Examples Run Analysis

Use this skill only to analyze evidence produced by a completed manual example workflow. The repository workflow belongs to the contributor who invoked its pnpm command; this skill never owns execution or cleanup.

Read-only boundary

• Use only read-only file listing, reading, and searching to inspect repository sources and existing evidence.
• Never invoke pnpm, Node.js, Bash, an example, a build, a test, or another workflow command.
• Never start, rerun, retry, stop, signal, or kill a process. Never create or own a background job.
• Never request elevated execution, broaden filesystem or network authority, source shell startup files, or alter credentials.
• Never create, modify, rename, or delete a log, rerun list, result file, source file, PID file, or other repository path.
• Do not treat this skill as authorization to perform a missing run. Ask the user to run the appropriate pnpm command manually and return after completed evidence exists.

Evidence to inspect

1. Find the newest completed .tmp/examples-start-logs/main_*.log. A completed main log contains the final Done. line, validation summary, All start results: heading, table header, and one final table row for every discovered entry in that run. Treat a log without that complete footer as incomplete or still running.
2. For every final table row with passed and exit 0, resolve the full package:script name from the earlier start or skip lines when the fixed-width table abbreviated it. Read the matching .tmp/examples-start-logs/<package>__<script>.log and the example's package.json script target plus its relevant source files.
3. Read the runner sources scripts/run-examples-workflow.sh and scripts/run-example-starts.mjs when needed to interpret filters, auto-input, concurrency, serialized entries, configured exclusions, auto-skips, optional server/audio/external modes, and timeouts.