verify

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

2.57x

Quality

74%

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

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.

The body is exemplary: a tight, fully executable verification workflow with explicit sequencing, parallelization guidance, per-step failure checkpoints, and defined success/failure outcomes. Nothing is padded and nothing is missing for a skill of this scope.

Dimension	Reasoning	Score
Conciseness	Lean and efficient: no concept explanations, no padding — every line is an instruction or an argument definition. Matches the anchor 'every token earns its place'.	5 / 5
Actionability	Fully executable, copy-paste-ready commands throughout: `yarn prettier`, `yarn linc`, `/flow`, `/test`, `/test www`, plus explicit $ARGUMENTS plumbing into the test step. Not below 5 because no key execution detail is missing.	5 / 5
Workflow Clarity	The sequence is explicit — two sequential steps first, then three parallel subagent checks — every step carries a 'stop if fails' checkpoint, and both the success path ('show success summary') and failure path ('stop immediately and report the issue with suggested fixes') are defined. Not 4 because validation checkpoints are present at every step, not just most.	5 / 5
Progressive Disclosure	A simple skill under 50 lines with a single task and no need for external references; sections (title, arguments, instructions) are well organized. Per the simple-skill scoring note, this scores 5 without external file references.	5 / 5
	Total	20 / 20 Passed

Description

48%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 leads with an explicit 'Use when...' trigger but omits nearly all of the 'what' — the concrete verification steps (prettier, lint, type check, tests) that make up the skill's substance are invisible to a reader deciding whether to invoke it. It is also written in second person rather than the required third person, which lowers specificity.

Suggestions

State the 'what' concretely in third person, e.g. 'Runs prettier formatting, lints changed files, type checks, and runs source and www tests' before the 'Use when...' clause.

Add natural trigger synonyms users would say — 'verify changes', 'check my changes', 'before committing or opening a PR', 'React contribution checklist' — to improve trigger-term coverage.

Rewrite in third person ('Validates changes...' instead of 'Use when you want...') to match the required description voice.

Dimension	Reasoning	Score
Specificity	The description names the domain ('React contribution requirements') but states no concrete actions — 'validate changes' and 'check all React contribution requirements' never mention the actual operations (formatting, linting, type checking, testing). Baseline 3 is reduced by 1 because it uses second-person voice ('you want', 'you need') instead of third person.	2 / 5
Completeness	It has a clear, explicit 'Use when...' clause, but the 'what' is only minimally present — 'validate changes' names no actual operation. This sits between anchor 2 ('when' present without a real 'what') and anchor 3 (clear 'what' with weak 'when'); not 4 because the 'what' is too vague to call both halves answered.	3 / 5
Trigger Term Quality	'validate changes', 'before committing', and 'React' are natural phrases a user might say, but common variations and synonyms ('verify', 'lint', 'test', 'pre-commit', 'CI checks') are missing. Not 4 because coverage is thin relative to the natural trigger vocabulary for this task.	3 / 5
Distinctiveness Conflict Risk	'React contribution requirements' carves out a distinct niche within a React repo, but 'validate changes before committing' overlaps with generic verify/test/lint skills. Not 5 because the leading trigger is broad enough to compete with other validation skills.	4 / 5
	Total	12 / 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: 7c6ac13

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.