FreeSkills
Commits, branches and sync with the but CLI
- 361361 downloads
- 198198 likes
- 103103 saves
- Claude Code
- Codex
- Cursor
- and 3 more
Every premium and members-only resource for $9.99/month, as a no-commitment subscription. See the plans
Use this resource to analyse and evaluate AI agent traces stored in BigQuery
New
Free
In a terminal, from the folder you want:
npx --yes palatekit@latest install bigquery-agent-trace-evaluationWith no option, the skill goes to ~/.agents/skills/; add --agent claude-code (or codex, cursor…) to target an agent.
First time: connect the CLI with
npx --yes palatekit@latest loginThe agent rebuilds traces from BigQuery, visualises them as a graph and runs an evaluation with an LLM judge or trajectory matching. It can also extract agent decisions at scale. You get measured quality results for your agents.
Mostly picked by
Updated November 2, 2026
You say
“Evaluate last week's traces with an LLM judge and list failures by step.”

Skill published by reason-machines under the MIT license, delivered in its original version.
Listed unmodified
« bigquery-agent-analytics-sdk » (reason-machines, MIT) livré dans sa version d'origine : fiche en français et en anglais par PalateKit.
–
No ratings yet
Loading reviews…