Skill Claude CodeCodex
How to write SKILL.md files that trigger reliably and teach effectively. Use when creating, improving, or reviewing skills for any tool — SKILL.md is the cross-tool open spec (agentskills.io), read identically by Claude Code, Codex CLI, and Antigravity.
Command
Check cross-artifact consistency — reference integrity, orphans, contradictions.
Command
Auto-fix fixable findings in NL artifacts — missing fields, heading gaps, field renames.
Command
Prepare NLPM for this project — detect artifacts, set strictness, capture baseline trend snapshot.
Command
Discover all natural language programming artifacts in a repository.
Command
Render a self-contained HTML report — per-file scores, score trend, cross-artifact graph, vocabulary noun-verb map, drift candidates, and findings — into .claude/nlpm-reports/. Opens directly via file://. No server, no build, no network.
Command
Score NL programming artifacts — 100-point quality score per file.
Command
Scan a Claude Code plugin for security risks in executable artifacts (hooks, scripts, MCP configs, dependencies).
Command
Sync nlpm's convention overlays with the latest official Claude Code / Codex / Antigravity specs — research upstream docs, diff, apply corrections, propagate, check.
Command
Run NL artifact tests — evaluate artifacts against .nlpm-test/.spec.md specifications (TDD for natural language programming).
Command
Show quality score trends over time — track improvements, detect degradation.
Command
Find vocabulary drift in a corpus without a declared registry — judgment-based clustering of likely-synonymous nouns and verbs. Advisory only, no penalty. Use for early-stage projects or as a periodic health check before/alongside R51.
Command
Create a vocabulary skill for the target project — detect layout, extract literary warrant from the corpus, seed canonical noun/verb tables, write the opt-in stub. Use to start adopting R51 vocabulary discipline in any Claude Code plugin or NL-artifact-heavy repo.
Hook
Runs after a tool call finishes for Write, Edit and MultiEdit tool calls, executing check-artifact.sh. From xiaolai/nlpm.
Command Claude Code
Bump Claudepot version numbers in lock-step across Cargo.toml, Cargo.lock, package.json, src-tauri/tauri.conf.json, README.md, the web install page, and stub a CHANGELOG section. Runs a quality gate first. Does not commit — leaves changes for review, and documents the tag/push path that follows.
Command Claude Code
Scaffold a new React component grounded in the paper-mono primitives. Requires explicit kind or a nearest-existing-component match. No empty divs, no speculative scaffolding.
Command Claude Code
Review UI changes against the paper-mono design rules. Requires a screenshot or running pnpm tauri dev for render-time checks.
Hook Claude Code
Runs before the agent uses a tool for Bash tool calls, running an inline shell check. From xiaolai/claudepot-app.
Settings file Claude Code
Agent settings declaring 1 hook event (PreToolUse).
MCP server Claude CodeCodexCursor +2
A Model Context Protocol server for use with Tauri v2 applications. Runs locally from the @hypothesi/tauri-mcp-server npm package.
MCP server Claude CodeCodexCursor +2
MCP server "codex-cli" as configured in xiaolai/claudepot-app. Launched with codex mcp-server.
Instructions file CodexOpenCode
Instructions for xiaolai/claudepot-app, covering claudepot, shared memory (dogfooding), build, test and gui (tauri).
Instructions file
Instructions for xiaolai/claudepot-app, a project described as: A control panel for Claude Code and Claude Desktop.
Instructions file Gemini CLI
Instructions for xiaolai/claudepot-app, a project described as: A control panel for Claude Code and Claude Desktop.