Stats
Actions
Tags
Help us improve
Share bugs, ideas, or general feedback.
From nlpm
Initializes NLPM for the project — detects artifacts, sets lint strictness, captures a baseline score snapshot, and writes config to .claude/nlpm.local.md.
npx claudepluginhub xiaolai/nlpm-for-claude --plugin nlpmHow this command is triggered — by the user, by Claude, or both
Slash command
/nlpm:initThis command is limited to the following tools:
The summary Claude sees in its command listing — used to decide when to auto-load this command
## Workflow ### Step 1: Check Existing Config Read `.claude/nlpm.local.md`. If exists, show current settings and ask: "Reconfigure? (yes/no)". If no → stop. ### Step 2: Scan Run artifact discovery (same as /nlpm:ls) to show what's in the project. ### Step 3: Ask Strictness ### Step 4: Write Config Create `.claude/` directory if needed. Write `.claude/nlpm.local.md`: ### Step 5: Update .gitignore Append the following to `.gitignore` (skip lines already present): ### Step 6: Capture Baseline Snapshot Score every NL artifact discovered in Step 2 so `/nlpm:trend` has a starting...
/alRuns AgentLint diagnostics across all projects with default core checks for findability, instruction quality, workability, continuity, safety, and harness. Optional deep/session analysis. Initializes config on first run.
/initInitializes or audits .claude/ configuration by detecting repository tech stack and generating CLAUDE.md, settings.json, and rules. Supports --audit and --force flags.
/initBootstraps project.intent.md and project.glossary.json from existing codebase via deterministic scan, LLM synthesis, and interactive editing. Supports --force, --harness, --project-root flags.
/project-healthAudits and manages project configuration: permissions, context, docs. Supports full checks, setup (settings.local.json, CLAUDE.md, .gitignore), tidy, capture learnings, presets, restructure.
/gen-claudeGenerate or enhance CLAUDE.md with project-specific guidance by analyzing codebase structure, languages, frameworks, linters, and build tools.
/cc-bootstrapScans repository to detect full tech stack and generates .claude/ architecture: CLAUDE.md, rules, agents, skills, settings.json, .mcp.json, and docs/context files. Supports --dry-run and --audit.
Share bugs, ideas, or general feedback.
Read .claude/nlpm.local.md. If exists, show current settings and ask: "Reconfigure? (yes/no)". If no → stop.
Run artifact discovery (same as /nlpm:ls) to show what's in the project.
AskUserQuestion:
question: "What lint strictness level?"
header: "Strictness"
options:
- label: "Relaxed"
description: "Threshold 60 — only flag seriously broken artifacts"
- label: "Standard (Recommended)"
description: "Threshold 70 — flag artifacts that need improvement"
- label: "Strict"
description: "Threshold 80 — flag anything below good quality"
Create .claude/ directory if needed. Write .claude/nlpm.local.md:
---
# NLPM Configuration
strictness: {chosen}
score_threshold: {60|70|80}
---
# NLPM Settings
When linting NL artifacts in this project, use **{strictness}** strictness.
Flag artifacts scoring below **{threshold}/100** for improvement.
Append the following to .gitignore (skip lines already present):
# nlpm generated artifacts
.claude/nlpm-history.json
Score every NL artifact discovered in Step 2 so /nlpm:trend has a starting point.
nlpm:scorer and nlpm:vague-scanner in parallel over the discovered artifacts (same dispatch pattern as /nlpm:score). The vague-scanner's counts override the scorer's heuristic detection.commands/shared/append-history.md with scope: "full" and files_scored equal to the artifact count.If Step 2 found zero artifacts, skip this step — there is nothing to score and the partial declines to write empty snapshots.
NLPM initialized for this project.
Strictness: {standard}
Threshold: {70}/100
Artifacts found: {N}
Baseline score: {overall}/100 (snapshot saved to .claude/nlpm-history.json)
Config: .claude/nlpm.local.md
Run /nlpm:score to re-score later, or /nlpm:trend to compare against this baseline.
If Step 6 was skipped (zero artifacts), omit the "Baseline score" line and replace the final sentence with "No artifacts found yet — re-run /nlpm:init after adding artifacts to the project."
Error handling:
.claude/ directory doesn't exist → create it