Maintainer Skills Lab
by
Provides a collection of reusable AI agent skills and workflows for Codex, Claude Code, Cursor, and Grok Bot, with tools for change detection, skill installation, and an optional MCP server for documentation monitoring.
Maintainer Skills Lab Overview
What is Maintainer Skills Lab about?
Maintainer Skills Lab offers a curated set of 16 "skills"—self‑contained prompts and utilities—that enhance AI coding assistants (Codex, Claude Code, Cursor, Grok Bot). Skills cover writing improvement, bug reproduction, ML‑training debugging, PR review, source‑change verification, README generation, localization, and more. All skills share a single Markdown source; generated client‑specific versions are kept in sync automatically. The project also ships a Skill Watch utility that detects changes in source documentation and flags affected skills, with an optional local MCP server for continuous monitoring.
How to use Maintainer Skills Lab?
- Install a single skill via the Vercel Skills CLI:
Replacenpx skills@1.5.26 add 00200200/maintainer-skills-lab --skill mkl-humanize --agent codex --copy--agent codexwith--agent claude-code,--agent cursor, or follow the Grok Bot recipes for other clients. - Install the full library into a target project:
Usegit clone https://github.com/00200200/maintainer-skills-lab.git cd maintainer-skills-lab python3 tools/kit.py install --target codex --project /path/to/your/repo--target claudeor--target cursorfor the respective clients. - Sync changes after editing a skill source:
python3 tools/kit.py sync - Run Skill Watch to catch outdated instructions:
python3 examples/skill-watch/run.py - Set up the staged‑export Git hook to prevent committing stale generated files:
python3 -B tools/check_staged.py
Key Features
- Unified Markdown source → deterministic generation of client‑specific skill files.
- Six ready‑made agent profiles for Codex, Claude Code, Cursor, and Grok Bot that combine multiple skills into end‑to‑end workflows.
- Skill Watch: local scraper + CLI that compares documentation against a saved baseline and signals which skills need review.
- Optional MCP server for continuous change monitoring (SDK installed separately).
- Git‑hook guard to enforce that generated provider copies stay in sync with their sources.
- Zero‑model requirement: all tooling runs with the standard library; only the AI client provides the model.
- Cross‑client compatibility: same skill works in Codex, Claude Code, Cursor, and manually in Grok Bot.
- Open‑source MIT license, CI badges, and pre‑built ZIP artifacts for offline use.
Use Cases
| Scenario | How Maintainer Skills Lab Helps |
|---|---|
| Improve draft documentation | Use the mkl-humanize skill to rewrite prose while preserving facts, code snippets, and caveats. |
| Reproduce and verify a bug | Chain mkl-reproduce-bug and mkl-verify-fix to generate a minimal failing example and confirm the fix automatically. |
| Debug ML training runs | Invoke mkl-debug-ml-training to spot shape mismatches, NaNs, or optimizer issues across PyTorch, Lightning, and TensorFlow/Keras. |
| Automate PR reviews | Run mkl-review-pr to get actionable findings with file locations and impact analysis. |
| Keep documentation in sync with code | Skill Watch flags when source docs change, prompting a run of mkl-review-source-change. |
| Localize README or comments | mkl-localize-pl-en provides fluent Polish↔English translations while preserving placeholders and commands. |
| Enforce commit hygiene | The staged‑export hook prevents committing out‑of‑date generated skill files. |
FAQ
- Do I need an OpenAI/Anthropic API key? No. The tooling itself runs locally; only the chosen AI client (Codex, Claude Code, Cursor, Grok Bot) requires its own credentials.
- Can I use the library with other AI platforms? Currently supported agents are Codex, Claude Code, Cursor, and Grok Bot. Adding a new client would require creating a provider folder and mapping the skill files.
- Is the MCP server mandatory? It is optional. Skill Watch works fully offline; the MCP server only adds a persistent monitoring service.
- What Python version is required? Python 3.11+ (the tools are standard‑library only). CI also tests against 3.13.
- How are generated files kept in sync?
tools/kit.py syncregenerates all provider copies from the master Markdown sources and CI validates that the repository’s checked‑in copies match. - Can I contribute a new skill?
Yes. Edit the source Markdown under
skills/NEW-SKILL/SKILL.mdand runtools/kit.py syncto produce client versions. Follow the CONTRIBUTING guide for PR etiquette.
Maintainer Skills Lab's README
Maintainer Skills Lab
Make stiff drafts readable. Debug code and ML training with reproducible evidence.
16 skills and 6 agent profiles for Codex, Claude Code, Cursor, and Grok Bot. The workflows share one Markdown source, with generated versions for each client. Start with one skill, or get the full library with its agents.
Try Humanizer
The Humanizer skill edits a draft in its original language, keeping facts, code, quotations, and meaningful caveats intact.
| Before | One possible edit |
|---|---|
We are thrilled to announce that you can now leverage --dry-run to preview changes. Windows has not been tested yet. |
Use --dry-run to preview changes. We haven't tested Windows yet. |
This is an authored illustration. More examples and acceptance checks →
Install one skill
With Node.js 22.20.0+ and Git, run this in the project where you want to use it:
npx skills@1.5.26 add 00200200/maintainer-skills-lab --skill mkl-humanize --agent codex --copy
For Claude Code, replace --agent codex with --agent claude-code.
For Cursor, use --agent cursor. This uses the third-party
Vercel Skills CLI to install one skill
locally in the current project. Read the linked skill before installing it.
Then ask your client:
Use mkl-humanize to improve this draft. Preserve its facts, code, and limitations. Explain any edit that changes the emphasis.
Explicit invocation uses $mkl-humanize in Codex CLI or /mkl-humanize in
Claude Code and Cursor. Installation, removal, and recorded checks →
Prefer Python or downloadable files? Install the full library or get a ZIP. Grok Bot uses manual setup recipes.
Find your next useful skill
| You want to… | Start here | What you get |
|---|---|---|
| Keep a consistent writing voice | Match voice | An edit grounded in supplied writing samples |
| Fix a bug with evidence | Reproduce bug → Verify fix | An observed failure and a comparable check of the fix |
| Debug a training run | Debug ML training | Focused PyTorch, Lightning, and TensorFlow/Keras diagnostics with a runnable example |
| Review a pull request | Review PR | Actionable findings with locations and consequences |
| Review changed reference docs | Review source change | Supported instruction updates, unaffected claims, and gaps that need evidence |
| Explain your project | Write README | An introduction and quickstart grounded in the actual repository |
| Work in Polish and English | Localize PL ↔ EN | Natural wording with commands, placeholders, and meaning preserved |
Browse all 16 skills and 6 agents → Includes tutorials, UX copy, launch posts, maintainer replies, issue triage, regression tests, and releases. The six agent profiles combine these workflows for bug investigation, ML training diagnosis, PR review, source-change review, release editing, and writing.
Catch outdated agent instructions
Skill Watch compares selected source documentation with a saved baseline and shows which skills, dependent agents, and generated client files need review. It includes a local scraper, CLI, and optional MCP server, with no model or API key required.
Try an authored change in a disposable project, without network access:
python3 examples/skill-watch/run.py
-Checkpoints remain enabled during this diagnostic.
+Checkpoints are disabled during this diagnostic.
Checks preserve the saved baseline. Accepting a new source version is explicit. A changed page is a signal to review the instructions, not proof that they are wrong. Watch real sources and connect through MCP →
Use Review source change with the diff and affected files, or let the source reviewer assess them together:
Use mkl-review-source-change to review this documentation diff against the affected skills. Identify supported corrections and instructions that remain valid. Flag missing evidence; return a review before making edits.
It also works with a supplied diff, without MCP. Worked review and acceptance cases →
Debug a loss that looks wrong
Your predictions are [[1], [3]], your labels are [1, 3], and the raw mean
squared residual is 2. Why isn't it zero? Broadcasting compares every
prediction with every label. Aligning these scalar regression labels produces
the intended per-example loss of 0.
Debug ML training helps investigate shape errors, NaNs, missing gradients, and reproducibility problems in PyTorch, Lightning, and TensorFlow/Keras. The ML investigator agent combines it with fix verification. These frameworks are the subject of the task; use the skill in your existing Codex, Claude Code, Cursor, or Grok Bot setup.
Use mkl-debug-ml-training to investigate this training failure. Keep the current framework and compare one fixed batch before and after the proposed fix.
Run the CPU example in your framework → It checks loss, gradients, and an optimizer update against an analytical result.
Start in a minute
Get the full library and native agents with Python 3.11+. The exporter, installer, and Skill Watch CLI use only the standard library. The optional MCP server installs its SDK separately.
git clone https://github.com/00200200/maintainer-skills-lab.git
cd maintainer-skills-lab
# The destination must be an existing project. Inspect changes first.
python3 tools/kit.py install --target codex --project /path/to/your/repo --dry-run
python3 tools/kit.py install --target codex --project /path/to/your/repo
Use --target claude or --target cursor for the other coding clients. The installer
adds the full library for one target, preserves unrelated files, and refuses
conflicting local edits. Start with one installation method and target per project;
mixed-client discovery is an untested limitation.
Updates, removal, and ZIPs →
One source, four versions
python3 tools/kit.py sync
Editing skills/mkl-humanize/SKILL.md generates:
providers/
├── codex/.agents/skills/mkl-humanize/SKILL.md
├── claude/.claude/skills/mkl-humanize/SKILL.md
├── cursor/.cursor/skills/mkl-humanize/SKILL.md
└── grok-bot/skills/mkl-humanize.md
Agent definitions in agents/*.toml combine shared skills. Their generated
versions embed the workflows they need, so a source edit also updates dependent
agents. CI checks that the checked-in copies match their source.
| Client | Get the files | How to use them |
|---|---|---|
| Codex | Skills + native agents | Project-local installation |
| Claude Code | Skills + native agents | Project-local installation |
| Cursor | Skills + native agents | Project-local installation |
| Grok Bot (SpaceXAI) | Skill + agent recipes | Set up in the Bot, try a task, then save the workflow as a skill |
Grok Bot recipes follow the official x.ai documentation. They are Markdown instructions for manual setup; copying them does not create a Bot. Issue Scout and Release Reporter include first-task prompts and optional routines.
Catch incomplete commits with a hook
Changed a skill but forgot to stage its generated versions? The optional staged export guard catches that before the commit is created. It checks the exact staged files, so a correct working tree cannot hide stale provider copies in the index. Unstaged edits are left alone.
python3 -B tools/check_staged.py
For contributors to this library and its forks. Setup, examples, and limits →
Check the evidence
Run a complete local regression example without a model or API key:
python3 examples/bugfix/run.py
Baseline: assertion-failure
Candidate: pass
Verified for this fixture: True
This checks the bundled example, not agent performance.
The same independent test runs against both implementations in fresh Python processes. Inspect the fixture and its limits →
Preview status: source/export checks and tool/fixture tests are automated. Humanizer installation and removal with Skills CLI 1.5.26 were checked for all three coding-client targets. Live-client discovery, writing quality, and Grok Bot execution have not yet been evaluated. Native agents inherit model and execution policy from the host. Compatibility matrix · Evaluation guide
Make it useful for you
Missing a workflow or found a rough edge? Open an issue with the task and a small example. To contribute a skill, edit one source and generate the client versions: contribution guide.
If a skill earns a place in your workflow, star the repository to find it again. To hear about changes, use GitHub's Watch → Custom → Releases.
Community, in numbers
Badges above refresh through Shields and GitHub and may be cached. This chart is a dated snapshot of GitHub data, refreshed alongside substantive changes. Views and unique visitors cover GitHub's returned 14-day window. The star chart groups current stargazers by their original star date; removed stars are excluded. Aggregate data · How it is generated
python3 tools/kit.py list
python3 tools/kit.py check
python3 tools/kit.py sync --check
python3 -m unittest discover -s tests -v
python3 examples/bugfix/run.py
python3 tools/kit.py build
Builds produce four deterministic ZIPs in dist/. CI checks Python 3.11 and 3.13
on Linux and macOS and uploads archives as run artifacts. Check the linked run
for the revision you intend to use. The checker validates this repository's
small authoring format; it is not a general YAML validator or a live-model benchmark.
Credits and license
blader/humanizer is a related project in the same problem space. This library's writing workflows and worked examples are authored here.
MIT. Independent community project; not affiliated with or endorsed by OpenAI, Anthropic, Cursor, or SpaceXAI/xAI.
Maintainer Skills Lab Reviews
Login Required
Please log in to share your review and rating for this MCP.
Similar MCP Servers like Maintainer Skills Lab
Explore related MCPs that share similar capabilities and solve comparable challenges
Git
Officialby modelcontextprotocol
A Model Context Protocol server for Git repository interaction and automation.
Zed
OfficialClientby zed-industries
A high‑performance, multiplayer code editor designed for speed and collaboration.
Everything
Officialby modelcontextprotocol
Model Context Protocol Servers
Time
Officialby modelcontextprotocol
A Model Context Protocol server that provides time and timezone conversion capabilities.
Cline
OfficialClientby cline
An autonomous coding assistant that can create and edit files, execute terminal commands, and interact with a browser directly from your IDE, operating step‑by‑step with explicit user permission.
Context7 MCP
Officialby upstash
Provides up-to-date, version‑specific library documentation and code examples directly inside LLM prompts, eliminating outdated information and hallucinated APIs.
Daytona
by daytonaio
Provides a secure, elastic infrastructure that creates isolated sandboxes for running AI‑generated code with sub‑90 ms startup, unlimited persistence, and OCI/Docker compatibility.
Continue
OfficialClientby continuedev
Enables faster shipping of code by integrating continuous AI agents across IDEs, terminals, and CI pipelines, offering chat, edit, autocomplete, and customizable agent workflows.
GitHub MCP Server
by github
Connects AI tools directly to GitHub, enabling natural‑language interactions for repository browsing, issue and pull‑request management, CI/CD monitoring, code‑security analysis, and team collaboration.