smithery.ai

anviloop-run-inspect

Unpack and inspect Anviloop result zips for meta, watchdog, run_summary, and proof logs. Use when extracting failure details or verifying proof.

First seen Apr 10, 2026

Installation

$ npx skills add https://smithery.ai

Also in this package

Other skills from smithery.ai · top by installs.

npx skills add https://smithery.ai

Browse all from smithery.ai

More details

Agent compatibility

Declared targets from SKILL.md / docs. Unmarked agents are not listed — the skill may still install via the CLI.

Claude Code Not declared
Cursor Not declared
Codex Not declared
GitHub Copilot Not declared
Windsurf Not declared
Gemini CLI Not declared
Cline Not declared
OpenCode Not declared

Package contents

Files included with this skill beyond the listing page.

  • skill md SKILL.md 1,022 B
  • docs SUMMARY.md 172 B

History

  1. First seen on skills.sh
  2. First recorded snapshot · 1 installs

SKILL.md

Anviloop Result Inspection

Extract

  • Unzip the newest result<jobid>.zip to a temp folder.

Read in order

  1. meta.json (exitreason, exitcode, failuresignature, scenarioid, seed, build_id, commit)
  2. out/watchdog.json (rawsignaturestring, stdouttail, stderrtail)
  3. out/run_summary.json (runtime, telemetry summary/bytes, artifacts presence)
  4. Optional proof: out/player.log, out/polishscorev0.json

Output (concise)

Use this shape:

Headline: <short failure headline>
Signature: <failure_signature or raw_signature_string>
Evidence: <files reviewed>
Proof: <marker or missing>

References

  • C:/Dev/unityclean/headlessrebuildtool/Polish/Docs/ANVILOOPRECURRING_ERRORS.md
  • C:/Dev/unityclean/headlessrebuildtool/Polish/Docs/MORNINGVIEW.md