review-health
First-pass strategic-orientation review of a repository. Produces an evidence-cited map (not a grade) calibrated to a reference class, helping the user decide where to engage, where to tread carefully, and where to leave alone. Advisory only — no changes made.
npx skills add majiayu000/claude-skill-registry --skill review-health --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.
What it does
The skill performs a high-level, evidence-based orientation of a repository. It collects signals across repo shape, history, tooling, and documentation in an Observe phase, then classifies the repo against a reference class and applies a rubric to dimensions like test health, dependency health, CI/automation health, documentation, and architecture hygiene. It outputs a Coverage Manifest of signals and offers 2-4 strategic engagement options for the user to choose from, without making any changes to the repository. It routes deeper work to sibling specialists as needed.
How it works
Phase 0 — Preflight: determine user intent and scope (whole repo or a subset). Phase 1 — OBSERVE: enumerate signals across repo shape, Git history, tooling, and documentation; collect evidence with citations (file:line, tool output, or explicit non-collection entry). Generate a structured Observation Record with IDs (e.g., O1, O2, ...). Phase 2 — ORIENT:
- 2a: Classify the repo by loading reference classes and weighing evidence against the user lens to select the best-fit class; provide a hedged classification.
- 2b: Load the rubric for the matched class.
- 2c: Apply the rubric to dimensions, assigning a Foundational / Adequate / Strong level with evidence citations.
- 2d: Attach ASHI severity levels to notable findings within each dimension.
- 2e: Synthesize cross-cutting findings across dimensions.
- 2f: Produce an updated Coverage Manifest noting any signals that could not be assessed. Phase 3 — DECIDE: generate 2-4 engagement options for the user’s lens, each citing Orient findings. Phase 4 — ACT: present top 3-5 concrete recommendations and routing to sibling skills if deeper work is needed.
When to use it
Use when you need a strategic, non-intrusive orientation of a repository to decide where to engage, where to tread carefully, and where to leave alone. Ideal for inherited repos, evaluating a FOSS project for adoption, onboarding teammates, or revisiting your own project’s strategy. The output is advisory only and does not modify the repository.
What it can touch
The skill operates as advisory only and does not perform code changes. It may reference outputs from signals such as repo shape, Git history, tooling signals, and documentation signals, but it does not execute modifications or apply fixes.
Caveats
All claims must be supported by observed evidence with citations (e.g., file:line or tool outputs). If a signal or tool could not be collected, the skill records a Coverage Manifest entry detailing what was attempted and why it could not be collected. The classification is contagious to downstream dimensions only through the reference-class rubric and observed signals; it is not an absolute verdict. The output is contingent on the availability of reference-class rubrics and observed data in the repository.
# Review-Health — Strategic Orientation for a Repository A first-pass review skill for the moment you want to step back and assess a repo strategically: you've just inherited it, you're evaluating a FOSS project for adoption, you're onboarding a teammate, or you're revisiting your own project to decide where to invest. The skill produces an evidence-cited map of the repo's state — not a grade. Its output is built to inform strategic decisions about engagement, not to itemize every imperfection. **This skill is advisory only. It makes no changes.** To act on findings, hand off to `/refactor`, `/review-arch`, `/review-test`, `/review-security`, or other specialists as the findings indicate. ## Philosophy **Observation before interpretation.** The skill's procedure enforces an OODA cadence — Observe, Orient, Decide, Act — with strict phase gates. The Observe phase collects signals without verdicts. Only after observation is complete does interpretation begin. This is the structural countermeasure to the most common failure mode of informal code review: fixating on the first file opened and building a distorted mental model from there. **"Good" is relational, not absolute.** A 34% test
- Philosophy
- Cognitive Failure Modes This Skill Countermands
- Workflow Overview
- Workflow Details
- Phase 0 — Preflight
- Phase 1 — OBSERVE
- Phase 2 — ORIENT
- Phase 3 — DECIDE
- Phase 4 — ACT
- Evidence Discipline
- Agent Coordination
- Sibling-Skill Composition
- Output Format
- Abort Conditions
What does the review-health skill do?
First-pass strategic-orientation review of a repository. Produces an evidence-cited map (not a grade) calibrated to a reference class, helping the user decide where to engage, where to tread carefully, and where to leave alone. Advisory only — no changes made.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill review-health --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.