devs:code-review
/devs:code-review
Use when reviewing code changes — a diff, branch, PR, or named files. Carries the review method: scoping the change-set, converting suspicions into verified findings, and ranking by evidence-backed severity. Language idioms belong to the language skills (rust-core, python-core, typescript-core, react-core); security review specifics to security-core.
- Author
- aaronbassett ↗
- Repository
- agent-foundry ↗
- Licence
- MIT
- Last repository change
- 16.08.2026
Assessment and security
- Files in this package
- 4
- Scripts
- 0
- HTML comments
- 0
- URLs in SKILL.md
- 0
No signals detected. Repository changed on 16.08.2026, without references to retired models or APIs.
MIT, open: use and modify while retaining author attribution.
What it does and when to use it
Use when reviewing code changes — a diff, branch, PR, or named files. Carries the review method: scoping the change-set, converting suspicions into verified findings, and ranking by evidence-backed severity. Language idioms belong to the language skills (rust-core, python-core, typescript-core, react-core); security review specifics to security-core.
Original author description
Use when reviewing code changes — a diff, branch, PR, or named files. Carries the review method: scoping the change-set, converting suspicions into verified findings, and ranking by evidence-backed severity. Language idioms belong to the language skills (rust-core, python-core, typescript-core, react-core); security review specifics to security-core.
How it works
- Reference routing
- Delegation
- The method in one paragraph
SKILL.md preview
--- name: devs:code-review description: "Use when reviewing code changes — a diff, branch, PR, or named files. Carries the review method: scoping the change-set, converting suspicions into verified findings, and ranking by evidence-backed severity. Language idioms belong to the language skills (rust-core, python-core, typescript-core, react-core); security review specifics to security-core." --- # Code Review — Method The review method for producing evidence-based, severity-ranked findings. A finding that hasn't been checked against the actual code is a guess, not a finding. This skill deliberately ships no analysis scripts: a reviewer that can read the diff, search the codebase, and run the project's own toolchain outperforms any metric-generating script — run the project's real commands instead. ## Reference routing | Reference | Use when | |---|---| | [diff-scoping.md](references/diff-scoping.md) | Getting the right change-set, reading order, blast radius, scope discipline | | [review-method.md](references/review-method.md) | The evidence bar per finding class; converting suspicion into verified finding | | [severity-taxonomy.md](references/severity-taxonomy.md) | Blocking/Important/Minor tiers and the evidence each requires | ## Delegation - **Security findings** — the `devs:security-core` skill (its review-lens reference is the weighted security checklist). - **Language-idiom findings** — the matching language skill defines idiomatic: `devs:rust-core`, `devs:python-core`, `devs:typescript-core`, `devs:react-core` (+ `devs:react-components` for component house style). Load the skill for each language in the diff. - **Dependency findings** (new packages in the diff, lockfile changes) — the `devs:deps-core` skill. ## The method in one paragraph Scope the exact change-set and read it in dependency order. Judge every hunk in its real context — the whole function, its callers, the data it touches. For each candidate finding, attempt refutation against the code (guards, types, existing tests), verify by execution where cheap, and file only what survives — at the severity its verified impact supports, with file:line and a concrete failure scenario. Run the project's own gauntlet (its lint/typecheck/test commands, not a guessed list) and never flag what the project's tooling already enforces or explicitly disables.
Files in this package (4)
- SKILL.md 2 KB
- references/diff-scoping.md 3 KB
- references/review-method.md 4 KB
- references/severity-taxonomy.md 2 KB
Versions
The database has no other skills named devs:code-review.
Database snapshot: 13.11.2026 · package version 11ca0481afc8 (SHA-256 digest of the entire package)
Downloads in the last 30 days: 0 · ranking
Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.
Similar skills
- 80devs:react-core
Use when building or debugging React applications — component and hook idioms, rendering and re-render performance, state architecture, data fetching, application security, project architecture, or choosing React-ecosystem packages. Contains runtime-verified references, a… - 80devs:security-core
Use when designing or reviewing authentication, authorization, secrets handling, rate limiting, or server-side HTTP hardening — and as the security lens for code review. Owns cross-language security decisions and policies; client-side browser security (XSS, CSP from the app's… - 90code-review
Review code changes for correctness, security, and maintainability with severity-ranked, evidence-based findings. Use when asked to review a diff, a pull request, or a file before merge. - 100review
Independent code review of changes (uncommitted work, a branch, a commit range, a GitHub PR or given files) by the code-reviewer subagent, plus security-auditor for sensitive code; findings are verified and ranked by severity, with fixes. Use when the user asks for a review… - 81code-review-lifecycle
审查当前仓库的代码改动、分支或已有 PR,自动确定范围与基线,修复已确认问题并验证、复审,最后准备人工检查材料。明确只读时仅交付审查结果。 - 90code-review
Review EF Core pull requests or local changes for concrete correctness, compatibility, performance, security, and test-coverage problems. Use when asked to review, critique, or check code changes before merge or submission.