Conventions Improver
Audit and improve project conventions files (AGENTS.md, CLAUDE.md, GEMINI.md). Scans for all conventions files, evaluates quality against a scoring rubric, outputs a quality report, then makes targeted improvements with user approval. Use when asked to check, audit, update, or improve AGENTS.md or similar files.
Install
npx skills add euxx/claude-skills-for-copilot --skill conventions-improvergit clone --depth 1 https://github.com/euxx/claude-skills-for-copilot.git /tmp/claude-skills-for-copilot
mkdir -p ~/.claude/skills
cp -r /tmp/claude-skills-for-copilot/skills/conventions-improver ~/.claude/skills/conventions-improverPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# Conventions File Improver Audit, evaluate, and improve project conventions files (AGENTS.md, CLAUDE.md, GEMINI.md) to ensure AI agents have optimal project context. **This skill can write to conventions files.** After presenting a quality report and getting user approval, it applies targeted improvements. ## Workflow ### Phase 1: Discovery Find all conventions files in the repository using this priority order: AGENTS.md, then CLAUDE.md, then GEMINI.md. Search for files named `AGENTS.md`, `CLAUDE.md`, or `GEMINI.md` at the root and in any subdirectories. **File Types & Locations:** | Type | Location | Purpose | | ---------------- | ------------------------------------------- | ----------------------------------------- | | Project root | `./AGENTS.md` (or `CLAUDE.md`, `GEMINI.md`) | Primary project context, shared with team | | Package-specific | `./packages/*/AGENTS.md` | Module-level context in monorepos | | Subdirectory | Any nested location | Feature/domain-specific context | **Note:** AI agents auto-discover conventions files in parent directories, so monorepo setups work automatically. ### Phase 2: Quality Assessment For each conventions file found, evaluate it against the following scoring rubric (total: 100 points): #### Scoring Criteria **1. Commands/Workflows (20 points)**
Details
- Skill name
conventions-improver- Repository
- euxx/claude-skills-for-copilot
- Path
skills/conventions-improver/SKILL.md- License
- MIT
- Repo updated
- 2 November 2026
FAQ
What does the Conventions Improver skill do?
Audit and improve project conventions files (AGENTS.md, CLAUDE.md, GEMINI.md). Scans for all conventions files, evaluates quality against a scoring rubric, outputs a quality report, then makes targeted improvements with user approval. Use when asked to check, audit, update, or improve AGENTS.md or similar files.
How do I install the Conventions Improver skill?
skills CLI (Claude Code, Cursor, Codex and more): npx skills add euxx/claude-skills-for-copilot --skill conventions-improver. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Conventions Improver popular?
It lives in euxx/claude-skills-for-copilot, which has 5 GitHub stars and 0 forks.
Related skills
Code Review
5euxx/claude-skills-for-copilot
Multi-agent code review for local changes, files, or directories. Detects bugs, security issues, and conventions-file violations (AGENTS.md/CLAUDE.md/GEMINI.md).
Code Simplifier
5euxx/claude-skills-for-copilot
Simplifies and refines code for clarity, consistency, and maintainability while preserving all functionality. Works on recently modified code, a set of changes, or the whole codebase.
Comment Analyzer
5euxx/claude-skills-for-copilot
Analyzes code comments for accuracy, completeness, and long-term maintainability. Detects comment rot and misleading documentation. Use after adding or modifying code comments.
Domain Modeling
9sandbaseai/workbuddy-skill
Use when establishing or changing domain vocabulary, relationships, boundaries, context documents, or architecture decisions so the model stays precise and consistent with code.
Context Management
5Sagargupta16/claude-skills
Use when managing Claude Code context window during long sessions, when context feels degraded, or when deciding between /compact, /clear, /rewind, and sub-agents. Covers context rot detection, compaction timing, branching strategy, and sub-agent isolation patterns.
Eval Driven Dev
9sandbaseai/workbuddy-skill
Use when improving a Python LLM application with reproducible evaluation criteria, golden datasets, instrumentation, run evidence, and a prioritized quality plan.
Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.