rule-writing

Implement React Doctor rules from a validated contract. Use when writing oxlint rules, planning syntax or control-flow detection, designing adversarial tests, reusing syntax tree utilities, or updating rule registration.

Quality

87%

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

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.

The body is a lean, well-structured workflow with executable commands and explicit validation gates, assuming Claude's competence throughout. Its weakest aspect is that the core detector implementation stays directive and the error-recovery feedback loop and external references are signaled implicitly rather than crisply.

Suggestions

Add an explicit validate→fix→re-run feedback loop (e.g., 'If `nr test` or `nr typecheck` fails, fix the issue and re-run until green before handing off') to lift workflow_clarity to the top anchor.

Provide one small copy-paste rule skeleton or test fixture snippet to cover the common detector case and close the actionability gap.

Promote the external pointers into a short reference list (e.g., a 'References' section listing `docs/HOW_TO_WRITE_A_RULE.md` and the `rule-research`/`rule-validate` companion skills) so navigation is well-signaled.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence — it never explains what oxlint, React Doctor, or syntax trees are, and every line is directive guidance or an executable command that earns its place.	5 / 5
Actionability	It provides two copy-paste-ready command blocks (the truffler reuse search and the `nr test/lint/typecheck/format/smoke` checks), but the central detector-implementation steps are directive rather than executable code, leaving minor gaps versus the top anchor.	4 / 5
Workflow Clarity	There is a clear numbered sequence (Plan → Implement and test → Run repository checks → Report) with explicit validation steps (focused tests, package checks, `rde-eval`, `rule-validate` handoff), but the validate→fix→re-run error-recovery loop is implied rather than spelled out as crisply as the 5-anchor example.	4 / 5
Progressive Disclosure	The content is well-organized into clean sections and points to external material (`docs/HOW_TO_WRITE_A_RULE.md`, companion `rule-research`/`rule-validate` skills), but the references are inline mentions rather than a structured, well-signaled reference map, leaving minor organization gaps.	4 / 5
	Total	17 / 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.

This is a strong, specific description that clearly states what the skill does and when to use it, with concrete enumerated triggers and a well-scoped niche. The only mild gap is trigger-term breadth, where more synonyms or natural variations would push it to the top anchor.

Dimension	Reasoning	Score
Specificity	The description enumerates multiple concrete actions — 'writing oxlint rules, planning syntax or control-flow detection, designing adversarial tests, reusing syntax tree utilities, or updating rule registration' — giving comprehensive coverage of the rule-writing workflow rather than vague abstraction.	5 / 5
Completeness	It explicitly answers both 'what' ('Implement React Doctor rules from a validated contract') and 'when' ('Use when writing oxlint rules, planning...') with concrete enumerated trigger phrases, matching the 5-anchor structure.	5 / 5
Trigger Term Quality	Natural domain triggers like 'writing oxlint rules', 'adversarial tests', and 'rule registration' would be said by a user in this codebase, but the list is fairly jargon-heavy and lacks synonyms or file-extension variants, so it falls short of comprehensive 5-level coverage.	4 / 5
Distinctiveness Conflict Risk	The niche is highly specific — 'React Doctor rules', 'oxlint rules', 'rule registration' within a particular plugin — yielding distinct triggers and minimal conflict risk with other skills.	5 / 5
	Total	19 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: millionco/react-doctor
Path: .agents/skills/rule-writing/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.