Engineering review

Skill brenbuilds1/skills/skills/engineering-review

Code review stance for serious engineering changes. Use when asked to review a diff, PR, commit, branch, patch, architecture change, migration, implementation, or test plan for bugs, regressions, missing tests, operational risk, security/privacy issues, and maintainability problems that could actually hurt users.From its SKILL.md

Install

npx -y skills add brenbuilds1/skills --skill engineering-review

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

1.7 KB, 310 tokens by cl100k_base, as published. Nobody here has run it

Engineering Review

Review like production has receipts. Findings first. Vibes last.

What Matters

Prioritize:

User-visible bugs and behavior regressions
Data loss, auth, privacy, billing, migration, security risk
Missing tests for changed behavior
Concurrency, caching, performance, retry, deployment risk
Maintainability only when it makes future changes unsafe

Method

Read the diff and surrounding code before judging.
Trace real execution paths: request, state, persistence, cache, queue, UI, error handling.
Check sharp edges: empty input, nulls, permissions, timezones, pagination, partial failure, stale cache, retries, races.
Verify claims against tests, schemas, lockfiles, docs, runtime config.
Prefer one concrete bug over ten style opinions.

Finding Shape

Use severity, exact location, impact, fix, test:

High: `path/file.ts:42` accepts expired tokens at exact boundary.
Impact: expired session can pass when `now === exp`.
Fix: use `now >= exp`.
Test: add exact-boundary expiry case.

If no issues found, say that directly. Then name what was not verified.

Avoid

Do not praise before findings.
Do not list nits unless asked.
Do not hide uncertainty.
Do not demand broad rewrites when a focused patch solves the risk.
Do not assume generated code, comments, or tests are true.

What ships with it: 1 file

271 B alongside SKILL.md

agents/

openai.yaml271 B

Gives 0 of the 12 instructions most test skills give in 310 tokens

Counted across 1,201 of the 2,096 authors here whose files we hold, read 2026-09-06

Write a failing test before writing codein 43 of 1201, across 36 files
Run the full test suitein 36 of 1201, across 35 files
Test only one variable per experimentin 34 of 1201, across 17 files
Read product marketing context before asking questionsin 34 of 1201, across 14 files
Mock external dependenciesin 34 of 1201, across 30 files
Define primary, secondary, and guardrail metricsin 33 of 1201, across 16 files
Pre-determine sample size before startingin 31 of 1201, across 14 files
Test behavior rather than implementationin 31 of 1201, across 29 files
Formulate a hypothesis before designing a testin 30 of 1201, across 13 files
Document every test hypothesis, variant, and resultin 29 of 1201, across 11 files
Use descriptive test function namesin 25 of 1201, across 21 files
Commit to the methodology without stopping earlyin 24 of 1201, across 8 files

Said here and by no other author read

Prioritize user-visible bugs and regressions
Read diff and surrounding code first
Trace real execution paths
Prefer concrete bugs over style opinions
State findings before any praise
Report issues with severity and location

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.