the-trace-execution-path

Trace a behavior, event, or request path through the Stave codebase. Use when the request asks "where does this happen", "execution path", "call flow", "흐름 추적", "어디서 처리돼", or needs the exact producer -> bridge -> consumer chain.

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

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 tight, well-structured navigation skill that assumes Claude's competence, gives specific file/function anchors for each contract boundary, and sequences the trace with a verification step and an error-avoidance checklist. No bundle files exist, and none are needed at this length.

Dimension	Reasoning	Score
Conciseness	Lean and information-dense — the contract-boundary table and Stave-specific tips assume Claude knows Electron/IPC/Zod concepts, with no padding or restated basics.	3 / 3
Actionability	Provides concrete, executable navigation guidance: exact file paths per boundary, named functions (parseNormalizedEvent, attachSession), and a specific gotcha (await before respond() or JSON.stringify(Promise) becomes {}).	3 / 3
Workflow Clarity	Five clearly sequenced steps with a verification checkpoint (step 5: check matching tests) and an Avoid checklist of pitfalls; no destructive/batch loop is required for a trace task.	3 / 3
Progressive Disclosure	Under 50 lines with well-organized sections (Workflow, boundaries table, guidance, Output, Avoid) and no need for external bundle references; the one inline doc pointer is a single-level repo reference.	3 / 3
	Total	12 / 12 Passed

Description

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.

A concise, third-person description that clearly states what the skill does and when to use it, with concrete bilingual trigger terms and a well-scoped niche. It hits every anchor at the top of the scale.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions — "Trace a behavior, event, or request path through the Stave codebase" and "the exact producer -> bridge -> consumer chain" — rather than vague language.	3 / 3
Completeness	Explicitly answers both what (trace a path through the Stave codebase) and when ("Use when the request asks ...") with an explicit trigger clause.	3 / 3
Trigger Term Quality	Includes natural phrases users would actually say ("where does this happen", "execution path", "call flow") plus bilingual Korean triggers ("흐름 추적", "어디서 처리돼"), giving strong coverage.	3 / 3
Distinctiveness Conflict Risk	Scoped to the Stave codebase with a distinct producer->bridge->consumer niche and specific trigger phrases, making conflict with unrelated skills unlikely.	3 / 3
	Total	12 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: sendbird/stave
Commit: 8e1e80c

Reviewed: 2 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.