AgentSkillLint
A linter for agent skill files (.claude/agents, .cursor/rules, AGENTS.md, CLAUDE.md, MCP server manifests) that catches contradictions, dead branches, unused tools, and broken references.
- Target market
- Teams using Claude Code or Cursor with 5+ skill files, plus skill-pack publishers on awesome-agent-skills who want a quality stamp.
Problem snapshot
What this solves
VoltAgent's awesome-agent-skills directory now lists 1,000+ skills with wildly variable quality, and individual repos accumulate dozens of skill files that contradict each other ('always use bun' in one, 'use npm for installs' in another). There is no validator, so contradictions only surface when an agent does the wrong thing in production.
Full ProvenTools analysis
Unlock the full analysis and build prompt
Unlock the solution, revenue model, feature scope, technical approach, user flow, and 13-section AI build prompt.
Already have access? Sign in
Related ideas
Explore similar problems
Affiliate Attribution Drop Finder
A detector that checks whether affiliate links, landing pages, checkout redirects, cookies, and post-purchase events still preserve attribution.
Agent Action Approval Gate
A runtime approval gate that intercepts only high-risk agent actions, such as refunds, deployments, deletes, emails, and database writes, before execution.
Agent Data-Access Scoper
A Supabase and Postgres RLS test harness that proves which rows an agent role can read or write before the agent is released.