← ClaudeAtlas

devex-reviewlisted

Audit the developer experience of your project — setup friction, onboarding clarity, local dev loop speed, tooling consistency, and documentation gaps. Produces a DX scorecard and prioritized improvement list. Inspired by gstack's devex-review skill.
manastalukdar/ai-devstudio · ★ 1 · Code & Development · score 77
Install: claude install-skill manastalukdar/ai-devstudio
# DevEx Review I'll audit your project's developer experience end-to-end: setup friction, onboarding, local dev loop, tooling consistency, documentation gaps. You get a scored DX report and a ranked list of quick wins. Inspired by gstack's devex-review skill. ## Token Optimization **Expected range**: 400–1,000 tokens (full audit), 50 tokens (no project structure found) **Patterns used**: Bash for file discovery, Grep-before-Read, progressive disclosure (scores → details on request) **Early exit**: If no `package.json`, `Makefile`, `pyproject.toml`, or similar project manifest is found, report "No project manifest found — cannot audit DX" and stop. ## Step 1 — Discover Project Structure ```bash # Detect project type and manifest files ls -la package.json pyproject.toml Cargo.toml go.mod Makefile Dockerfile \ README.md CONTRIBUTING.md .env.example .envrc 2>/dev/null # Check for common dev tooling ls -la .github/workflows/ .circleci/ .gitlab-ci.yml \ .editorconfig .prettierrc .eslintrc* .flake8 2>/dev/null # Check dev setup scripts ls -la scripts/ bin/ Makefile 2>/dev/null | head -20 # Local dev loop — what commands exist? if [ -f package.json ]; then node -e "const p=require('./package.json'); console.log(JSON.stringify(Object.keys(p.scripts||{})))" 2>/dev/null fi if [ -f Makefile ]; then grep "^[a-zA-Z].*:" Makefile | head -20 fi ``` ## Step 2 — Evaluate Eight DX Dimensions Score each dimension 1–5 (5 = excellent, 1 = painful). ### D1 — First-Run Set