forge
Lean code implementation pair. Claude (Smith) writes code, Gemini (Temper) reviews for bugs, security, and edge cases. ~2x token cost for high-quality code output.
按技能名称、说明或 GitHub 作者匹配的结果。
Lean code implementation pair. Claude (Smith) writes code, Gemini (Temper) reviews for bugs, security, and edge cases. ~2x token cost for high-quality code output.
Permission validation, architecture patterns, anti-patterns, and best practices for Claude Code settings management
Automated test coverage analysis with support for multiple testing frameworks, coverage reporting, gap identification, metric tracking, and quality gate enforcement. Use when Claude needs to analyze test covera...
Automated code review assistance including best practices evaluation, security vulnerability detection, performance optimization suggestions, code quality assessment, and style guide enforcement. Use when Claud...
Organize Claude Code instructions into modular rule files in .claude/rules/. Use when setting up project standards, adding team conventions, creating domain-specific rules, or managing shared coding guidelines.
Run Codex plan validation or implementation review as a quality gate for non-trivial tasks. Use after planning or implementation.
This skill automatically detects when CLAUDE.md files need updates based on codebase analysis. It identifies new patterns, code violations, stale documentation, and anti-patterns, then proposes specific markdow...
Diagnose and fix issues with Claude Code skills (malformed frontmatter, broken structure, loading errors, missing files). Use when a skill isn't working, won't load, or needs validation.
Enforce homelab-proxmox workflow patterns including single source of truth documentation, prompt logging, git commits, environment variables, and phase tracking. Use this skill when completing tasks, updating d...
Automatically runs project validation commands (linters, type checkers, tests) after file edits and blocks commits on any failure. Reads validation commands from CLAUDE.md or auto-detects from project type. Enf...
Use when setting up git workflows for Claude Code - installs pre-commit hooks, commit templates with Claude attribution, PR templates, branch naming helpers, and Claude-specific gitignore entries
Dual-AI code validation using both Claude and Google Gemini to catch 20% more issues. Validates React Native screens for security vulnerabilities, performance anti-patterns, accessibility gaps, and best practic...
Conventional Commits formatting guide for creating standardized commit messages. Use when Claude needs to create git commits, ensuring consistent message format with type prefixes (feat, fix, docs, chore). Auto...
Expert skill for analyzing Claude Code primitive structures (skills, commands, hooks) in projects. Performs deep quality analysis, detects naming conflicts, validates best practices, identifies missing configur...
Validate and optimize CLAUDE.md files using Anthropic's best practices for focused sessions. Detects contradictions, redundancy, excessive length (200+ lines), emphasis overuse (2%+ density), broken links, and...
Applies Sun Lab Python coding conventions when writing, reviewing, or refactoring code. Covers .py files, docstrings, type annotations, naming conventions, README.md files, git commit messages, and Claude skill...
This skill provides guidance on using OpenAI's Codex CLI for detail-oriented code analysis. Use when the user explicitly invokes "/codex", asks to "use codex", "run codex", "have codex review", or when Claude d...
This skill should be used when the user asks to "analyze this project", "what type of project is this", "detect project structure", "understand this codebase", or when Claude needs to determine project type for...
Code review for all uncommitted changes (staging status is irrelevant). Checks CLAUDE.md compliance, identifies bugs, security issues, style problems, and simplification opportunities.
Markdown linting and automated fixing using markdownlint-cli2. Use when Claude needs to: (1) Check markdown files for style issues, (2) Fix markdown formatting problems, (3) Ensure markdown follows best practic...
Guide conventional commit creation with mandatory pre-commit checks for the Shortcuts project. Use when: (1) Creating commits, (2) Running pre-commit checks, (3) Following conventional commit format, (4) Ensuri...
Reviews code for ClaudeMix project, verifying adherence to 3-layer architecture, TDD principles, and coding standards. Generates detailed review reports with scoring and improvement recommendations.
Automatically assesses confidence in code changes. Apply after making edits to evaluate certainty and flag risky areas. Use when Claude should self-critique changes.
Help users configure and verify LSP (Language Server Protocol) setup for Python and JavaScript/TypeScript in Claude Code. This skill should be used when users ask about LSP configuration, need to check if LSP s...
默认按已收录数据中的 GitHub 仓库 Stars 排序。Stars 属于来源仓库,同一仓库的多个技能可能共享相同数值;它反映仓库关注度,不代表单个技能的安装量或质量评分。