xiaolaixiaolaiCommunity·4 Agent Skills Included

nlpm

Score, lint, and test natural-language agent configuration files

Scores and lints the markdown files that drive coding assistants, including skills, agents, commands, hooks, rules, and memory files. Catches vague wording, broken cross-references, missing manifest entries, and security risks before they silently break your setup. Works across Claude Code, Codex CLI, and Antigravity with a deterministic 100-point rubric and auto-fix commands.
npx skills add xiaolai/nlpm --all -g -y
Available:

Tells the agent how nlpm's commands, sub-agents, and skills fit together so it can route scoring, checking, fixing, and testing requests to the right component.

All Skills in This Repository (4)

Pure Emerald Level Indicators

Frequently Asked Questions

FAQPage Schema
How to install nlpm?

Run `npx skills add xiaolai/nlpm --all -g -y` in your terminal to install all skills in this collection globally.

What does nlpm actually check?

It scores skills, agents, commands, hooks, rules, and memory files against a 100-point rubric, flagging vague wording, missing descriptions, broken references, and manifest files that don't match what's on disk.

Does nlpm work with Codex CLI and Antigravity?

Yes. The scoring rubric covers Claude Code, Codex CLI, and Antigravity through per-tool convention overlays, and the standalone nlpm-check validator runs anywhere with Python 3.11+.

Can nlpm run in CI or pre-commit hooks?

Yes. The single-file Python validator bin/nlpm-check runs without any assistant installed and exits non-zero on high-confidence findings, with drop-in pre-commit and GitHub Actions templates included.

Can nlpm fix problems automatically?

Yes. The /nlpm:fix command auto-repairs mechanical findings, and /nlpm:test lets you write spec files first so new artifacts are verified against expectations before shipping.

Related Repositories in Software Engineering

View All in Software Engineering