flags

Use when you need to check feature flag states, compare channels, or debug why a feature behaves differently across release channels.

1.03x

Quality

80%

Does it follow best practices?

Impact

98%

1.03x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Quality

Content

86%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 tight, well-structured skill body that is token-efficient and well-organized. It sits just below top marks only because the 'explain the output' step leaves Claude without concrete guidance on what to surface.

Suggestions

Replace 'Explain the output to the user' with concrete guidance, e.g. list changed flags, call out enabled/disabled per channel, and flag any __VARIANT__ deltas.

Add a short sample of expected 'yarn flags' output so Claude can ground its explanation and recognize malformed runs.

Dimension	Reasoning	Score
Conciseness	Lean throughout with no padding or explanation of concepts Claude already knows; the Options table, Channels list, Legend, and Common Mistakes each earn their tokens.	5 / 5
Actionability	Provides the executable command 'yarn flags $ARGUMENTS' plus exact option flags, but step 2 ('Explain the output to the user') is vague and lacks guidance on what to surface.	4 / 5
Workflow Clarity	A clear 3-step sequence (run, explain, handle --diff) for a read-only skill with no validation requirement; minor gaps in how to interpret or highlight output keep it below 5.	4 / 5
Progressive Disclosure	Under 50 lines with no need for external references, organized into well-labeled sections (Options, Channels, Legend, Instructions, Common Mistakes) — the simple-skill exception applies.	5 / 5
	Total	18 / 20 Passed

Description

75%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 solid, trigger-forward description that names a clear niche and several concrete actions. It earns consistent 4s rather than 5s because coverage of capabilities and trigger synonyms is good but not exhaustive.

Suggestions

Lead with a standalone 'what' clause (e.g., 'Inspects and compares feature flag states across release channels.') before the 'Use when' trigger to separate capability from trigger.

Broaden trigger synonyms ('feature flags', 'flag rollout', 'experiment channels') so users phrasing the need differently still match.

Dimension	Reasoning	Score
Specificity	Lists three concrete actions ('check feature flag states, compare channels, or debug why a feature behaves differently'), but omits other capabilities (cleanup grouping, CSV output, variant handling) so it is not comprehensive.	4 / 5
Completeness	Has an explicit 'Use when...' trigger and concrete actions conveying the 'what', but the 'what' is fused into the 'when' clause rather than standing as its own capability statement.	4 / 5
Trigger Term Quality	Natural phrases like 'feature flag states', 'compare channels', and 'debug' are present and would be said by users, though some synonyms (e.g. 'feature flags', 'flag rollout', 'experiments') are missing.	4 / 5
Distinctiveness Conflict Risk	The feature-flag / release-channel niche is specific and unlikely to misfire, with only minor overlap risk against generic debugging skills.	4 / 5
	Total	16 / 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/flags/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.