verify

Use when you want to validate changes before committing, or when you need to check all React contribution requirements.

2.57x

Quality

56%

Does it follow best practices?

Impact

98%

2.57x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/verify/SKILL.md

Quality

Content

75%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 tight, actionable verification workflow with concrete commands, clear sequencing, and explicit pass/fail checkpoints. It efficiently assumes Claude's competence and avoids concept re-explanation.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence — it lists exact commands and stop conditions with no padding or explanation of concepts Claude already knows, sitting just below the 5 anchor only because a couple of phrases ("format code", "lint changed files") could be trimmed.	4 / 5
Actionability	Provides concrete, runnable commands (`yarn prettier`, `yarn linc`, `/flow`, `/test`, `/test www`) with clear stop-if-fails semantics, missing only full copy-paste coverage of subagent output handling, so it is mostly executable with minor gaps.	4 / 5
Workflow Clarity	A clear two-phase sequence (sequential then parallel subagents) with explicit "stop if fails" checkpoints and a final success/failure gate; the only gap is that failure recovery only says to report and suggest fixes rather than re-validate, keeping it just below 5.	4 / 5
Progressive Disclosure	Well-organized into Arguments and Instructions sections with a sensible quick-start ordering; as a single short file under 50 lines it needs no external references, so it is just below the 5 anchor only because section signaling could be slightly tighter.	4 / 5
	Total	16 / 20 Passed

Description

37%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.

The description is short and trigger-oriented but vague on concrete capabilities and missing an explicit 'what does this do' statement. It reads as a usage hint rather than a complete capability description.

Suggestions

Add a concrete 'what' clause naming the specific actions the skill performs (e.g., 'Runs prettier, lint, type-check, and tests') before the 'Use when' trigger.

Include natural user-facing keywords and synonyms such as 'lint', 'format', 'type-check', 'tests', 'CI checks', or 'contribution requirements'.

Tighten distinctiveness by leading with the React-specific contribution context so it cannot be confused with a generic git/lint skill.

Dimension	Reasoning	Score
Specificity	Names the domain ("validate changes before committing", "React contribution requirements") but the actions are minimal and generic — it says "validate" and "check" without naming concrete steps, so it sits just below the 3-anchor that expects 1-2 concrete actions.	2 / 5
Completeness	Has a clear "when" ("Use when you want to validate changes before committing") but no explicit "what does this do" — the action is only weakly implied by the trigger, which caps it at 3 per the missing/explicit guidance rule.	3 / 5
Trigger Term Quality	Only one or two generic phrases ("validate changes before committing", "check all React contribution requirements"); it lacks the natural terms and synonyms a user would actually say, falling between the 1 and 3 anchors, noticeably below midpoint.	2 / 5
Distinctiveness Conflict Risk	The React contribution-requirements framing gives it some specificity, but "validate changes before committing" is broad and could overlap with general lint/test or git skills, so it is somewhat specific but not clearly distinct.	3 / 5
	Total	10 / 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: facebook/react
Path: .claude/skills/verify/SKILL.md
Commit: eb8feb7

Reviewed: 3 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.