Generate concise Conventional Commits under 50 tokens from staged git diffs.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Generate conventional commits
Generate concise, informative Conventional Commits (v1.0.0) from staged changes without conversational preamble or token waste.
## 1. Inspect Staged Changes Compactly
Assess the size and scope of changes before reading full diffs:
```bash
# Check modified files and diff scale
git diff --staged --stat
# Inspect targeted unified diff
git diff --staged
```
For large diffs (> 100 lines), focus on changed symbol definitions, tests, or modified interfaces (`git diff --staged -U1`) rather than dumping thousands of lines into context.
## 2. Conventional Commit Specification
Format the message strictly according to Conventional Commits:
```text
<type>(<scope>): <imperative summary under 72 characters>
- <Optional bullet point explaining why the change was made>
- <Optional bullet point highlighting key behavioral impact or issue reference>
```
### Type Taxonomy
- `feat`: A new user-visible or API capability.
- `fix`: A bug fix or defect correction.
- `docs`: Documentation changes only.
- `refactor`: Code change that neither fixes a bug nor adds a feature.
- `perf`: Code change that improves performance or latency.
…
The line at the top of this page pins the label git:20261015.d651c97, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
GET https://markdownregistry.com/api/v1/artifacts/art_5bqqkcywmpq54ljz
GET https://markdownregistry.com/api/v1/resolve?ref=00200200/maintainer-skills-lab/mkl-generate-commit
GET https://markdownregistry.com/api/v1/blob/54264de5953f69ad8160b370d3649bb3dbfd7833a6be7d9fffa99d2ffef48cdb
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
00200200/maintainer-skills-lab · providers/claude/.claude/skills/mkl-architect-editor/SKILL.md · Two-model pipeline routing high-level design to an Architect model, and mechanical search/replace edits to an Editor…
00200200/maintainer-skills-lab · providers/claude/.claude/skills/mkl-bisect-regression/SKILL.md · Pinpoint regressions using automated git bisect test scripts with zero prompt token waste.
00200200/maintainer-skills-lab · providers/claude/.claude/skills/mkl-bump-version/SKILL.md · Evaluate conventional commits since latest tag, determine next SemVer, and surgically update version files.
00200200/maintainer-skills-lab · providers/claude/.claude/skills/mkl-humanize/SKILL.md · Edit stiff or AI-sounding prose into natural writing while preserving meaning, facts, citations, and the author's point…
00200200/maintainer-skills-lab · providers/claude/.claude/skills/mkl-localize-fault/SKILL.md · Isolate suspect files and line ranges before code repair using AST skeletons and stack traces (< 300 tokens). Use…
