braintrust-evals
Skill0 starsChanged 4 days agoNo licenceView on GitHub
Run LLM evaluations, compare models, build datasets, define scoring functions, and track experiments using the Braintrust platform. NSLS uses Braintrust for AI pipeline evaluation across products. Trigger phrases: braintrust, evaluate, model comparison, LLM eval, scoring, prompt testing, experiment, dataset, which model, compare models, evaluation framework, test prompts, model benchmark, scoring rubric, structured output testing. Includes gotchas: prompt-schema alignment failures, key name mismatches, JSON mode markdown wrapping, minItems/maxItems strict-mode issues, scoring function edge cases, experiment naming collisions.
In this repository76 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- academic-outcomesSkill
- add-domainSkill
- ai-level-upSkill
- airtableSkill
- bet-ideaSkill
- bet-planSkill
- bet-researchSkill
- bet-studioSkill
- kw:brainstormSkill
- campus-roadshowSkill
- kw:compoundSkill
- connectSkill
- customerioSkill
- dashboard-designSkill
- data-intelSkill
- data-model-discoverySkill
- deployment-guideSkill
- email-ab-test-analysisSkill
- feature-branch-protocol-templateSkill
- frontend-slidesSkill
- full-shapeSkill
- gdoc-buildSkill
- gdoc-editSkill
- google-driveSkill
- google-slides-apiSkill
- gwsSkill
- help-centerSkill
- hex-accessSkill
- hubspotSkill
- instructional-designSkill
- interrogateSkill
- investigationSkill
- jd-builderSkill
- job-function-auditSkill
- kb-articleSkill
- llm-email-workflowSkill
- macroscopeSkill
- n8nSkill
- netlify-deploySkill
- nsls-authSkill
- nsls-focus-groupSkill
- nsls-setmeupSkill
- nsls-slidesSkill
- personal-setupSkill
- kw:planSkill
- posthogSkill
- product-designSkill
- prompt-packSkill
- provision-builderSkill
- publish-to-dsrSkill
- pydoc-pipelineSkill
- quicknoteSkill
- receiptsSkill
- register-automationSkill
- kw:reviewSkill
- scorecard-builderSkill
- second-opinionSkill
- setupSkill
- signal-setupSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
12 rules. About 0 are common, 10 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈10
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
No licence file, so all rights are reserved — read it at the source. We count its rules but don't quote them. Read them on GitHub.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.