CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

75

Quality

94%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

93%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.

A tight, well-organized navigation skill with concrete file references and a useful boundary-crossing table. The only soft spot is workflow_clarity, which lacks explicit in-flow validation/feedback checkpoints.

Suggestions

Add an explicit verification checkpoint inside the workflow (e.g., after crossing each boundary, confirm the matching Zod schema or replay consumer before proceeding) to turn the implicit 'Avoid' checks into in-flow validation steps.

Consider a short 'Verify' step that re-traces the reverse path to confirm producer and consumer actually connect, giving the workflow a feedback loop for error recovery.

DimensionReasoningScore

Conciseness

Lean body with no padding and no explanation of concepts Claude already knows; every line (workflow, boundary table, gotchas, output, avoid) earns its place, matching the 'lean and efficient; every token earns its place' anchor.

5 / 5

Actionability

For an instruction-only navigation skill it gives concrete file paths to inspect and a specific gotcha ('attachSession must be awaited before respond() — JSON.stringify(Promise) silently becomes {}'); per scoring notes, absence of code is not penalized when guidance is this actionable, fitting the fully-actionable anchor.

5 / 5

Workflow Clarity

A clear 5-step sequence with an 'Avoid' checklist and a step-5 test-check checkpoint, but it lacks explicit validation/feedback loops within the flow, so it sits at 'clear sequence with most checkpoints; minor gaps' rather than the full-checklist 5.

4 / 5

Progressive Disclosure

Under 50 lines, single-purpose, no external references needed, and well-organized into clear sections (Workflow, Contract Boundaries table, Stave-Specific Guidance, Output, Avoid), which the rubric explicitly allows to score 5 for simple skills.

5 / 5

Total

19

/

20

Passed

Description

95%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.

A strong, niche-scoped description that answers both what and when with concrete, bilingual trigger phrases. The only minor gap is that the capability is essentially a single tracing action rather than multiple distinct actions.

DimensionReasoningScore

Specificity

Names the domain ('Trace a behavior, event, or request path through the Stave codebase') and the concrete producer -> bridge -> consumer chain structure, but it is essentially one core action described with rich detail rather than a list of several distinct actions, fitting the 'several specific actions; minor gaps' anchor better than the comprehensive 5.

4 / 5

Completeness

Explicitly states what the skill does and follows with an explicit 'Use when the request asks ...' clause listing concrete trigger phrases, matching the anchor that requires both what and when with concrete triggers.

5 / 5

Trigger Term Quality

Includes natural user phrases across two languages ('where does this happen', 'execution path', 'call flow', '흐름 추적', '어디서 처리돼') with synonyms, matching the comprehensive-coverage-with-synonyms anchor.

5 / 5

Distinctiveness Conflict Risk

Scoped to the Stave codebase with a niche producer -> bridge -> consumer framing and distinct bilingual triggers, giving minimal conflict risk with other skills.

5 / 5

Total

19

/

20

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.