The best platform agnostic Linter for AI agent plugins and skills — validates structure, frontmatter, and token limits for Claude Code, Cursor, Codex, and many others!
This repository also configures its own agents. See what skilllint tells them →
Skill Claude CodeCodex
Strategic rebase with mandatory pre-analysis. Use when asked to rebase a branch onto main (or any target). Runs a file-level diff of both sides before touching git, produces a per-file disposition plan (KEEP/MERGE/DROP/REWRITE), and only then executes the rebase. Prevents surprise conflicts and silent data loss from…
Skill Claude CodeCodex
Work through every unresolved review thread on a PR to completion — validate, fix if warranted, reply, resolve, then re-check on a bounded schedule. Use after pushing a commit to a PR, or when asked to check or address PR reviews.
Skill Claude Code
Produce a structured, end-to-end linear walkthrough of an unfamiliar codebase. Use when onboarding to a new repository, understanding how a system works from entry points through execution paths, or generating navigable codebase documentation. Spawns parallel subagents for discovery, tracing, validation, and synthesis…
Skill Claude Code
Enforces memory-mapped file I/O for large file processing in Python. Use when reading, searching, or processing files larger than 100MB, or when performing delimiter/boundary searches without loading the entire file into RAM. Rejects pathlib.readbytes(), readtext(), and f.read() on files of unknown or large size.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: