root detection: `git rev-parse --show-toplevel`\n- Respect `.gitignore` patterns\n\n## Quality Standards\n\n**SKILL.md Requirements:**\n- 1,500-2,000 words (ideal)\n- Under 5,000 words (maximum)\n- Third-person description format\n- Imperative\u002Finfinitive writing style\n- Progressive disclosure pattern\n\n**README.md Requirements:**\n- 300-500 words\n- User-facing language\n- Clear installation instructions\n- Practical usage examples\n\n**Validation Checks:**\n- YAML frontmatter completeness\n- Description format (third-person)\n- Word count limits\n- Writing style (no second-person)\n- Required fields present\n\n## References\n\n- **Anthropic Official Skill Development Guide:** https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fclaude-plugins-official\u002Fblob\u002Fmain\u002Fplugins\u002Fplugin-dev\u002Fskills\u002Fskill-development\u002FSKILL.md\n- **Repository:** https:\u002F\u002Fgithub.com\u002Fyourusername\u002Fcli-ai-skills\n- **Writing Style Guide:** `resources\u002Ftemplates\u002Fwriting-style-guide.md`\n- **Progress Tracker Template:** `resources\u002Ftemplates\u002Fprogress-tracker.md`\n","# skill-creator\n\n## Purpose\n\nTo create new CLI skills following Anthropic's official best practices with zero manual configuration. This skill automates brainstorming, template application, validation, and installation processes while maintaining progressive disclosure patterns and writing style standards.\n\n## When to Use This Skill\n\nThis skill should be used when:\n- User wants to extend CLI functionality with custom capabilities\n- User needs to create a skill following official standards\n- User wants to automate repetitive CLI tasks with a reusable skill\n- User needs to package domain knowledge into a skill format\n- User wants both local and global skill installation options\n\n## Core Capabilities\n\n1. **Interactive Brainstorming** - Collaborative session to define skill purpose and scope\n2. **Prompt Enhancement** - Optional integration with prompt-engineer skill for refinement\n3. **Template Application** - Automatic file generation from standardized templates\n4. **Validation** - YAML, content, and style checks against Anthropic standards\n5. **Installation** - Local repository or global installation with symlinks\n6. **Progress Tracking** - Visual gauge showing completion status at each step\n\n## Step 0: Discovery\n\nBefore starting skill creation, gather runtime information:\n\n```bash\n# Detect available platforms\nCOPILOT_INSTALLED=false\nCLAUDE_INSTALLED=false\nCODEX_INSTALLED=false\n\nif command -v gh &>\u002Fdev\u002Fnull && gh copilot --version &>\u002Fdev\u002Fnull 2>&1; then\n    COPILOT_INSTALLED=true\nfi\n\nif [[ -d \"$HOME\u002F.claude\" ]]; then\n    CLAUDE_INSTALLED=true\nfi\n\nif [[ -d \"$HOME\u002F.codex\" ]]; then\n    CODEX_INSTALLED=true\nfi\n\n# Determine working directory\nREPO_ROOT=$(git rev-parse --show-toplevel 2>\u002Fdev\u002Fnull || pwd)\nSKILLS_REPO=\"$REPO_ROOT\"\n\n# Check if in cli-ai-skills repository\nif [[ ! -d \"$SKILLS_REPO\u002F.github\u002Fskills\" ]]; then\n    echo \"⚠️  Not in cli-ai-skills repository. Creating standalone skill.\"\n    STANDALONE=true\nfi\n\n# Get user info from git config\nAUTHOR=$(git config user.name || echo \"Unknown\")\nEMAIL=$(git config user.email || echo \"\")\n```\n\n**Key Information Needed:**\n- Which platforms to target (Copilot, Claude, Codex, or all three)\n- Installation preference (local, global, or both)\n- Skill name and purpose\n- Skill type (general, code, documentation, analysis)\n\n## Main Workflow\n\n### Progress Tracking Guidelines\n\nThroughout the workflow, display a visual progress bar before starting each phase to keep the user informed. The progress bar format is:\n\n```\n[████████████░░░░░░] 60% - Step 3\u002F5: Creating SKILL.md\n```\n\n**Format specifications:**\n- 20 characters wide (use █ for filled, ░ for empty)\n- Percentage based on current step (Step 1=20%, Step 2=40%, Step 3=60%, Step 4=80%, Step 5=100%)\n- Step counter showing current\u002Ftotal (e.g., \"Step 3\u002F5\")\n- Brief description of current phase\n\n**Display the progress bar using:**\n```bash\necho \"[████░░░░░░░░░░░░░░] 20% - Step 1\u002F5: Brainstorming & Planning\"\n```\n\n### Phase 1: Brainstorming & Planning\n\n**Progress:** Display before starting this phase:\n```bash\necho \"[████░░░░░░░░░░░░░░] 20% - Step 1\u002F5: Brainstorming & Planning\"\n```\n\nDisplay progress:\n```\n╔══════════════════════════════════════════════════════════════╗\n║     🛠️  SKILL CREATOR - Creating New Skill                  ║\n╠══════════════════════════════════════════════════════════════╣\n║ → Phase 1: Brainstorming                 [10%]               ║\n║ ○ Phase 2: Prompt Refinement                                 ║\n║ ○ Phase 3: File Generation                                   ║\n║ ○ Phase 4: Validation                                        ║\n║ ○ Phase 5: Installation                                      ║\n╠══════════════════════════════════════════════════════════════╣\n║ Progress: ███░░░░░░░░░░░░░░░░░░░░░░░░░░░  10%              ║\n╚══════════════════════════════════════════════════════════════╝\n```\n\n**Ask the user:**\n\n1. **What should this skill do?** (Free-form description)\n   - Example: \"Help users debug Python code by analyzing stack traces\"\n   \n2. **When should it trigger?** (Provide 3-5 trigger phrases)\n   - Example: \"debug Python error\", \"analyze stack trace\", \"fix Python exception\"\n\n3. **What type of skill is this?**\n   - [ ] General purpose (default template)\n   - [ ] Code generation\u002Fmodification\n   - [ ] Documentation creation\u002Fmaintenance\n   - [ ] Analysis\u002Finvestigation\n\n4. **Which platforms should support this skill?**\n   - [ ] GitHub Copilot CLI\n   - [ ] Claude Code\n    - [ ] Codex\n    - [ ] All three (recommended)\n\n5. **Provide a one-sentence description** (will appear in metadata)\n   - Example: \"Analyzes Python stack traces and suggests fixes\"\n\n**Capture responses and prepare for next phase.**\n\n### Phase 2: Prompt Enhancement (Optional)\n\n**Progress:** Display before starting this phase:\n```bash\necho \"[████████░░░░░░░░░░] 40% - Step 2\u002F5: Prompt Enhancement\"\n```\n\nUpdate progress:\n```\n╔══════════════════════════════════════════════════════════════╗\n║ ✓ Phase 1: Brainstorming                                     ║\n║ → Phase 2: Prompt Refinement             [30%]               ║\n╠══════════════════════════════════════════════════════════════╣\n║ Progress: █████████░░░░░░░░░░░░░░░░░░░░░  30%              ║\n╚══════════════════════════════════════════════════════════════╝\n```\n\n**Ask the user:**\n\"Would you like to refine the skill description using the prompt-engineer skill?\"\n- [ ] Yes - Use prompt-engineer to enhance clarity and structure\n- [ ] No - Proceed with current description\n\nIf **Yes**:\n1. Check if prompt-engineer skill is available\n2. Invoke with current description as input\n3. Review enhanced output with user\n4. Ask: \"Accept enhanced version or keep original?\"\n\nIf **No** or prompt-engineer unavailable:\n- Proceed with original user input\n\n### Phase 3: File Generation\n\n**Progress:** Display before starting this phase:\n```bash\necho \"[████████████░░░░░░] 60% - Step 3\u002F5: File Generation\"\n```\n\nUpdate progress:\n```\n╔══════════════════════════════════════════════════════════════╗\n║ ✓ Phase 1: Brainstorming                                     ║\n║ ✓ Phase 2: Prompt Refinement                                 ║\n║ → Phase 3: File Generation               [50%]               ║\n╠══════════════════════════════════════════════════════════════╣\n║ Progress: ███████████████░░░░░░░░░░░░░░░  50%              ║\n╚══════════════════════════════════════════════════════════════╝\n```\n\n**Generate skill structure:**\n\n```bash\n# Convert skill name to kebab-case\nSKILL_NAME=$(echo \"$USER_INPUT\" | tr '[:upper:]' '[:lower:]' | tr ' ' '-')\n\n# Create directories\nif [[ \"$PLATFORM\" =~ \"copilot\" ]]; then\n    mkdir -p \".github\u002Fskills\u002F$SKILL_NAME\"\u002F{references,examples,scripts}\nfi\n\nif [[ \"$PLATFORM\" =~ \"claude\" ]]; then\n    mkdir -p \".claude\u002Fskills\u002F$SKILL_NAME\"\u002F{references,examples,scripts}\nfi\n\nif [[ \"$PLATFORM\" =~ \"codex\" ]]; then\n    mkdir -p \".codex\u002Fskills\u002F$SKILL_NAME\"\u002F{references,examples,scripts}\nfi\n```\n\n**Apply templates:**\n\n1. **SKILL.md** - Use appropriate template:\n   - `skill-template-copilot.md`, `skill-template-claude.md`, or `skill-template-codex.md`\n   - Substitute placeholders:\n     - `{{SKILL_NAME}}` → kebab-case name\n     - `{{DESCRIPTION}}` → one-line description\n     - `{{TRIGGERS}}` → comma-separated trigger phrases\n     - `{{PURPOSE}}` → detailed purpose from brainstorming\n     - `{{AUTHOR}}` → from git config\n     - `{{DATE}}` → current date (YYYY-MM-DD)\n     - `{{VERSION}}` → \"1.0.0\"\n\n2. **README.md** - Use `readme-template.md`:\n   - User-facing documentation (300-500 words)\n   - Include installation instructions\n   - Add usage examples\n\n3. **References\u002F** (optional but recommended):\n   - Create `detailed-guide.md` for extended documentation (2k-5k words)\n   - Move lengthy content here to keep SKILL.md under 2k words\n\n**File creation commands:**\n\n```bash\n# Apply template with substitution\nsed \"s\u002F{{SKILL_NAME}}\u002F$SKILL_NAME\u002Fg; \\\n     s\u002F{{DESCRIPTION}}\u002F$DESCRIPTION\u002Fg; \\\n     s\u002F{{AUTHOR}}\u002F$AUTHOR\u002Fg; \\\n     s\u002F{{DATE}}\u002F$(date +%Y-%m-%d)\u002Fg\" \\\n    resources\u002Ftemplates\u002Fskill-template-copilot.md \\\n    > \".github\u002Fskills\u002F$SKILL_NAME\u002FSKILL.md\"\n\n# Create README\nsed \"s\u002F{{SKILL_NAME}}\u002F$SKILL_NAME\u002Fg\" \\\n    resources\u002Ftemplates\u002Freadme-template.md \\\n    > \".github\u002Fskills\u002F$SKILL_NAME\u002FREADME.md\"\n\n# Apply template for Codex if selected\nif [[ \"$PLATFORM\" =~ \"codex\" ]]; then\n    sed \"s\u002F{{SKILL_NAME}}\u002F$SKILL_NAME\u002Fg; \\\n         s\u002F{{DESCRIPTION}}\u002F$DESCRIPTION\u002Fg; \\\n         s\u002F{{AUTHOR}}\u002F$AUTHOR\u002Fg; \\\n         s\u002F{{DATE}}\u002F$(date +%Y-%m-%d)\u002Fg\" \\\n        resources\u002Ftemplates\u002Fskill-template-codex.md \\\n        > \".codex\u002Fskills\u002F$SKILL_NAME\u002FSKILL.md\"\n    \n    sed \"s\u002F{{SKILL_NAME}}\u002F$SKILL_NAME\u002Fg\" \\\n        resources\u002Ftemplates\u002Freadme-template.md \\\n        > \".codex\u002Fskills\u002F$SKILL_NAME\u002FREADME.md\"\nfi\n```\n\n**Display created structure:**\n```\n✅ Created:\n   .github\u002Fskills\u002Fyour-skill-name\u002F (if Copilot selected)\n   .claude\u002Fskills\u002Fyour-skill-name\u002F (if Claude selected)\n   .codex\u002Fskills\u002Fyour-skill-name\u002F (if Codex selected)\n   ├── SKILL.md (832 lines)\n   ├── README.md (347 lines)\n   ├── references\u002F\n   ├── examples\u002F\n   └── scripts\u002F\n```\n\n### Phase 4: Validation\n\n**Progress:** Display before starting this phase:\n```bash\necho \"[████████████████░░] 80% - Step 4\u002F5: Validation\"\n```\n\nUpdate progress:\n```\n╔══════════════════════════════════════════════════════════════╗\n║ ✓ Phase 3: File Generation                                   ║\n║ → Phase 4: Validation                    [70%]               ║\n╠══════════════════════════════════════════════════════════════╣\n║ Progress: █████████████████████░░░░░░░░░  70%              ║\n╚══════════════════════════════════════════════════════════════╝\n```\n\n**Run validation scripts:**\n\n```bash\n# Validate YAML frontmatter\nscripts\u002Fvalidate-skill-yaml.sh \".github\u002Fskills\u002F$SKILL_NAME\"\n\n# Validate content quality\nscripts\u002Fvalidate-skill-content.sh \".github\u002Fskills\u002F$SKILL_NAME\"\n```\n\n**Expected output:**\n```\n🔍 Validating YAML frontmatter...\n✅ YAML frontmatter valid!\n\n🔍 Validating content...\n✅ Word count excellent: 1847 words\n✅ Content validation complete!\n```\n\n**If validation fails:**\n- Display specific errors\n- Offer to fix automatically (common issues)\n- Ask user to manually correct complex issues\n\n**Common auto-fixes:**\n- Convert second-person to imperative form\n- Reformat description to third-person\n- Add missing required fields\n\n### Phase 5: Installation\n\n**Progress:** Display before starting this phase:\n```bash\necho \"[████████████████████] 100% - Step 5\u002F5: Installation\"\n```\n\nUpdate progress:\n```\n╔══════════════════════════════════════════════════════════════╗\n║ ✓ Phase 4: Validation                                        ║\n║ → Phase 5: Installation                  [90%]               ║\n╠══════════════════════════════════════════════════════════════╣\n║ Progress: ██████████████████████████░░░░░  90%              ║\n╚══════════════════════════════════════════════════════════════╝\n```\n\n**Ask the user:**\n\"How would you like to install this skill?\"\n\n- [ ] **Repository only** - Files created in `.github\u002Fskills\u002F` (works when in repo)\n- [ ] **Global installation** - Create symlinks in `~\u002F.copilot\u002Fskills\u002F` (works everywhere)\n- [ ] **Both** - Repository + global symlinks (recommended, auto-updates with git pull)\n- [ ] **Skip installation** - Just create files\n\n**If global installation selected:**\n\n```bash\n# Detect which platforms to install for\nINSTALL_TARGETS=()\n\nif [[ \"$COPILOT_INSTALLED\" == \"true\" ]] && [[ \"$PLATFORM\" =~ \"copilot\" ]]; then\n    INSTALL_TARGETS+=(\"copilot\")\nfi\n\nif [[ \"$CLAUDE_INSTALLED\" == \"true\" ]] && [[ \"$PLATFORM\" =~ \"claude\" ]]; then\n    INSTALL_TARGETS+=(\"claude\")\nfi\n\nif [[ \"$CODEX_INSTALLED\" == \"true\" ]] && [[ \"$PLATFORM\" =~ \"codex\" ]]; then\n    INSTALL_TARGETS+=(\"codex\")\nfi\n\n# Ask user to confirm detected platforms\necho \"Detected platforms: ${INSTALL_TARGETS[*]}\"\necho \"Install for these platforms? [Y\u002Fn]\"\n```\n\n**Installation process:**\n\n```bash\n# GitHub Copilot CLI\nif [[ \" ${INSTALL_TARGETS[*]} \" =~ \" copilot \" ]]; then\n    ln -sf \"$SKILLS_REPO\u002F.github\u002Fskills\u002F$SKILL_NAME\" \\\n           \"$HOME\u002F.copilot\u002Fskills\u002F$SKILL_NAME\"\n    echo \"✅ Installed for GitHub Copilot CLI\"\nfi\n\n# Claude Code\nif [[ \" ${INSTALL_TARGETS[*]} \" =~ \" claude \" ]]; then\n    ln -sf \"$SKILLS_REPO\u002F.claude\u002Fskills\u002F$SKILL_NAME\" \\\n           \"$HOME\u002F.claude\u002Fskills\u002F$SKILL_NAME\"\n    echo \"✅ Installed for Claude Code\"\nfi\n\n# Codex\nif [[ \" ${INSTALL_TARGETS[*]} \" =~ \" codex \" ]]; then\n    ln -sf \"$SKILLS_REPO\u002F.codex\u002Fskills\u002F$SKILL_NAME\" \\\n           \"$HOME\u002F.codex\u002Fskills\u002F$SKILL_NAME\"\n    echo \"✅ Installed for Codex\"\nfi\n```\n\n**Verify installation:**\n\n```bash\n# Check symlinks\nls -la ~\u002F.copilot\u002Fskills\u002F$SKILL_NAME 2>\u002Fdev\u002Fnull\nls -la ~\u002F.claude\u002Fskills\u002F$SKILL_NAME 2>\u002Fdev\u002Fnull\nls -la ~\u002F.codex\u002Fskills\u002F$SKILL_NAME 2>\u002Fdev\u002Fnull\n```\n\n### Phase 6: Completion\n\n**Progress:** Display completion message:\n```bash\necho \"[████████████████████] 100% - ✓ Skill created successfully!\"\n```\n\nUpdate progress:\n```\n╔══════════════════════════════════════════════════════════════╗\n║ ✓ Phase 5: Installation                                      ║\n║ ✅ SKILL CREATION COMPLETE!                                  ║\n╠══════════════════════════════════════════════════════════════╣\n║ Progress: ██████████████████████████████  100%              ║\n╚══════════════════════════════════════════════════════════════╝\n```\n\n**Display summary:**\n\n```\n🎉 Skill created successfully!\n\n📦 Skill Name: your-skill-name\n📁 Location: .github\u002Fskills\u002Fyour-skill-name\u002F\n🔗 Installed: Global (Copilot + Claude)\n\n📋 Files Created:\n   ✅ SKILL.md (1,847 words)\n   ✅ README.md (423 words)\n   ✅ references\u002F (empty, ready for extended docs)\n   ✅ examples\u002F (empty, ready for code samples)\n   ✅ scripts\u002F (empty, ready for utilities)\n\n🚀 Next Steps:\n   1. Test the skill: Try trigger phrases in CLI\n   2. Add examples: Create working code samples in examples\u002F\n   3. Extend docs: Add detailed guides to references\u002F\n   4. Commit changes: git add .github\u002Fskills\u002Fyour-skill-name && git commit\n   5. Share: Push to repository for team use\n\n💡 Pro Tips:\n   - Keep SKILL.md under 2,000 words (currently: 1,847)\n   - Move detailed content to references\u002F folder\n   - Add executable scripts to scripts\u002F folder\n   - Update README.md with real usage examples\n   - Run validation before committing: scripts\u002Fvalidate-skill-yaml.sh\n```\n\n## Error Handling\n\n### Platform Detection Issues\n\nIf platforms cannot be detected:\n```\n⚠️  Unable to detect GitHub Copilot CLI or Claude Code\n    \nWould you like to:\n1. Install for repository only (works when in repo)\n2. Specify platform manually\n3. Skip installation\n```\n\n### Template Not Found\n\nIf templates are missing:\n```\n❌ Error: Template not found at resources\u002Ftemplates\u002F\n\nThis skill requires the cli-ai-skills repository structure.\n\nOptions:\n1. Clone cli-ai-skills: git clone \u003Crepo-url>\n2. Create minimal skill structure manually\n3. Exit and set up templates first\n```\n\n### Validation Failures\n\nIf content doesn't meet standards:\n```\n⚠️  Validation Issues Found:\n\n1. YAML: Description not in third-person format\n   Expected: \"This skill should be used when...\"\n   Found: \"Use this skill when...\"\n   \n2. Content: Word count too high (5,342 words, max 5,000)\n   Suggestion: Move detailed sections to references\u002F\n\nFix automatically? [Y\u002Fn]\n```\n\n### Installation Conflicts\n\nIf symlink already exists:\n```\n⚠️  Skill already installed at ~\u002F.copilot\u002Fskills\u002Fyour-skill-name\n\nOptions:\n1. Overwrite existing installation\n2. Rename new skill\n3. Skip installation\n4. Install to different location\n```\n\n## Bundled Resources\n\nThis skill includes additional resources in subdirectories:\n\n### references\u002F\n\nDetailed documentation loaded when needed:\n- `anthropic-best-practices.md` - Official Anthropic skill development guidelines\n- `writing-style-guide.md` - Writing standards and examples\n- `progressive-disclosure.md` - Content organization patterns\n- `validation-checklist.md` - Pre-commit quality checks\n\n### examples\u002F\n\nWorking examples demonstrating skill usage:\n- `basic-skill-creation.md` - Simple skill creation walkthrough\n- `advanced-skill-bundled-resources.md` - Complex skill with references\u002F\n- `global-installation.md` - Installing skills system-wide\n\n### scripts\u002F\n\nExecutable utilities for skill maintenance:\n- `validate-all-skills.sh` - Batch validation of all skills in repository\n- `update-skill-version.sh` - Bump version and update changelog\n- `generate-skill-index.sh` - Auto-generate skills catalog\n\n## Technical Implementation Notes\n\n**Template Substitution:**\n- Use `sed` for simple replacements\n- Preserve YAML formatting exactly\n- Handle multi-line descriptions with proper escaping\n\n**Symlink Strategy:**\n- Always use absolute paths: `ln -sf \u002Ffull\u002Fpath\u002Fto\u002Fsource ~\u002F.copilot\u002Fskills\u002Fname`\n- Verify symlink before considering installation complete\n- Benefits: Auto-updates when repository is pulled\n\n**Validation Integration:**\n- Run validation before installation\n- Block installation if critical errors found\n- Warnings are informational only\n\n**Git Integration:**\n- Extract author from `git config user.name`\n- Use repository root detection: `git rev-parse --show-toplevel`\n- Respect `.gitignore` patterns\n\n## Quality Standards\n\n**SKILL.md Requirements:**\n- 1,500-2,000 words (ideal)\n- Under 5,000 words (maximum)\n- Third-person description format\n- Imperative\u002Finfinitive writing style\n- Progressive disclosure pattern\n\n**README.md Requirements:**\n- 300-500 words\n- User-facing language\n- Clear installation instructions\n- Practical usage examples\n\n**Validation Checks:**\n- YAML frontmatter completeness\n- Description format (third-person)\n- Word count limits\n- Writing style (no second-person)\n- Required fields present\n\n## References\n\n- **Anthropic Official Skill Development Guide:** https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fclaude-plugins-official\u002Fblob\u002Fmain\u002Fplugins\u002Fplugin-dev\u002Fskills\u002Fskill-development\u002FSKILL.md\n- **Repository:** https:\u002F\u002Fgithub.com\u002Fyourusername\u002Fcli-ai-skills\n- **Writing Style Guide:** `resources\u002Ftemplates\u002Fwriting-style-guide.md`\n- **Progress Tracker Template:** `resources\u002Ftemplates\u002Fprogress-tracker.md`\n",{"name":5,"risk":25,"tags":26,"author":31,"created":32,"updated":33,"version":34,"category":35,"platforms":36,"description":7},"safe",[27,28,29,30],"automation","scaffolding","skill-creation","meta-skill","Eric Andrade",1738368000000,1770163200000,"1.3.0","meta",[37,38,39],"github-copilot-cli","claude-code","codex","master","63f17866001c5ca854bf2fa0b678ce277133de5b","skills\u002Fmarketplace\u002Fskill-creator__skills-sickn33-skill-creator",0,"https:\u002F\u002Fgithub.com\u002Fbg-szy\u002FTOP-SKILLS","https:\u002F\u002Fbg-szy.github.io\u002FTOP-SKILLS\u002F","https:\u002F\u002Fgithub.com\u002Fbg-szy","https:\u002F\u002Fwww.ecust.edu.cn\u002F","a student of East China University of Science and Technology","2026-11-15 03:38:02",{"source":8,"skillName":5,"commands":51,"prompt":61,"zipAvailable":62},[52,55,58],{"tool":53,"command":54},"npx","npx skills add bg-szy\u002FTOP-SKILLS --skill skill-creator",{"tool":56,"command":57},"bunx","bunx skills add bg-szy\u002FTOP-SKILLS --skill skill-creator",{"tool":59,"command":60},"pnpm","pnpm dlx skills add bg-szy\u002FTOP-SKILLS --skill skill-creator","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fbg-szy\u002FTOP-SKILLS\u002Fblob\u002Fmaster\u002Fskills\u002Fmarketplace\u002Fskill-creator__skills-sickn33-skill-creator\u002FSKILL.md",true,[64,69,75],{"path":65,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":68,"sourceHtmlUrl":16},"LICENSE.txt","LICENSE","许可证",11357,{"path":70,"resourceType":71,"resourceTypeDesc":72,"sizeBytes":73,"sourceHtmlUrl":74},"README.md","REFERENCE","参考文档",8157,"https:\u002F\u002Fgithub.com\u002Fbg-szy\u002FTOP-SKILLS\u002Fblob\u002Fmaster\u002Fskills\u002Fmarketplace\u002Fskill-creator__skills-sickn33-skill-creator\u002FREADME.md",{"path":76,"resourceType":71,"resourceTypeDesc":72,"sizeBytes":77,"sourceHtmlUrl":78},"skill-report.json",149237,"https:\u002F\u002Fgithub.com\u002Fbg-szy\u002FTOP-SKILLS\u002Fblob\u002Fmaster\u002Fskills\u002Fmarketplace\u002Fskill-creator__skills-sickn33-skill-creator\u002Fskill-report.json",[80,89,96,103,110,117],{"skillNo":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":84,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":88},"01M7DXW9N826PKXK174PVW3038","serpmaven","Scrape Google search results (SERP) to JSON with SERP Maven (serpmaven) - a real Chrome browser on a residential proxy with sticky sessions. Run it as a CLI, a Python library, a local HTTP search API (`serve`), an MCP server or a Docker image; set the proxy login, workers, pages and cost tracking. Use when the user wants Google results, rank tracking, a self-hosted SERP API, or live Google search for an AI agent.","MIT","https:\u002F\u002Fgithub.com\u002Fbg-szy\u002FTOP-SKILLS\u002Fblob\u002Fmaster\u002Fskills\u002Fmarketplace\u002Fserpmaven\u002FSKILL.md",[],[],"2026-11-15 14:19:17",{"skillNo":90,"name":91,"nameZh":6,"description":92,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":84,"licenseFileUrl":6,"sourceHtmlUrl":93,"categories":94,"keywords":95,"publishedAt":88},"01M7DXVHSTWDV65475QEQ915M7","revnu-landing-page-audit","Find out why a landing page isn't turning visitors into signups, demos or sales. Audits one page against what the ad, post or search that sends people there promised, then checks the first screen, proof, call to action, friction and mobile. Returns at most 7 prioritized fixes, plus what is fine and what could not be checked; rewrites specific lines and fixes the page in the repo when asked. Never promises a conversion lift. Works without a Revnu account. Use when the user says or asks: \"audit my landing page\", \"why isn't this page converting\", \"review my homepage\", \"my ads get clicks but no signups\", \"people bounce from the pricing page\", \"CRO review\", \"improve conversion rate\", \"is my hero section clear\", \"roast my landing page\", \"rewrite my headline\", \"what's wrong with this page\", \"landing page feedback\", \"make the signup page convert better\". Not for SEO or AI-search audits, page speed engineering on its own, or building a new page from scratch.","https:\u002F\u002Fgithub.com\u002Fbg-szy\u002FTOP-SKILLS\u002Fblob\u002Fmaster\u002Fskills\u002Fmarketplace\u002Frevnu-landing-page-audit\u002FSKILL.md",[],[],{"skillNo":97,"name":98,"nameZh":6,"description":99,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":84,"licenseFileUrl":6,"sourceHtmlUrl":100,"categories":101,"keywords":102,"publishedAt":88},"01M7DXV8X2D7B3VTD4HHYYHTGR","revnu-growth-context","Write down once who buys, what they're stuck on, what it costs, what proof you have and what you've already tried, so every growth task starts from facts instead of a questionnaire. Creates or updates .agents\u002Frevnu-growth.md from the repo, the live site and the user, and imports an existing product-marketing.md. Use when the user says \"set up our marketing context\", \"who is our ideal customer\", \"write our ICP\", \"describe the product for marketing\", \"positioning doc\", \"what's our brand voice\", \"remember this about our customers\", \"log what we tried\", \"what have we learned from marketing\", \"we changed pricing, update the context\", \"update our growth notes\", \"summarize the business for the agent\", \"import my product-marketing.md\", \"start a growth doc\", or before a first marketing, SEO, outreach or launch task when no context file exists. Works without a Revnu account.","https:\u002F\u002Fgithub.com\u002Fbg-szy\u002FTOP-SKILLS\u002Fblob\u002Fmaster\u002Fskills\u002Fmarketplace\u002Frevnu-growth-context\u002FSKILL.md",[],[],{"skillNo":104,"name":105,"nameZh":6,"description":106,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":84,"licenseFileUrl":6,"sourceHtmlUrl":107,"categories":108,"keywords":109,"publishedAt":88},"01M7DXV0DGJ1G0A60PAHC6J3C5","revnu-get-listed","Get onto the third-party pages AI answers and search cite when buyers ask for the best tool in your category: \"best X\" roundups, directories, review sites, GitHub awesome lists, community threads and comparison pages. Finds which ones are cited, ranks them by fit and effort, and drafts each submission, PR or pitch by the target's own rules. Use when the user says \"get us listed\", \"which directories should we submit to\", \"how do we get into best-of lists\", \"why does ChatGPT recommend competitors and not us\", \"get mentioned in AI answers\", \"submit to awesome lists\", \"get on G2\", \"where are our competitors listed\", \"pitch listicle authors\", \"find backlink opportunities\", \"launch directories\", \"get into roundups\", \"Product Hunt alternatives\", \"where should we be listed\", \"get cited by Perplexity\". Never submits, pays or posts without a yes. Works without a Revnu account.","https:\u002F\u002Fgithub.com\u002Fbg-szy\u002FTOP-SKILLS\u002Fblob\u002Fmaster\u002Fskills\u002Fmarketplace\u002Frevnu-get-listed\u002FSKILL.md",[],[],{"skillNo":111,"name":112,"nameZh":6,"description":113,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":84,"licenseFileUrl":6,"sourceHtmlUrl":114,"categories":115,"keywords":116,"publishedAt":88},"01M7DXTSPMGT9D6DSS0HP9BSTA","revnu-ai-readiness-audit","Audit whether your website gives ChatGPT, Perplexity, Claude, Gemini and Google's AI Overviews something worth quoting, and fix the pages that don't. Use when the user says or asks \"is my site ready for AI search\", \"audit my site for AI answers\", \"AEO audit\", \"GEO audit\", \"why doesn't ChatGPT quote our pricing\", \"make our pages citable by AI\", \"do I need llms.txt\", \"does schema help with ChatGPT\", \"check our structured data\", \"is our content visible without JavaScript\", \"AI SEO audit\", \"optimize our homepage for AI answers\", \"LLM SEO check\", \"why does AI get our product wrong\", \"fix our site for AI Overviews\". Checks fetchability and indexability, answers in the raw HTML, entity facts, schema (including JS-injected markup), headings, dates and llms.txt, then gives at most 10 prioritised fixes and edits the repo when asked. Works without a Revnu account.","https:\u002F\u002Fgithub.com\u002Fbg-szy\u002FTOP-SKILLS\u002Fblob\u002Fmaster\u002Fskills\u002Fmarketplace\u002Frevnu-ai-readiness-audit\u002FSKILL.md",[],[],{"skillNo":118,"name":119,"nameZh":6,"description":120,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":84,"licenseFileUrl":6,"sourceHtmlUrl":121,"categories":122,"keywords":123,"publishedAt":88},"01M7DXSZHCVTRS620GC3S97JZV","proxy-troubleshooting","Diagnose residential proxy failures, with NodeMaven's gateway as the reference - 407 with correct credentials, 406, 410, 500, a connection that hangs, ERR_TUNNEL_CONNECTION_FAILED in a browser, Playwright or Puppeteer ignoring proxy credentials, a sticky session that changes IP, geo-targeting that is silently ignored, passwords with special characters, and unexpected traffic from headless Chrome. Use when a proxy connection fails, returns the wrong location, or costs more traffic than expected.","https:\u002F\u002Fgithub.com\u002Fbg-szy\u002FTOP-SKILLS\u002Fblob\u002Fmaster\u002Fskills\u002Fmarketplace\u002Fproxy-troubleshooting\u002FSKILL.md",[],[]]