Code review
Global Kiro steering + skills — portable AI engineering layer. Pairs with template-generic-project (spec → handoff → code).
npx -y skills add LaProgrammerie/ai-engineering-core --skill code-reviewAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 0 stars0 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.
What its author says it does
Copied from the file, not written here
Structured code review: correctness, security, tests; checks alignment with handoff and project docs when they exist.
SKILL.md
1.5 KB, as published. Nobody here has run it
Code review (global)
Objective
Review a change systematically and return a prioritized action list without unsolicited large rewrites.
When to use
- Before merging a substantial PR or diff
- On explicit review request
Expected inputs
- Diff, file list, PR link, or change summary
- Stated intent or ticket (if any)
- Known constraints (perf, compatibility, security)
Steps
- Map touched files and stated or carefully inferred intent.
- Correctness: logic, errors, edge cases, API contracts, concurrency where relevant.
- Security: authz, injection, secrets, unsafe defaults.
- Tests: new paths covered, regression risk.
- Maintainability: coupling or readability only if it blocks evolution or reliability.
Documentation alignment (when the repo has it)
If project docs exist, verify consistency with:
docs/ai/active/handoff.md(or equivalent) — scope and allowed filesdocs/ai/02-architecture.md(or equivalent) — boundaries and patternsdocs/ai/03-standards.md(or equivalent) — conventions and commands
Call out drift between code and these documents as review findings.
Output format
- Summary in 2–4 lines
- P0 / P1 / P2 with location (file, symbol, or line when possible) and concrete suggestion
- No massive rewrite unless requested
Gives 0 of the 12 instructions most code review skills give
Counted across 610 of the 674 authors here whose files we hold, read 2026-08-06
- push back with technical reasoning if wrongin 60 of 610, across 24 files
- ask for clarification on unclear itemsin 51 of 610, across 16 files
- fix critical issues immediatelyin 45 of 610, across 29 files
- implement one item at a timein 45 of 610, across 11 files
- group findings by severityin 44 of 610, across 43 files
- verify feedback against the codebasein 42 of 610, across 8 files
- dispatch a code reviewer subagentin 39 of 610, across 23 files
- fix important issues before proceedingin 37 of 610, across 22 files
- test each fix individuallyin 35 of 610, across 7 files
- reply in github comment threadsin 33 of 610, across 5 files
- check for security vulnerabilitiesin 31 of 610, across 27 files
- factualize corrections without over-explainingin 30 of 610, across 2 files
Said here and by no other author read
- Review a change systematically
- Return a prioritized action list
- Map touched files and inferred intent
- Check authorization, injection, secrets, and unsafe defaults
- Assess coupling and readability only if it blocks evolution
- Verify consistency with project documentation
Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once.