implement
Generate clean C# code, Markdown files, agents, prompts, skills in MacroFlow.
Découvrez les skills blockchain automation tools, comparez leurs dépôts et consultez leurs instructions.
Generate clean C# code, Markdown files, agents, prompts, skills in MacroFlow.
Comprehensive forensic analysis skill for enterprise codebases across Azure, Dynamics 365, C#, SAP, Mulesoft, Power Platform, and more. Covers security, performance, architecture, and compliance in multi-langua...
Open files edited by the agent in VSCode after making changes, using the bundled open-changed-files script (silent no-op when unavailable).
Find, triage, and fix bugs with or without user input. Autonomously scan codebases, produce an issues list, implement a fix, create a fix branch, commit via semantic-commit, and open a PR with gh.
Automated documentation auditing - ensures CLAUDE.md coverage, updates stale docs, recommends structural improvements
Use when creating or editing agent definitions - ensures proper frontmatter, clear structure, validation of references, and no duplication with existing agents
Analyze problems, design solutions, plan task breakdowns. Use for epic planning, architecture design, and task specification. Outputs planning artifacts for GitHub issue creation.
Baseline justfile commands - exact comment strings, all projects implement these
Use when setting up git pre-commit and pre-push hooks - provides simple shell script approach and pre-commit framework method, both calling justfile commands for DRY principle
Use when setting up GitHub Actions CI/CD for pull request checks - provides workflow templates for Python, JavaScript, and polyglot projects that run quality gates on every PR
Learn project conventions, detect patterns, suggest consistency improvements
Design, discover, and refactor multi-command workflows for Claude Code
Provides systematic code review with focus on quality, security, and best practices. Use when reviewing code, doing PR reviews, or asking for code feedback.
File-mediated parallel security audit for codebases. Launches domain-specific auditors that write findings to files, then synthesizes into consolidated report. Token-efficient through file state instead of cont...
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.
Guidelines and checklist for thorough code review.
Explore codebase, understand architecture, find how things work. Navigate unfamiliar repositories, discover code structure, find where functionality lives by intent rather than exact text. NOT for debugging fai...
Generate architecture documentation, create codebase maps, document code structure. Create ARCHITECTURE.md, generate mermaid diagrams, label modules and processes, write READMEs describing the codebase. NOT for...
Analyze blast radius, check what will break, review changes before commit. Use for pre-commit review, PR risk assessment, planning safe refactors, or checking if changes are safe to merge. NOT for debugging (us...
Refactor code, rename symbols, extract modules, split services. Plan safe refactoring by mapping dependencies, find what depends on code before moving or deprecating APIs. NOT for quick change impact (use chang...
Creates a streamlined pull request from v2 (staging) to main (production) with change summary, affected apps detection, and deployment checklist. This skill should be used when ready to deploy staging changes t...
Manage development and content logs for Hugo static sites. Use this skill when working with Hugo websites to track changes, add log entries for code modifications or content updates (posts, tutorials, projects)...
Create or update a quality gate decision for a story or code changes. Runs quality checks, specialist reviews, and produces a persistent YAML gate file with actionable findings. Supports PASS, CONCERNS, FAIL, o...
Use when asked to create or edit style guides, design systems, component libraries, or update existing frontend components for web projects
Le classement utilise les étoiles du dépôt GitHub indexé. Plusieurs skills peuvent partager ce nombre : ce n’est ni un nombre d’installations ni une note de qualité.