section-review
First-principles, truth-seeking, zero-assumption section review. Decomposes the problem before judging the solution. Questions every decision. Red-teams inputs. Evaluates scalability, security, testability, performance, and maintainability. Names specific alternatives. Calibrates depth to project stage. Talks to a senior engineer who wants the real picture.
npx skills add majiayu000/claude-skill-registry --skill section-review --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
Read `../_house-style/house-style.md` and `references/rating-rubric.md` before writing the review. ## Stage calibration Before starting the review, determine the project stage. This controls how deep you go — not how honest you are. Honesty is always maximum. Depth scales with maturity. | Stage | What to focus on | What to skip or lighten | |---|---|---| | **Prototype / proof of concept** | Does the core idea work? Is the approach fundamentally sound? Are there architectural dead ends that will force a rewrite? | Security hardening, performance optimization, test coverage, dependency health. Flag them as "will matter later" but don't score for them. | | **Active development (pre-launch)** | Architecture, scalability design, security posture, testability, data model correctness. These are cheap to fix now and expensive later. | Minor code quality, polish, optimization. | | **Production / shipped** | Everything. Full depth. Security, performance, maintainability, bus factor, dependency decay, test coverage — all of it matters because real users are affected and changes are expensive. | Nothing. This is the full review. | | **Legacy / maintenance mode** | Maintainability, bus factor,
- Stage calibration
- Mindset
- First principles thinking
- How to question
- Name the alternative
- Adversarial thinking
- Testability evaluation
- Performance and efficiency
- Tone
- Banned phrases
- What brutal actually looks like
- Writing discipline
- Evidence standard
- Core rules
What does the section-review skill do?
First-principles, truth-seeking, zero-assumption section review. Decomposes the problem before judging the solution. Questions every decision. Red-teams inputs. Evaluates scalability, security, testability, performance, and maintainability. Names specific alternatives. Calibrates depth to project stage. Talks to a senior engineer who wants the real picture.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill section-review --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.