contextlint

Run contextlint over the project's structured Markdown and fix the violations it detects. Use this skill whenever the user asks to fix lint errors, clean up docs, repair broken Markdown links, or after bulk edits to documentation (especially AI-generated specs/ADRs) — even if they don't explicitly mention contextlint by name. Handles broken cross-references, missing required sections, empty table cells, leftover placeholders (TODO/TBD), and circular dependency references across the documentation graph. Reach for this any time the user mentions doc integrity, broken refs, or wants their Markdown checked.

Analyze the impact of changing or deleting a Markdown document by leveraging contextlint's Context Graph. Use this skill whenever the user asks "what breaks if I change X?", "what depends on this doc?", "is it safe to delete this file?", or wants to plan a refactor / understand cross-doc dependencies — even if they don't mention contextlint by name. Detects direct vs transitive impact, identifies orphan docs, and surfaces hidden dependencies that grep alone can't find. Built on contextlint's deterministic graph engine — same input, same answer.

Bootstrap contextlint into a repository. Use this skill whenever the user wants to set up, install, initialize, or configure contextlint — even if they only say "lint setup", "doc integrity check", or "set up Markdown linting" without naming contextlint by name. Detects the package manager (bun/npm/pnpm/yarn), scans the repo's actual doc layout (no hardcoded `docs/` assumption), infers a rule set tailored to the project's structure (ADR style, spec style, table-heavy, etc.), installs `@contextlint/cli`, and writes `contextlint.config.json`. Also handles existing contextlint setups and offers optional GitHub Actions workflow + README scaffolding.