Audit Stave multi-file contracts before or during changes. Use when a task touches provider runtime options, IPC payloads, window.api, schemas, NormalizedProviderEvent, replay payloads, or asks for a contract or sync checklist. Trigger on phrases like "ipc", "schema", "runtimeOptions", "window.api", "provider event", "계약", "스키마", "동기화 체크".
76
96%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is an excellent skill description that clearly defines its scope (auditing Stave multi-file contracts), provides explicit trigger conditions with both English and Korean keywords, and occupies a highly distinctive niche. The description is concise yet comprehensive, covering what the skill does, when to use it, and specific phrases that should activate it.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions and artifacts: provider runtime options, IPC payloads, window.api, schemas, NormalizedProviderEvent, replay payloads, contract/sync checklists. These are highly specific technical capabilities. | 3 / 3 |
Completeness | Clearly answers both 'what' (audit Stave multi-file contracts) and 'when' (explicit 'Use when' clause listing specific scenarios, plus a 'Trigger on phrases' clause with concrete keywords). Both dimensions are thoroughly addressed. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms including both English and Korean variations: 'ipc', 'schema', 'runtimeOptions', 'window.api', 'provider event', '계약', '스키마', '동기화 체크'. These are terms users would naturally use when working in this domain. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive — targets a very specific application ('Stave') with domain-specific concepts like NormalizedProviderEvent, IPC payloads, and window.api. The combination of these terms creates a clear niche that is unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
92%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a high-quality, project-specific contract audit skill that provides precise, actionable guidance for a complex multi-file synchronization problem. Its greatest strengths are the concrete file paths, specific failure modes with explanations of why they fail silently, and clear verification steps. The only minor weakness is that the content is somewhat long for a single file and could benefit from splitting detailed file listings into a reference document.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Every section delivers project-specific, non-obvious information. No generic explanations of IPC, Zod, or TypeScript concepts. The content is dense with actionable, domain-specific knowledge that Claude wouldn't know without this skill. | 3 / 3 |
Actionability | Provides exact file paths, specific function names (parseNormalizedEvent, respond()), concrete failure modes (JSON.stringify(Promise) === '{}'), specific commands (bun run typecheck), and a clear output format. Every instruction is precise and directly executable. | 3 / 3 |
Workflow Clarity | The 'Required Chain' establishes a clear inspection sequence, 'Event Sync Checks' provides an ordered checklist with explicit validation steps, and the 'Verification' section includes concrete validation checkpoints including smoke-checks for both adapter paths. The 'Common Failure Modes' section serves as an error-recovery reference. | 3 / 3 |
Progressive Disclosure | The content is well-organized into logical sections and references another skill ('the-provider-runtime-symmetry') for deeper detail. However, with no bundle files provided, the cross-reference cannot be verified, and the skill is moderately long — some sections like the full file listings for Provider CLI Environment Parity could potentially be split into a reference file. | 2 / 3 |
Total | 11 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
e275ad5
Table of Contents
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.