react-doctor
Run after making React changes to catch issues early. Use when reviewing code, finishing a feature, or fixing bugs in a React project.
59
68%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./config/claude/skills/react-doctor/SKILL.mdQuality
Discovery
49%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
The description provides clear 'when' guidance with multiple trigger scenarios, which is a strength. However, it fails to specify what the skill actually does — the concrete actions are entirely absent, replaced by the vague phrase 'catch issues early.' This lack of specificity also makes it highly prone to conflicts with other code quality or testing skills.
Suggestions
Add specific concrete actions the skill performs, e.g., 'Runs ESLint, TypeScript type-checking, and unit tests on React components to catch issues early.'
Include more distinctive trigger terms that differentiate this from generic code review skills, such as specific tool names (Jest, ESLint, tsc) or file types (.tsx, .jsx).
Narrow the scope to reduce conflict risk — specify whether this is about linting, testing, building, or a combination, so it won't overlap with other code quality skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description says 'catch issues early' and 'Run after making React changes' but never specifies what concrete actions the skill performs (e.g., run linting, run tests, type-check, build). The actions are vague — 'catch issues' is abstract. | 1 / 3 |
Completeness | It answers both 'what' (run after making React changes to catch issues early) and 'when' (when reviewing code, finishing a feature, or fixing bugs in a React project), with explicit trigger scenarios. | 3 / 3 |
Trigger Term Quality | Includes 'React', 'code', 'feature', 'bugs', and 'reviewing code' which are somewhat natural terms, but lacks specifics like 'lint', 'test', 'type check', 'build', 'CI', or file extensions that would help match user intent precisely. | 2 / 3 |
Distinctiveness Conflict Risk | Very generic — 'reviewing code', 'finishing a feature', and 'fixing bugs' could apply to almost any code quality, testing, or linting skill. Without specifying the mechanism (tests, linting, type-checking, etc.), this would easily conflict with other skills. | 1 / 3 |
Total | 7 / 12 Passed |
Implementation
87%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a concise, focused skill that provides a clear, actionable command for running react-doctor. Its main weakness is the workflow section, which could benefit from guidance on interpreting results (e.g., what score thresholds mean, how to prioritize error categories) and a more explicit fix-validate loop. Overall it's effective for its simple purpose but leaves some ambiguity about how to act on the output.
Suggestions
Add brief guidance on interpreting the 0-100 score (e.g., thresholds for pass/fail, which issue categories to prioritize)
Make the feedback loop more explicit: e.g., '1. Run react-doctor 2. Fix all errors (red) first 3. Re-run and confirm score improved 4. Then address warnings'
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Very lean — no unnecessary explanations. Every line serves a purpose. Doesn't explain what React is or how npx works. | 3 / 3 |
Actionability | Provides a single, copy-paste ready command with specific flags (--verbose --diff). For a tool-wrapping skill, this is fully executable guidance. | 3 / 3 |
Workflow Clarity | There's a basic workflow (run → fix errors → re-run to verify), but it lacks explicit validation checkpoints or guidance on interpreting the 0-100 score, what constitutes passing, or how to prioritize fixes (errors vs warnings). | 2 / 3 |
Progressive Disclosure | For a simple, single-purpose skill under 50 lines with no need for external references, the content is well-organized with clear sections (Usage, Workflow). No bundle files are needed. | 3 / 3 |
Total | 11 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- freekmurze/dotfiles
- Commit
3974caa
- 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.