calibration
Skill0 starsChanged 19 days agoMITView on GitHub
Analyze a QA calibration round where several evaluators scored the same tickets; report reviewer bias, agreement within tolerance, Krippendorff alpha, and which tickets to discuss. Use when the user mentions calibration, inter rater agreement, reviewer consistency, or shares a CSV with ticket_id, evaluator, score.
2 other projects use a version of this.
Adopted by
Most recently taken up by
- dynos-fit/dynos-worktheir own version, first seen Oct 13, 2026
- KirKruglov/ARMARIUMtheir own version, first seen Jul 1, 2026
Other versions2 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 2
- dynos-fit/dynos-work★ 2same name
- KirKruglov/ARMARIUM★ 1same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository3 other files it gives its agents.
- coaching-noteSkill
- nesting-reviewSkill
- qa-reviewSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 8
Run the script, do not estimate:
- Distinctive: line 23
Never name an evaluator as "wrong".
≈ “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.
Files
Calibration analysis
Run the script, do not estimate:
python3 ${CLAUDE_PLUGIN_ROOT}/scripts/calibrate.py --input <csv> --tolerance 5Input needs columns ticket_id, evaluator, score. If the user gives per criterion scores instead, first run score.py to get totals, then feed its CSV output to calibrate.py (it ignores extra columns).
How to read the result for the user
- Krippendorff alpha at or above 0.80: scores are trustworthy. 0.67 to 0.80: usable for coaching, not for consequences. Below 0.67: do not use this month's QA for anything that affects pay, PIPs or promotions; run a calibration session first.
- "Within tolerance" alone can look fine on a month where all tickets scored 90 plus; always report alpha next to it.
- An evaluator flagged
lenientorstricthas a mean bias larger than the tolerance. Report the number without judgment. - The tickets list is the session agenda, highest spread first. Offer to draft the agenda using
${CLAUDE_PLUGIN_ROOT}/templates/calibration-session.md.
Never name an evaluator as "wrong". Consensus is the median, and the goal of the session is to agree on a reading of the criterion, not to pick a winner.
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.