CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

63

Quality

75%

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

Fix and improve this skill with Tessl

tessl review fix ./config/claude/skills/react-doctor/SKILL.md

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

SKILL.md
Quality
Evals
Security

Quality

Content

86%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.

The body is an efficient, well-structured overview with an executable command and a clear run-fix-rerun feedback loop, weakened only by unexplained flags and a thin validation checkpoint.

Suggestions

Briefly note what --verbose and --diff do so the command is fully self-explanatory.

Make the verification step explicit, e.g. 'Re-run and confirm the score increased; stop when no errors remain'.

DimensionReasoningScore

Conciseness

The body is a lean overview with a one-line capability statement, a single executable command, and a two-line workflow; no padding or over-explanation of concepts Claude already knows.

5 / 5

Actionability

It gives a copy-paste ready command 'npx -y react-doctor@latest . --verbose --diff', but the --verbose/--diff flags are unexplained and there is no example of interpreting the output, leaving minor gaps.

4 / 5

Workflow Clarity

The workflow sequences run -> fix errors -> re-run to verify with an explicit feedback loop, but the steps are terse and lack an explicit validation checkpoint beyond 'verify the score improved'.

4 / 5

Progressive Disclosure

A simple under-50-line skill with no external references needed; it is organized into clear Usage and Workflow sections, which satisfies the simple-skill exception for a 5.

5 / 5

Total

18

/

20

Passed

Description

65%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.

The description cleanly pairs a what-and-when structure with natural trigger terms and a React-scoped niche, but its 'what' stays generic ('catch issues early') instead of naming the concrete diagnostics the tool performs.

Suggestions

Replace 'catch issues early' with the specific checks performed, e.g. 'Scans for security, performance, correctness, and architecture issues and outputs a 0-100 score'.

Add natural synonyms or file cues (e.g. 'React components', 'JSX/TSX files') to broaden trigger coverage toward a 5.

DimensionReasoningScore

Specificity

The phrase 'catch issues early' names the React domain but the action is minimal and generic; it never enumerates concrete checks (security, performance, correctness) the way the score-3 anchor expects.

2 / 5

Completeness

It states both a 'what' ('Run after making React changes to catch issues early') and an explicit 'when' clause; the 'what' is somewhat thin, which keeps it just below a 5.

4 / 5

Trigger Term Quality

'reviewing code, finishing a feature, or fixing bugs in a React project' supplies several natural trigger phrases a user would actually say, though synonyms and file extensions are absent.

4 / 5

Distinctiveness Conflict Risk

Tying triggers to 'a React project' gives it a clear niche with minor overlap risk against general code-review skills, but the broad 'reviewing code / fixing bugs' phrasing prevents a 5.

4 / 5

Total

14

/

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.

Validation15 / 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
freekmurze/dotfiles
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.