Skip to content

hoavdc/CodexKit / skills/codexkit-high-signal-review

codexkit-high-signal-review

Verified

Review changes with a risk-first mindset that prioritizes bugs, regressions, missing tests, and operational gaps.

FileKindSize
SKILL.mdskill md2.1 KB
agents/openai.yamlconfig210 B
examples/common-mistakes.mdmarkdown814 B
examples/good-output.mdmarkdown796 B
references/severity-rubric.mdmarkdown262 B
verification/checklist.mdmarkdown1.3 KB

examples/common-mistakes.md

View on GitHub
# Common Mistakes — High-Signal Review

> Anti-patterns to watch for when using the High-Signal Review skill.

## 1. Wall of nitpicks

**What goes wrong:** 20 minor comments with no severity ranking — the author can't tell what matters

**How to fix it:** Categorize: Blockers (must fix) → Important (should fix) → Nits (nice to fix)

## 2. Destructive feedback

**What goes wrong:** 'This section is wrong' without explaining what's wrong or how to fix it

**How to fix it:** Every critique must include: what's wrong + why + specific improvement

## 3. Reviewing what you wish it was

**What goes wrong:** Redesigning the author's approach instead of reviewing what they actually wrote

**How to fix it:** Review against the stated goals. If goals are wrong, say so — but that's a separate discussion.
finishing-a-development-branchobra/superpowersUse when implementation is complete, all tests pass, and you need to decide how to integrate the workStars: 322kUpdated Claude CodeCodexVerifiedInstall
systematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixesStars: 322kUpdated Claude CodeCodexVerifiedInstall
test-driven-developmentobra/superpowersUse when implementing any feature or bugfix, before writing implementation codeStars: 322kUpdated Claude CodeCodexVerifiedInstall
skill-creatoranthropics/skillsCreate new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.Stars: 198kUpdated Claude CodeCodexVerifiedInstall