vercel-flags

Vercel Flags guidance — feature flags platform with unified dashboard, Flags Explorer, gradual rollouts, A/B testing, and provider adapters. Use when implementing feature flags, experimentation, or staged rollouts.

Quality

85%

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

82%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 tightly written, highly actionable reference with executable code across the main scenarios and clear navigation. Its weaknesses are minor: time-sensitive version/beta facts are inlined rather than segregated into a dated section, and all API reference material lives inline with no separate reference files to offload it.

Suggestions

Move the 'public beta (February 2026)' and per-version notes (v4.0.3, v1.0.1, v4.0+) into a dedicated 'Version & lifecycle' or 'Deprecated/old patterns' section so time-sensitive facts are isolated and easy to prune.

Split the larger API surface (custom adapter interface, precompute pattern, full provider-adapter list) into reference files under references/ and link to them one level deep, reducing inline bulk.

Add a brief ordered workflow (e.g. install → define flags → add discovery endpoint → verify Flags Explorer loads) with an explicit verification checkpoint to raise workflow clarity.

Dimension	Reasoning	Score
Conciseness	Dense, accurate reference that mostly assumes Claude's competence and earns its tokens, but several time-sensitive facts (the 'public beta (February 2026)' line and scattered version pins like 'v4.0.3', 'v1.0.1', 'v4.0+') are inlined rather than isolated in a dated/deprecated section, which the guideline says should penalize conciseness.	4 / 5
Actionability	Multiple complete, executable code blocks covering the common cases — boolean/variant flag definitions, vercelAdapter setup, App- and Pages-Router discovery endpoints, the next.config rewrite, and the custom adapter interface — making it copy-paste ready.	5 / 5
Workflow Clarity	Sections are well sequenced and the 'Drafts Workflow' and v4-upgrade steps are ordered, but there are no explicit validation checkpoints; this is acceptable for a reference skill with no destructive/batch operations, just short of the anchor-5 feedback-loop bar.	4 / 5
Progressive Disclosure	A single well-organized SKILL.md with clear section headers (What It Is, Key APIs, When to Use / Not to Use, References) and one-level-deep external doc links; no bundle files exist, so navigation is easy but bulk API reference is inlined rather than split into separate files.	4 / 5
	Total	17 / 20 Passed

Description

87%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 strong: it clearly states both what the skill covers and when to use it, with natural trigger terms and a distinct, named niche. The only soft spots are that the enumerated capabilities are platform features rather than crisp action verbs, and a few common synonyms (e.g. 'feature toggles', 'canary') are missing.

Dimension	Reasoning	Score
Specificity	Enumerates several concrete capabilities — 'unified dashboard, Flags Explorer, gradual rollouts, A/B testing, and provider adapters' — rather than vague language, but these read as platform features rather than the crisp action verbs the anchor-5 example uses, leaving minor coverage gaps.	4 / 5
Completeness	Explicitly states what ('Vercel Flags guidance — feature flags platform with...') and when ('Use when implementing feature flags, experimentation, or staged rollouts') with concrete trigger phrases, matching the anchor-5 pattern.	5 / 5
Trigger Term Quality	Includes natural terms a user would say — 'feature flags', 'experimentation', 'A/B testing', 'gradual rollouts', 'staged rollouts' — with synonyms, but omits common variations like 'feature toggles', 'kill switches', or 'canary releases', so coverage is good rather than comprehensive.	4 / 5
Distinctiveness Conflict Risk	Names a specific platform ('Vercel Flags') with a clear niche (feature flags / experimentation / staged rollouts) and distinct triggers, giving minimal conflict risk with other skills.	5 / 5
	Total	18 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning

	Total	14 / 16 Passed

Repository: openai/plugins
Path: plugins/vercel/skills/vercel-flags/SKILL.md
Commit: 1e28582

Reviewed: 6 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.