21 instruction files for AI agents, collected from rikvanriel/code-hygiene. Install any of them at an exact version with mdr add rikvanriel/code-hygiene/<name>.
rikvanriel/code-hygiene · skills/artifact-handoff/SKILL.md · Use when handing an artifact to someone, or trusting one you received — identity, provenance, verification.
rikvanriel/code-hygiene · skills/catalog/SKILL.md · Use when starting work in an unfamiliar repo, setting up hygiene skills, or unsure which skills a task needs…
rikvanriel/code-hygiene · skills/change-splitting/SKILL.md · Use when committing or splitting a large change — tests whether it splits into easy-to-review smaller changes: mixed…
rikvanriel/code-hygiene · skills/changelog-quality/SKILL.md · Use when drafting or reviewing a commit message, changelog entry, diff summary, test plan, cover letter, or PR…
rikvanriel/code-hygiene · skills/code-structure/SKILL.md · Use when a function is too long, nests too deep, or mixes themes. Extracts helpers that earn their names.
rikvanriel/code-hygiene · skills/evidence-discipline/SKILL.md · Use when measuring, benchmarking, or validating anything — proves the instrument, the sample, and the artifact.
rikvanriel/code-hygiene · skills/factual-integrity/SKILL.md · Use when writing or verifying claims — numbers, hashes, quotes, perf results. Sources or TODOs it.
rikvanriel/code-hygiene · skills/language-style-sampling/SKILL.md · Use when working in an unfamiliar language or matching an unfamiliar codebase style. Derives a style guide by sampling.
rikvanriel/code-hygiene · skills/llm-tells/SKILL.md · Use as a final pass before commit or PR, or when text sounds AI-generated. Strips AI tells from code, comments…
rikvanriel/code-hygiene · skills/plan-iteration-gate/SKILL.md · Use when refining a draft plan, stuck iterating, or deciding whether to escalate to a human. Converges via 4Q loop.
rikvanriel/code-hygiene · skills/pre-commit-check/SKILL.md · Use before commit or push, or when asking if work is ready. Runs hygiene, changelog, and never-invent gates.
rikvanriel/code-hygiene · skills/project-discovery/SKILL.md · Use before editing anything in a repo or asking how a project wants contributions. Finds upstream's own rules.
rikvanriel/code-hygiene · skills/repo-hygiene/SKILL.md · Use when something must not live in a maintained source tree — paths, runtime state, data, duplicates.
rikvanriel/code-hygiene · skills/self-review-gate/SKILL.md · Use before final output on non-trivial work, or before irreversible or externally visible steps. Checks errors, better…
rikvanriel/code-hygiene · skills/skill-authoring/SKILL.md · Use when writing, editing, or reviewing a skill's description, tags, structure, or size. Matches triggers to loading…
rikvanriel/code-hygiene · skills/socratic-spec/SKILL.md · Use when the goal is ambiguous, needs clarifying, or has 3+ steps. Builds a spec one question per turn.
rikvanriel/code-hygiene · skills/systematic-debugging/SKILL.md · Use when debugging a failure — failing test, crash, broken behavior, or flake. Finds root cause before fixing.
rikvanriel/code-hygiene · skills/upstream-hygiene/SKILL.md · Use before commit, amend, push, or PR, or when cleaning a tainted message. Keeps private context out of public history.