rde-eval

Run a targeted local React Doctor Evals loop against an uncommitted rule change. Use after focused rule tests pass, while inspecting real open-source hits, or when rule-validate needs local false-positive evidence before pull request parity.

Quality

91%

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

100%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 tightly written, fully executable local-eval skill with a clear multi-step workflow, explicit feedback loops for the batch sampling operation, and clean section organization. It exemplifies concise, actionable, well-structured skill content.

Dimension	Reasoning	Score
Conciseness	Lean and efficient; assumes Claude's competence, explains no basic concepts (git, build, RDE), and every line earns its place. Re-reading anchors, this matches the 'lean and efficient' 5 better than the 'minor over-explanation' 4.	5 / 5
Actionability	Fully executable copy-paste-ready shell commands with concrete flags (--runner local, --take 100, --rule); placeholders like <rule-id> are clearly parameterized user inputs, not missing detail. Matches the 5 anchor covering common cases.	5 / 5
Workflow Clarity	Clear sequenced workflow (prepare -> run sample -> inspect hits -> report) with explicit feedback loops ('Increase --take only after tests and the first sample pass', 'Rebuild and rerun the same sample'); the batch operation has validation, so the cap does not apply.	5 / 5
Progressive Disclosure	Under 50 lines, single-purpose, no external references needed (confirmed no bundle files present), with well-organized section headers; the simple-skill exception permits a 5.	5 / 5
	Total	20 / 20 Passed

Description

83%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 specific, well-scoped description that clearly states both what it does and when to use it, with concrete trigger guidance. It is strong across the board but leaves slight room on keyword synonym coverage and sibling-skill distinctiveness.

Dimension	Reasoning	Score
Specificity	Names the domain ('React Doctor Evals loop against an uncommitted rule change') and several concrete actions/contexts ('inspect real open-source hits', 'local false-positive evidence', 'pull request parity'); minor coverage gaps keep it below a 5.	4 / 5
Completeness	Explicitly answers both 'what' (run a targeted local RDE loop) and 'when' ('Use after focused rule tests pass, while inspecting real open-source hits, or when rule-validate needs local false-positive evidence') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes natural domain phrases a user would say ('rule tests pass', 'open-source hits', 'false-positive evidence', 'pull request parity'); a few natural synonyms/variations are missing, so not a 5.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (local pre-PR RDE iteration on uncommitted rule changes) with distinct triggers; minor overlap with sibling rule-validate/run-parity skills prevents a 5.	4 / 5
	Total	17 / 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/rde-eval/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.