fuzz

Fuzz React Doctor rules for crashes, slowness, false positives, and mutation-sensitive diagnostics with @react-doctor/fuzz. Use after rule tests pass, when investigating a fuzz finding, or whenever an eval, review, or user report confirms a new false positive.

Quality

94%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

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 dense, highly actionable single-file skill with executable commands, explicit triage and validation feedback loops, and a well-signaled external README reference. The only soft spot is progressive disclosure, where some inlined reference material could live in separate files.

Suggestions

Move the canonical-corpus setup detail (sync-fuzz-corpus.ts / build-bench-corpus.ts walkthrough) and the stable weakness-name enumeration into a short referenced file or appendix so the main body stays a lean overview.

Dimension	Reasoning	Score
Conciseness	Lean throughout with no explanation of concepts Claude already knows; every line is actionable command, triage, or procedure, e.g. 'Use `packages/fuzz` after focused rule tests pass. Read its `README.md` for harness architecture and corpus setup.'	5 / 5
Actionability	Copy-paste-ready commands throughout ('FUZZ_RULE=<rule-id> FUZZ_STRICT=1 FUZZ_ITERATIONS=500 nr fuzz', 'bun scripts/hunt-false-positives.ts') plus a numbered preserve-FP procedure with exact fixture paths, covering the common cases.	5 / 5
Workflow Clarity	Clear sequence (run harness → confirm rule fires → triage → preserve → report) with explicit validation/feedback loops: 'Confirm that the target rule fires... If it stays silent, add a triggering shape... and rerun' and 'Run `nr -C packages/fuzz test` and replay the target rule.'	5 / 5
Progressive Disclosure	Well-organized sections with a clearly signaled one-level-deep reference ('Read its `README.md` for harness architecture and corpus setup'), but the canonical-corpus paragraph and the full weakness-name list are inlined rather than split out, leaving minor organization gaps.	4 / 5
	Total	19 / 20 Passed

Description

92%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 states concrete capabilities and gives explicit, multi-condition 'Use when' triggers. It is highly specific and low-conflict; the only minor gap is trigger-term synonym breadth.

Suggestions

Broaden trigger terms with a few natural synonyms or shorthand users might say (e.g. 'fuzzing', 'mutation testing', 'flaky/noisy rules') to push trigger_term_quality to comprehensive.

Dimension	Reasoning	Score
Specificity	Names the tool (@react-doctor/fuzz), the target (React Doctor rules), and four concrete weakness classes ('crashes, slowness, false positives, and mutation-sensitive diagnostics'), matching the comprehensive-coverage anchor.	5 / 5
Completeness	Explicitly answers both 'what' (fuzz rules for four named weakness classes) and 'when' ('Use after rule tests pass, when investigating a fuzz finding, or whenever an eval, review, or user report confirms a new false positive') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Strong natural keywords ('fuzz finding', 'false positive', 'rule tests pass', 'eval, review, or user report') that users would actually say, but coverage is specialized and a few common synonyms are absent, so it sits just below the comprehensive anchor.	4 / 5
Distinctiveness Conflict Risk	A clear niche (fuzzing React Doctor rules via @react-doctor/fuzz) with distinct triggers and minimal overlap risk with other skills.	5 / 5
	Total	19 / 20 Passed

Validation

93%

Warnings & errors only

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

Criteria	Description	Result
referenced_paths_exist	Referenced path issues: 4 missing	Warning

	Total	15 / 16 Passed

Repository: millionco/react-doctor
Path: .agents/skills/fuzz/SKILL.md
Commit: 83466a8

Reviewed: 5 days ago

Table of Contents

Discovery Implementation Validation

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.