Conciseness

The body is almost entirely operational — copy-paste curl/python commands, checklists, and tables with no tutorials on concepts Claude already knows. It is not a 5 because there is repeated material that could be trimmed: the PyPI install warnings appear in sections 6, 10, 11, and again in the tools table, and the report template with example titles runs long. This matches 'efficient; minor instances of over-explanation that could be trimmed'.

Actionability

Nearly every section gives fully executable, copy-paste-ready commands (curl probes, python3 one-liners for alias/depth bombs, exact clairvoyance/graphql-cop/wscat invocations) with concrete expected outputs and severity/CVSS guidance. Placeholders like VICTIM_TOKEN are clearly task-inherent, matching the top anchor for copy-paste ready commands covering the common cases.

Workflow Clarity

The 'Quick Kill Checklist' opens with a sequenced plan, sections follow the natural audit order, decision branches exist ('If introspection off — run clairvoyance', 'When __schema is blocked, try:'), and 'KILL SIGNALS' plus the report template's 'confirm impact' step provide checkpoints. It falls short of a 5 because there is no explicit validate-findings-then-retry loop (e.g., verifying a suspected IDOR/DoS result before escalating), matching 'clear sequence with most checkpoints present; minor validation gaps'.

Progressive Disclosure

There is good section structure (14 numbered, clearly headed sections plus a tools table), but the skill is a ~520-line single file with no references/ bundle at all — everything is inline. Content that clearly belongs in separate files is inlined, notably the full introspection query, the chaining/report templates, and the per-tool install details; this matches 'some structure but could be better organized; content that should be separate is inline'.

Specificity

The description enumerates many concrete capability areas — 'introspection abuse, field suggestion enumeration (clairvoyance), batching DoS, IDOR via aliasing, auth bypass, injection via arguments, subscription abuse, depth/complexity bombs, and WAF bypass' — plus specific tool coverage ('graphw00f fingerprinting, GraphQLmap, graphql-cop, and inql'). This matches the anchor for multiple specific concrete actions with comprehensive coverage; it is well above the 'several specific actions; minor gaps' anchor.

Completeness

Both questions are answered explicitly: the 'what' is the enumerated attack list with tools, and the 'when' is a literal trigger clause — 'Use when a target exposes a /graphql, /api/graphql, or GQL-over-HTTP endpoint.' This clearly matches the top anchor for explicit what and when with concrete trigger phrases, and exceeds the anchor where 'when' could be more specific.

Trigger Term Quality

Natural trigger terms are comprehensively covered for this niche: 'GraphQL', 'GQL', '/graphql', '/api/graphql', and 'GQL-over-HTTP' — synonyms plus the endpoint-path equivalents of file extensions, paralleling the top anchor. A user needing this skill would naturally mention a GraphQL endpoint; nothing significant is missing.

Distinctiveness Conflict Risk

It carves out a clear niche (GraphQL security testing) with distinct triggers tied to GraphQL endpoint exposure, so it would not fire for general web-app, API, or PDF-type skills. Minimal conflict risk, matching the 'clear niche with distinct triggers' anchor.