Loading...
Loading...
Inspect eval manifests and portable validators for trace-friendly skill signals. Use when debugging skill invocation gaps. NOT for live LLM trace capture.
npx skill4agent add wyattowalsh/agents skill-trace-debugger| $ARGUMENTS | Action |
|---|---|
| Trace readiness report for one skill |
| Fleet trace readiness summary |
| Machine-readable report |
| Empty | Show trace signal checklist |
| Signal | Meaning |
|---|---|
| Behavioral cases exist for post-hoc grading |
| Portable validator contract is wired |
| explicit-invocation case | Eval includes a slash-command or named dispatch prompt |
| NOT-for boundary | Description names the correct alternate skill |
uv run python skills/skill-trace-debugger/scripts/trace_report.py <name>
uv run python skills/skill-trace-debugger/scripts/trace_report.py --all --format jsonuv run python skills/skill-trace-debugger/scripts/check.py