tufantunc
UserRepository-aware AI code review for coding agents — triage → 13 specialist reviewers → synthesis. Reviews what the agent changed and what the repo already knew. Claude Code, opencode, Cursor, Codex.
Categories
Indexed Skills (15)
a11y
Accessibility audit of changed UI code: semantic HTML, ARIA correctness, focus management, keyboard support, contrast, name/role/value. Conditionally dispatched when the diff touches interactive UI. Use for accessibility review, a11y, ARIA, focus or keyboard-nav audit of a diff.
ai-antipatterns
Audit for AI-written-code anti-patterns: hallucinated APIs/symbols/imports, invented config/env keys, needless dependencies, over-engineering, ignored existing conventions/helpers. Use for AI code review, hallucination check, over-engineering or ignored-conventions audit of a diff.
api-contract
API contract & type-safety audit of changed code: breaking signature/route/response changes without versioning, schema drift, serialization issues, any/cast at boundaries, back-compat-breaking enum/union changes. Use for API contract review, back-compat check, schema or type-boundary audit of a diff.
backend
Backend design audit of changed code: error handling, input validation, transactional/atomic boundaries, idempotency, rate limiting, API shape, service-boundary leaks. Use for backend review, API handler audit, validation or transaction-safety check of a diff.
correctness
Correctness audit of changed code: logic bugs, broken existing functionality, cross-file side effects, race conditions, error-path gaps, devex regressions, feature-gate leaks. Use for bug review, breakage check, side-effect tracing, devex or feature-gate leak audit of a diff.
craft
Strict maintainability audit: code-judo, the 1k-line rule, spaghetti growth, abstraction/boundary quality, layer leaks, type-boundary cleanliness, canonical-helper reuse. Use for code quality review, refactor, maintainability or code-judo audit of a diff.
db
Database & migration safety audit of changed code: destructive/non-reversible migrations, data-loss transformations, missing indexes, constraint correctness, query correctness, transaction boundaries. Use for migration review, DB safety, index or query-correctness audit of a diff.
dry
Repo-wide duplication and canonical-reuse audit: copy-pasted logic, near-duplicate functions/components, reinvented utilities, missing shared abstractions. Use for DRY review, duplicate detection, or canonical-helper reuse audit of a diff.
frontend
Frontend design audit of changed code: component structure, state placement, prop drilling, design-system consistency, effect correctness, loading/error states, i18n-readiness. Use for frontend review, component or state audit, UI consistency check of a diff.
performance
Performance audit of changed code: N+1 queries, algorithmic complexity regressions, unnecessary re-renders, memory leaks, blocking work, missing pagination, bundle bloat. Use for performance review, N+1 check, complexity or memory-leak audit of a diff.
review-pro-triage
Stage 1 of review-pro: classify changed files, detect relevant specialist reviewers, detect active stacks, scope context per reviewer, and emit a dispatch plan. Use to start a review-pro review, triage a PR/branch, or fan out reviewers.
review-pro
One-command AI code review. Runs triage -> relevant specialist reviewers -> synthesis on the current branch and returns the verdict + report. Stack-specific signals are loaded automatically from the repo's .review-pro/ directory. Use to review a branch or PR with review-pro.
security
Security audit of changed code: authn/authz bypass, secret/PII leaks, injection, unsafe deserialization, weak crypto, CSRF/SSRF/open redirect, feature-gate leaks. Use for security review, authz check, secret leak, injection or deserialization audit of a diff.
tests
Test-quality audit of changed tests/code: weak or missing assertions, missing coverage for new behavior/branches/edge cases, flaky patterns, unrealistic test data, testing implementation details, skipped tests. Use for test review, coverage check, flakiness or assertion-quality audit of a diff.
review-pro-synthesize
Stage 3 of review-pro: dedup, weight, resolve conflicts, calibrate severity, and produce the final verdict + report from specialist findings. Use to merge reviewer results into one review verdict.
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.