CtrlK
BlogDocsLog inGet started
Tessl Logo

improve-react

Survey a whole React codebase as a senior React engineer, using React Doctor's scan as evidence, then produce a prioritized audit and self-contained implementation plans for other agents (or cheaper models) to execute. Read-only on source code — it plans improvements, it does not apply them. Use when the user asks to "improve the React code", "audit this codebase", "make this app faster / more robust", or wants a roadmap of fixes rather than a review of a single diff. For a regression check or a fix-it-now pass, use the `react-doctor` skill instead.

77

Quality

98%

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

SKILL.md
Quality
Evals
Security

Quality

Content

96%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 well-structured, actionable read-only audit skill with a clear phased workflow and concrete commands throughout. The only real weakness is that two core referenced files (AUDIT.md, PLAN-TEMPLATE.md) are not present in the bundle.

Suggestions

Ship the referenced AUDIT.md and PLAN-TEMPLATE.md alongside SKILL.md — the audit categories and plan template are described as living in those files but they are absent from the bundle.

Consider inlining the five audit category names (currently only listed in AUDIT.md) directly in SKILL.md so the recon/audit phase is followable even if the referenced file is not loaded.

Add a one-line note near the first reference stating these files must exist in the skill directory, so a missing bundle is detected early rather than mid-audit.

DimensionReasoningScore

Conciseness

Lean and dense throughout; assumes React competence, never explains basics, and every section earns its tokens — the prose sets operating posture rather than padding.

5 / 5

Actionability

Provides copy-paste-ready commands (`npx react-doctor@latest --json --json-out …`, `git rev-parse --short HEAD`, `npx react-doctor@latest --scope changed`), concrete table formats, and the exact canonical-fix URL pattern to fetch and inline.

5 / 5

Workflow Clarity

A clear four-phase sequence with explicit checkpoints — Phase 3 re-reads and rejects unconfirmed findings, Phase 4 requires mechanical + behavioral verification, and a stop-and-wait confirmation gate before planning.

5 / 5

Progressive Disclosure

Good one-level-deep structure with clearly signaled references to AUDIT.md and PLAN-TEMPLATE.md, but neither referenced file is present in the bundle, so navigation leads to missing material — an organization gap beyond minor.

4 / 5

Total

19

/

20

Passed

Description

100%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 names concrete actions, gives natural trigger phrases for both what and when, and clearly distinguishes itself from the related react-doctor skill. No notable gaps.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'Survey a whole React codebase', 'produce a prioritized audit and self-contained implementation plans', 'Read-only on source code — it plans improvements, it does not apply them' — with comprehensive coverage.

5 / 5

Completeness

Explicitly answers both what (survey, audit, produce prioritized plans) and when ('Use when the user asks to…') with concrete trigger phrases, plus a redirect for the adjacent regression case.

5 / 5

Trigger Term Quality

Includes natural phrases users would actually say — 'improve the React code', 'audit this codebase', 'make this app faster / more robust', 'roadmap of fixes' — covering several synonyms and intents.

5 / 5

Distinctiveness Conflict Risk

Carves a clear niche (read-only audit-then-plan) and explicitly contrasts it with the `react-doctor` skill's fix-it-now flow, minimizing wrong-skill triggering.

5 / 5

Total

20

/

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

relative_links

Relative link issues: 4 missing

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.