CtrlK
BlogDocsLog inGet started
Tessl Logo

the-ipc-contract-audit

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

Quality

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Quality

Content

100%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A tightly written, highly actionable audit checklist with concrete file paths, named functions, an explicit verification command, and clear checklists throughout. The sole minor weakness is the absence of an explicit validate-fix-retry feedback loop in the Verification section, though all validation checkpoints are explicit.

DimensionReasoningScore

Conciseness

The body is lean file-path lists and targeted pitfalls with no generic concept explanations; domain-specific notes like "JSON.stringify(Promise) === '{}'" and "silently drop unknown event variants at parseNormalizedEvent" earn their tokens, matching anchor 3.

3 / 3

Actionability

It gives concrete file paths, named functions ("parseNormalizedEvent", "respond()"), and an executable command ("bun run typecheck"); per the scoring note, an instruction-only skill need not be penalized for absent code when guidance is this concrete, matching anchor 3.

3 / 3

Workflow Clarity

It provides a clearly sequenced "Required Chain", an "Event Sync Checks" checklist, and explicit "Verification" steps, plus "Common Failure Modes" diagnostics; checkpoints are explicit rather than implicit, satisfying anchor 3 despite no formal validate-fix-retry loop.

3 / 3

Progressive Disclosure

No bundle files exist and the skill is a self-contained, well-sectioned single-purpose audit checklist; its only cross-references ("See the-provider-runtime-symmetry", "Invoke the-provider-runtime-symmetry") are one-level-deep and well-signaled, matching anchor 3.

3 / 3

Total

12

/

12

Passed

Description

90%

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 strong, specific, third-person description that clearly states what it does and when to use it, with natural (and multilingual) trigger terms and low conflict risk. Its only gap is that it names a single audit action rather than enumerating multiple distinct concrete operations.

Suggestions

Consider listing the distinct audit actions the skill performs (e.g., "trace the IPC chain, sync Zod schemas to TypeScript, verify async host-service dispatch, check CLI env parity") so specificity reads as multiple concrete operations rather than one verb.

DimensionReasoningScore

Specificity

The description gives one action ("Audit Stave multi-file contracts before or during changes") applied to a named domain; the enumerated items ("provider runtime options, IPC payloads, window.api, schemas, NormalizedProviderEvent, replay payloads") are trigger contexts rather than multiple distinct concrete actions, so it lands at anchor 2 rather than 3.

2 / 3

Completeness

It answers both "what" ("Audit Stave multi-file contracts before or during changes") and "when" ("Use when a task touches…"; "Trigger on phrases like…") with explicit triggers and third-person voice, matching anchor 3.

3 / 3

Trigger Term Quality

It explicitly lists natural terms users would say ("ipc", "schema", "runtimeOptions", "window.api", "provider event") plus multilingual triggers ("계약", "스키마", "동기화 체크"), giving good coverage of common variations as required by anchor 3.

3 / 3

Distinctiveness Conflict Risk

The niche is tightly scoped to "Stave multi-file contracts" with distinctive triggers like "NormalizedProviderEvent" and "window.api", making it unlikely to fire for the wrong skill per anchor 3.

3 / 3

Total

11

/

12

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
sendbird/stave
Reviewed

Table of Contents

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.