CtrlK
BlogDocsLog inGet started
Tessl Logo

react-doctor

Use when finishing a feature, fixing a bug, before committing React code, or when the user types `/doctor`, asks to scan, triage, or clean up React diagnostics. Covers lint, accessibility, bundle size, architecture. Includes a regression check and a full local-triage workflow that fetches the canonical playbook.

69

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

The canonical home for this skill is react-doctor in millionco/react-doctor

SKILL.md
Quality
Evals
Security

Quality

Content

82%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A tight, highly actionable body that gives copy-paste commands and clear workflows with validation feedback for the regression path. Minor conciseness redundancy and delegation of the triage validation steps to a remote playbook keep it from the top band.

Suggestions

Remove the duplicated `npx react-doctor@latest --verbose --scope changed` block and flag table — keep one canonical 'Command' reference section and link to it from the workflow sections.

Inline the key validation checkpoint of the /doctor triage loop (e.g. 're-run `--scope changed` and confirm the score did not drop before stopping') so the destructive working-tree edits have an explicit local verification step, not only one inside the fetched playbook.

DimensionReasoningScore

Conciseness

The body is lean, assumes Claude's competence, and avoids explaining React/library concepts, but the core `npx react-doctor@latest --verbose --scope changed` command and its flag table are restated across the 'After making React code changes' and 'Command' sections, leaving minor trim opportunities.

4 / 5

Actionability

Fully executable, copy-paste-ready commands throughout (`npx react-doctor@latest --verbose --scope changed`, the `curl` playbook fetch) plus a complete flag/purpose table covering the common scan variants.

5 / 5

Workflow Clarity

The regression workflow has an explicit checkpoint ('check the score did not regress... fix the regressions before committing') and the /doctor workflow names a scan→filter→triage→fix→validate loop, but the detailed validation steps are delegated to the fetched playbook rather than spelled out inline, leaving a minor checkpoint gap.

4 / 5

Progressive Disclosure

Well-organized sections with a clearly signaled one-level-deep local reference (`references/explain.md`, verified present) and a remote playbook fetched on demand; sits just below a 5 because the remote-fetch pattern adds a layer of indirection beyond a clean local reference tree.

4 / 5

Total

17

/

20

Passed

Description

87%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, third-person description that clearly states both capabilities and trigger conditions with a distinctive React-scoped niche. The only weak spot is specificity, where coverage is expressed more as domains than as an exhaustive list of concrete actions.

DimensionReasoningScore

Specificity

Names the React-diagnostics domain plus several concrete coverage areas ('lint, accessibility, bundle size, architecture') and two concrete workflows ('regression check', 'full local-triage workflow'), but the items lean toward covered-domains rather than a comprehensive list of discrete actions, so it falls just short of a 5.

4 / 5

Completeness

Explicitly answers 'what' ('Covers lint, accessibility, bundle size, architecture. Includes a regression check and a full local-triage workflow') and 'when' ('Use when finishing a feature, fixing a bug, before committing React code, or when the user types /doctor...') with concrete trigger phrases.

5 / 5

Trigger Term Quality

Strong natural triggers ('finishing a feature, fixing a bug, before committing React code', 'scan, triage, or clean up') plus the explicit `/doctor` command, but it stops short of the full synonym/extension breadth of a 5.

4 / 5

Distinctiveness Conflict Risk

Scoped tightly to React diagnostics with a distinctive `/doctor` trigger and 'react-doctor' framing, giving it a clear niche with minimal overlap risk against other skills.

5 / 5

Total

18

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
millionco/react-doctor
Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.