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.
68
83%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
89%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 a well-crafted skill description with excellent trigger terms (including multilingual support), a clear 'Use when' clause, and strong distinctiveness due to its specific codebase scope. The main weakness is that the 'what' portion could enumerate more specific concrete actions beyond the general concept of tracing paths. Overall, it would perform well in a multi-skill selection scenario.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | It names the domain (Stave codebase) and describes the general action (trace a behavior/event/request path), but doesn't list multiple specific concrete actions beyond tracing. It mentions 'producer -> bridge -> consumer chain' which adds some specificity, but overall it's one action described in slightly different ways. | 2 / 3 |
Completeness | Clearly answers both 'what' (trace a behavior/event/request path through the Stave codebase) and 'when' (explicit 'Use when' clause with specific trigger phrases and scenarios). The when clause is detailed with multiple trigger examples. | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms: 'where does this happen', 'execution path', 'call flow', and even Korean equivalents ('흐름 추적', '어디서 처리돼'). These are phrases users would naturally say when needing this skill, with good coverage of variations. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive due to being scoped to a specific codebase (Stave) and a specific task (tracing execution paths/call flows). The 'producer -> bridge -> consumer chain' terminology further narrows the niche. Unlikely to conflict with other skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured, codebase-specific tracing skill that efficiently maps Stave's contract boundaries and provides a clear workflow. Its main weakness is the lack of concrete executable examples—such as grep commands, code snippets for inspecting schemas, or a worked example of tracing a specific event end-to-end. The 'Avoid' section effectively serves as a validation checklist, compensating somewhat for the absence of explicit verification steps.
Suggestions
Add a concrete worked example tracing one specific event (e.g., a provider turn) through all boundary crossings, showing actual file contents or grep commands at each step.
Include executable search commands (e.g., `grep -r 'eventName' electron/main/ipc/`) to make the trace workflow more actionable and copy-paste ready.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Every section is lean and project-specific. No unnecessary explanations of what IPC is, what Zod does, or how Electron works. The boundary table is dense and informative. The Stave-specific guidance section adds only non-obvious gotchas (e.g., the Promise/JSON.stringify pitfall). | 3 / 3 |
Actionability | The workflow steps are clear and the boundary table provides specific file paths, which is highly useful. However, there are no concrete code snippets, grep commands, or executable examples showing how to actually perform a trace (e.g., searching for an event name, inspecting a Zod schema). The guidance is specific to the codebase but remains procedural rather than executable. | 2 / 3 |
Workflow Clarity | The 5-step workflow is clearly sequenced and covers both forward and backward tracing. Steps include crossing contract boundaries with explicit file references, confirming consumers, and checking tests. The 'Avoid' section acts as a validation checklist, warning against common incomplete traces (stopping before Zod schema, describing only one side). | 3 / 3 |
Progressive Disclosure | The skill references `docs/architecture/conversation-flow.md` for deeper context, which is good. However, with no bundle files provided and no other external references, the content is essentially self-contained. The boundary table could benefit from linking to more detailed per-boundary documentation if it existed. For the complexity of the topic, the single-file approach is borderline adequate. | 2 / 3 |
Total | 10 / 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 | |
- Repository
- sendbird/stave
- Commit
e275ad5
- 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.