run-parity

Compare React Doctor diagnostics for a GitHub pull request (PR) with Daytona. Use when asked to run parity, check a PR for diagnostic regressions, compare a PR with its base, or report added and removed diagnostics.

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

85%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.

An operationally rigorous runbook with excellent actionability and validation-gated workflow clarity. Its main weakness is progressive disclosure: most detail is inlined into SKILL.md rather than split across the existing scripts bundle with clear navigation pointers.

Suggestions

Move the matrix-treatment descriptor JSON shape and paired-sandbox semantics into a references/ file, keeping only a concise example and a 'See X' pointer in SKILL.md to reduce inline bulk.

Tighten the explanatory prose around CPU/memory envelopes and retry concurrency tiers to the essential constraints, trimming rationale that does not change the commanded actions.

Add a short top-of-file overview listing the major phases and which scripts/ references back each phase, so the inlined runbook reads as a navigated overview rather than a wall of detail.

Dimension	Reasoning	Score
Conciseness	The body is dense and assumes Claude's competence without padding, but several prose passages (CPU/memory envelopes, retry concurrency tiers, paired-sandbox rationale) could be tightened.	4 / 5
Actionability	It provides fully executable, copy-paste-ready shell commands with real flags, concrete script paths, exact JSON shapes, and explicit exit-code meanings covering the common cases.	5 / 5
Workflow Clarity	A clear prepare-run-cache-compare-report sequence is given with explicit validation checkpoints (jq stream-validation, exit-zero + 100% completion, provenance verify) and feedback loops for the batch/destructive operations.	5 / 5
Progressive Disclosure	Section headers exist and inline script references all resolve to real bundle files, but the SKILL.md is a 350-line monolithic runbook with dense detail (matrix descriptor JSON, paired-sandbox semantics) inlined rather than split into clearly signaled reference files.	3 / 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.

A strong, third-person description that clearly states both the capability and explicit use-when triggers with concrete, natural phrasing. Minor room to add a few more natural synonyms for the niche domain.

Dimension	Reasoning	Score
Specificity	The description lists multiple concrete actions — compare diagnostics, check a PR for diagnostic regressions, compare a PR with its base, report added and removed diagnostics — giving comprehensive coverage of the parity workflow.	5 / 5
Completeness	It explicitly answers both what ('Compare React Doctor diagnostics for a GitHub pull request (PR) with Daytona') and when ('Use when asked to run parity...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Natural trigger phrases are present ('run parity', 'check a PR for diagnostic regressions', 'compare a PR with its base', 'report added and removed diagnostics'), but a few natural synonyms or variations are missing for this niche domain.	4 / 5
Distinctiveness Conflict Risk	The narrow niche of React Doctor PR parity with Daytona has distinct triggers and minimal overlap 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/run-parity/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.