Workflow skill
Dev Review Skill
Run a final pre-push review across design, implementation, tests, and risk.
On this page
Install command
AI DevKit installs its built-in skills as one curated set. Run this once to install dev-review with the rest of the built-in workflow skills.
npx ai-devkit@latest skill add --built-inWhat it does
Use dev-review before pushing or merging work. It focuses on bugs, regressions, missing tests, and alignment with the approved design.
When to use it
- Review work before push
- Find integration risks and missing tests
- Check final design and implementation alignment
Supported agents
- Claude Code
- Codex
- Cursor
- opencode
The SKILL.md file
This is what your agent reads when the skill runs. View it on GitHub (opens in a new tab)
Run final pre-push review for configured AI docs features. Before changing docs or code, propose the concrete review plan and wait for user approval unless the user already approved the exact phase plan.
Phase Contract#
- Run
npx ai-devkit@latest lintbefore phase work. - If working on a named feature, run
npx ai-devkit@latest lint --feature <name>. - Check
git status -sbandgit diff --stat. - Read feature docs and relevant changed files before findings.
- Load
verifywith your skill tool before claiming readiness. Loaddev-smokewith your skill tool when the change touches a user-facing entry point (CLI command, API route or RPC handler, UI screen, daemon or wire protocol); skipping it requires a stated reason. - If parent
dev-lifecycleestablished usable task tracing, emit review phase, progress, blocker/finding, next-step, and final evidence/readiness events pertask.
Code Review#
Use for Phase 9. Take a holistic review stance: findings first, ordered by severity, grounded in file/line references.
- Gather context: feature description, modified files, design docs, risky areas, tests already run.
- Verify design alignment by summarizing architectural intent and checking implementation matches.
- For each modified file, grep exported names to trace callers and dependents. Read relevant signatures, call sites, and type definitions.
- Check consistency against 1-2 similar modules.
- Search for existing utilities the new code could reuse or now duplicates. Flag near-matches honestly; do not force a wrong abstraction.
- Verify contract integrity at API, type, config, and schema boundaries.
- Check boundary discipline: external data is validated at edges, internal code is not littered with redundant guards, and transport/storage/framework types do not leak through domain APIs.
- Check reader load: needless layers, pass-through methods, broad shallow interfaces, mutable state scope, and unclear value ownership.
- Check domain fit: branch growth, synchronized flags, repeated shape assumptions, temporal decomposition, and missing state models.
- Check dependency health, including circular dependencies or version conflicts from new imports.
- Check breaking changes. For public/external APIs, recommend parallel change and deprecation over in-place mutation. For in-repo-only callers, all callers should be migrated and legacy APIs deleted.
- Check rollback safety, especially irreversible migrations or one-way data/state changes.
- For bug fixes, check the fix lands at the owner of the broken invariant, not only at the caller that triggered it; flag other paths that can still violate it.
- Review file by file for correctness, logic, edge cases, redundancy, security, performance, error handling, and test coverage.
- Check cross-cutting concerns: naming conventions, documentation updates, missing tests, config/migration changes.
- Summarize blocking issues, important follow-ups, and nice-to-haves. Per finding include file, issue, impact severity, and recommendation.
- If task tracing is available, add blockers and set
blockedfor blocking findings; if review passes with final evidence, close the task pertask. - Complete final checklist: design match, no logic gaps, security addressed, integration points verified, tests cover changes, docs updated.
Done: if the checklist passes, the feature is ready to push and create a PR. If blocking issues remain, return to dev-implementation or dev-testing.