Init
Skill Verified ActiveCreates, updates, or optimizes an AGENTS.md file for a repository with minimal, high-signal instructions covering non-discoverable coding conventions, tooling quirks, workflow preferences, and project-specific rules that agents cannot infer from reading the codebase. Use when setting up agent instructions or Claude configuration for a new repository, when an existing AGENTS.md is too long, generic, or stale, when agents repeatedly make avoidable mistakes, or when repository workflows have changed and the agent configuration needs pruning. Applies a discoverability filter—omitting anything Claude can learn from README, code, config, or directory structure—and a quality gate to verify each line remains accurate and operationally significant.
To establish and maintain effective, high-signal AI agent instructions for repositories by focusing on non-discoverable project-specific nuances.
Features
- Generates minimal, high-signal AGENTS.md instructions
- Covers non-discoverable coding conventions and project rules
- Applies a discoverability filter to omit inferable information
- Includes a quality gate to verify instruction accuracy and significance
- Supports setting up new agent configurations or pruning existing ones
Use Cases
- Setting up agent instructions for a new repository
- Updating stale or overly long AGENTS.md files
- Pruning agent configurations when repository workflows change
- Reducing repeated avoidable mistakes made by agents
Non-Goals
- Providing a general codebase overview
- Including information discoverable from README, code, or config
- Listing generic best practices
- Enforcing rules already covered by linters or tests
Installation
npx skills add mcollina/skillsRuns the Vercel skills CLI (skills.sh) via npx — needs Node.js locally and at least one installed skills-compatible agent (Claude Code, Cursor, Codex, …). Assumes the repo follows the agentskills.io format.
Quality Score
VerifiedTrust Signals
Similar Extensions
Context Optimization
100This skill should be used when the user asks to "optimize context", "reduce token costs", "improve context efficiency", "implement KV-cache optimization", "partition context", or mentions context limits, observation masking, context budgeting, or extending effective context capacity.
Context Compression
100This skill should be used when the user asks to "compress context", "summarize conversation history", "implement compaction", "reduce token usage", or mentions context compression, structured summarization, tokens-per-task optimization, or long-running agent sessions exceeding context limits.
Cleanup Dashboards
100Audit and consolidate HubSpot reporting dashboards. Identifies unused, duplicate, or outdated dashboards. Must be performed manually — no dashboard API is available.
ClawSweeper Skill
100Use for all ClawSweeper work: OpenClaw issue/PR sweep reports, commit-review reports, repair jobs, cloud fix PRs, @clawsweeper maintainer mention commands, trusted ClawSweeper-reviewed autofix/automerge, GitHub Actions monitoring, permissions, gates, and manual backfills.
Audit Dependency Versions
100Audit project dependencies for version staleness, security vulnerabilities, and compatibility issues. Covers lock file analysis, upgrade path planning, and breaking change assessment. Use before a release to ensure dependencies are current and secure, during periodic maintenance reviews, after receiving a security advisory, when upgrading to a new language version, before submitting to CRAN or npm, or when inheriting a project to assess its dependency health.
Janitor Usage
100Show which skills you use and which you never use