calibrate-workshop
Skill4 starsChanged 5 months agoNo licenceView on GitHub
Set up and run a rater calibration (human labeling) workshop on Calibrate with Claude Code. Turns a chat or WhatsApp conversation export into a Calibrate annotation task with rubric questions, an AI judge and one labeling link per rater, then turns the downloaded annotations into an inter-rater agreement dashboard for the group discussion, and rolls the revised rubric into the next round. Use when someone asks to set up a Calibrate project, task or annotation task, run a labeling or rubric workshop, write evaluator questions, create annotator links, run the AI judge, compare raters, build an agreement dashboard from a Calibrate CSV export, or prepare the next workshop. Ships Noora Health presets (India and Bangladesh RES data, self-hosted Calibrate).
- Reads credentials
In this repository4 other files it gives its agents.
- ask-agency-measurementSkill
- behavioral-scienceSkill
- taf-design-systemSkill
- taf-web-designSkill
The file
We split this skill into the rules it gives an agent
12 rules. About 0 are common, 3 are distinctive, and 9 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
9
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.