mirror of https://github.com/pbakaus/impeccable.git synced 2026-09-12 06:06:37 +03:00

Files

T

Paul BakausandClaude Opus 4.6 efcfd5dadd Merge main into v2.0: consolidate critique skill with scoring, personas, and detection

Merges 54 commits from main including factory-based build system, Trae support,
improved skill descriptions, and security hardening. Consolidates the critique
skill to combine v2.0's sub-agent architecture and automated anti-pattern
detection with main's Nielsen heuristics scoring, cognitive load assessment,
persona-based testing, and structured follow-up workflow. Fixes browser detector
build to create target directory after skill sync.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

2026-03-27 22:20:04 -07:00

3.5 KiB

Raw Blame History

Project Instructions for Claude

CSS Build Process

IMPORTANT: After modifying any CSS files in public/css/ (especially workflow.css or main.css), you MUST rebuild the Tailwind CSS:

bunx @tailwindcss/cli -i public/css/main.css -o public/css/styles.css

The CSS architecture:

public/css/main.css - Main entry point, imports Tailwind and all other CSS files
public/css/workflow.css - Commands section, glass terminal, case studies styles
public/css/styles.css - Compiled output (do not edit directly)

Development Server

bun run dev        # Bun dev server at http://localhost:3000
bun run preview    # Build + Cloudflare Pages local preview

Deployment

Hosted on Cloudflare Pages. Static assets served from build/, API routes handled via _redirects rewrites (JSON) and Pages Functions (downloads).

bun run deploy     # Build + deploy to Cloudflare Pages

Build System

The build system compiles skills and commands from source/ to provider-specific formats in dist/:

bun run build      # Build all providers
bun run rebuild    # Clean and rebuild

Source files use placeholders that get replaced per-provider:

{{model}} - Model name (Claude, Gemini, GPT, etc.)
{{config_file}} - Config file name (CLAUDE.md, .cursorrules, etc.)
{{ask_instruction}} - How to ask user questions

Testing

bun run test       # Run all tests

Unit tests (build, detector logic) run via bun test. Fixture tests (jsdom-based HTML detection) run via node --test because bun is too slow with jsdom. The test script handles this split automatically.

CLI

Impeccable includes a CLI for running anti-pattern detection outside of AI harnesses:

bun bin/impeccable.mjs detect [file-or-dir-or-url...]   # detect anti-patterns
bun bin/impeccable.mjs detect --fast --json src/         # regex-only, JSON output
bun bin/impeccable.mjs --help                            # show help

The detection script is at source/skills/critique/scripts/detect-antipatterns.mjs. It auto-detects browser vs Node and works as both:

CLI/Node: jsdom for HTML, regex for CSS/JSX/TSX, Puppeteer for URLs
Browser: visual overlays injected via <script src="/js/detect-antipatterns-browser.js">

Build the browser script: node scripts/build-browser-detector.js

Versioning

When bumping the version, update all of these locations to keep them in sync:

package.json → version
.claude-plugin/plugin.json → version
.claude-plugin/marketplace.json → plugins[0].version
public/index.html → hero version link text + new changelog entry (user-facing changes only, not internal build/tooling details)

Adding New Skills

When adding a new user-invocable skill, update the command count in all of these locations:

public/index.html → meta descriptions, hero box, section lead
public/cheatsheet.html → meta description, subtitle, commandCategories, commandRelationships
public/js/data.js → commandProcessSteps, commandCategories, commandRelationships
public/js/components/framework-viz.js → commandSymbols, commandNumbers
public/js/demos/commands/ → new demo file + import in index.js
README.md → intro, command count, commands table
NOTICE.md → steering commands count
AGENTS.md → intro command count
.claude-plugin/plugin.json → description
.claude-plugin/marketplace.json → metadata description + plugin description

3.5 KiB Raw Blame History