dev-review skill
✓ VerifiedPerforms holistic pre-push code reviews, design alignment checks, and integration risk assessments for software development lifecycles.
- GitHub stars
- 1,663
- Files
- 2
- Last commit
- Nov 9, 2026
- License
- Apache-2.0
- Allowed tools
- —
What does the dev-review skill do?
dev-review performs holistic pre-push code reviews, design alignment checks, and integration risk assessments for software development lifecycles.
Summary generated from the skill's SKILL.md.
About the dev-review skill
Developers performing final pre-push checks can use this skill to conduct holistic code reviews and integration risk assessments. It functions as a phase nine lifecycle tool that evaluates whether implementation matches architectural intent and design documentation. An agent should load this skill when a user requires design alignment checks, dependency health audits, or a final review before creating a pull request.
The process begins by running npx ai-devkit@latest lint and inspecting git status or diffs to establish context. It examines exported names, type definitions, and API boundaries to ensure contract integrity and prevent leaking framework types into domain logic. The skill produces a structured summary of findings ordered by severity, including specific file and line references, impact assessments, and actionable recommendations. It relies on existing feature docs, grep for tracing callers, and the verify skill to confirm readiness. If the review identifies blocking issues, the agent directs the workflow back to implementation or testing phases instead of proceeding to a push.
What an agent can do with it
- 1Verify design alignmentAsk the agent to ensure that the new code implementation matches the original architectural intent described in the design docs.
- 2Audit API contract integrityRequest a check of API, type, config, and schema boundaries to prevent breaking changes or type leakage.
- 3Identify integration risksHave the agent search for circular dependencies or version conflicts introduced by new imports.
- 4Perform pre-push lintingInstruct the agent to run linting commands for a specific feature before starting the review process.
Written from the skill's SKILL.md. Every use case is checked against a quote from it.
How to install the dev-review skill
Each command copies the skill folder into the client's skills directory. Restart the client or start a new session to load it.Install the dev-review skill in Claude Code
~/.claude/skills/dev-review/SKILL.md
$ npx degit codeaholicguy/ai-devkit/skills/dev-review ~/.claude/skills/dev-reviewInstall the dev-review skill in Claude Code (project)
.claude/skills/dev-review/SKILL.md
$ npx degit codeaholicguy/ai-devkit/skills/dev-review .claude/skills/dev-reviewInstall the dev-review skill in Codex
~/.agents/skills/dev-review/SKILL.md
$ npx degit codeaholicguy/ai-devkit/skills/dev-review ~/.agents/skills/dev-reviewInstall the dev-review skill in Gemini CLI
~/.gemini/skills/dev-review/SKILL.md
$ npx degit codeaholicguy/ai-devkit/skills/dev-review ~/.gemini/skills/dev-reviewInstall the dev-review skill in Claude.ai
npx degit codeaholicguy/ai-devkit/skills/dev-review dev-review && zip -r dev-review.zip dev-review # claude.ai → Customize → Skills → + → Create skill → Upload a skill → dev-review.zip
Automated checks
Ran Nov 15, 2026Full report →Passed our automated checks. That is not a security audit: read the scripts before you let an agent run them. How checks work
- Source repository linked and reachablecodeaholicguy/ai-devkit/skills/dev-review is public and reachablegithub.com/codeaholicguy/ai-devkit/tree/HEAD/skills/dev-revi ↗Pass
- Open source license (OSI)Apache-2.0spdx.org/licenses/Apache-2.0.html ↗Pass
- Commit or release in the last yearLast commit 2026-11-09github.com/codeaholicguy/ai-devkit/commits ↗Pass
- No download-and-run or credential theft in scriptsNo scripts in the skill folderPass
- No hidden instructions in SKILL.mdNo override phrases, safeguard switches, credential requests or hidden charactersgithub.com/codeaholicguy/ai-devkit/blob/HEAD/skills/dev-revi ↗Pass
- Pre-approved tools are scopedNo pre-approved tools; the agent asks before using onegithub.com/codeaholicguy/ai-devkit/blob/HEAD/skills/dev-revi ↗Pass
- SKILL.md follows the Agent Skills formatValid name and description; says when to use it; 43 linesgithub.com/codeaholicguy/ai-devkit/blob/HEAD/skills/dev-revi ↗Pass
SKILL.md
View on GitHubDev Review
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.
- Apply the
verifyskill before claiming readiness. Rundev-smokewhen the change touches user-facing flows. - 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.
- 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.
Files in this skill
2dev-review skill questions
How do I install the dev-review skill in Claude Code?
Run npx degit codeaholicguy/ai-devkit/skills/dev-review ~/.claude/skills/dev-review. Claude Code loads skills from ~/.claude/skills (all projects) or .claude/skills (one project) and uses a skill when its description matches the task.
Which clients can use the dev-review skill?
Any client that reads the Agent Skills format: Claude Code, Codex, Gemini CLI and claude.ai (upload as a ZIP). Scripts in the skill run only where the client allows code execution.
What steps should be taken before starting the review phase?
You should run the lint command using npx ai-devkit@latest lint, check the git status and diff, and read the feature documentation and changed files.
How does the tool handle breaking changes in public APIs?
For public or external APIs, it recommends using parallel changes and deprecation rather than mutating them in place.
What happens if blocking issues are found during the review?
If blocking issues remain, the process should return to the dev-implementation or dev-testing phases.