inspect-run

inspect-run is an LLM evaluation & observability skill for AI agents, published by Certora in the AIComposer repository on GitHub. Skillspace rates inspect-run C (70/100) and it passed the safety scan; the rating is based on static analysis only.

Read the full LLM message history (inputs, outputs, tool calls, errors, token usage, stop reasons) for an AIAutoProver run from its log folder. Use this skill ANY time the user asks something about a specific run that produced an autoProve log — e.g. "why did that run loop", "what error did the model see on retry 5", "how many tokens did it burn", "show me the prompt for the system-analysis call", "what did the code_explorer subagent for X return", "what was the LLM's last response before it died". The events.jsonl only contains metadata; the actual messages live in Postgres and this skill is the way to reach them. If the user asks about a run but does NOT provide a log path, proactively ask where the log is (e.g. ".certora_internal/autoProve/<timestamp>.events.jsonl" or the autoProve folder) before answering — do not guess or make claims about message content without inspecting it.

Grade
C
Quality
70 / 100
Safety
Passed
GitHub stars
30

Unproven: rated by static analysis only, not yet compared head-to-head.

Our two independent classifiers differ on this skill's category, so treat the placement as provisional.

This rating describes the version of the repository we crawled; it may have changed since, so go by its current files.

View source on GitHubCertora/AIComposer

Our review

Architecture
100 / 100
Maturity
Structured: ships references or scripts
Security scan
Low-risk patterns
License
MIT
Adoption
Adopted by 0 other repositories, in 0 collections

What the scanner flagged

  • mentions secrets in text

Not checked yet

  • Not judged on the rubric yet (not a contender in its category)
  • No blind task eval yet
  • Scope (portable / vendor / repo-internal) not assessed; only the top of each category is read for scope
  • Sibling files (scripts, references) not fetched; security scan covers SKILL.md only

More LLM evaluation & observability skills

Skillspace indexes and rates this skill; it does not host or endorse it. Run third-party skills at your own risk.