agentleFS
Sign inStart free
sethatwoodsethatwood/belay/skills/calibrate/SKILL.md

calibrate

Skill0 starsChanged 51 days agoMITView on GitHub

Seed your map on the first session. A few questions per skill so what you already know starts earned and what you don't starts unearned.

6 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions6 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 6

    1. grainulation/grainulator★ 86same name
    2. robonuggets/skills★ 36same name
    3. robonuggets/calibrate★ 18same name
    4. sparkline-ventures/product-eval★ 15same name
    5. ronniepinnell/casper★ 1same name
    6. mehboobali98/rmine-skills★ 0same 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 repository5 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

4 rules. 0 are common, 1 is distinctive, and 3 are very specific to this project.

  • 0

    Common

    Most of the 6 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Call belay_map. Skip every skill that already has a logbook entry.

    line 9
  2. Distinctive:

    Ask, once, which of the remaining skills they believe they have done alone before, in production or close to it.

    line 10
  3. Very specific:

    After each skill, call belay_calibrate with earned true or false and a note that holds both questions and both answers in their words.

    line 12
  4. Very specific:

    When the list is done, call belay_map again and show the result as a plain list.

    line 13

“Common” is measured: kept by at least 6 in 10 of the 6 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

The person is new to this repo's map and some of its skills are ones they have done before. Find out which, honestly, and record it. Calibration is the only way a skill starts earned without three witnessed runs, so it has to be harder to pass than a review question.

  1. Call belay_map. Skip every skill that already has a logbook entry; calibration is for untouched skills only.
  2. Ask, once, which of the remaining skills they believe they have done alone before, in production or close to it. Take their list; do not calibrate the rest.
  3. For each skill on their list, one at a time, ask two questions a senior would ask to tell whether someone has done it, not whether they have read about it. Ask about the case that goes wrong, the thing that is easy to get past a test, the decision they had to make. Judge the answers honestly. Two good answers and the skill is earned. Anything less and it stays unearned, and you say so in one line without softening it.
  4. After each skill, call belay_calibrate with earned true or false and a note that holds both questions and both answers in their words.
  5. When the list is done, call belay_map again and show the result as a plain list.

One question per turn. No hints during calibration; a hint would make the answer yours. Judge without flattery, and never record a skill as earned because they asked you to.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.

Check your setup, free