Home / grainulation / grainulator · GitHub

calibrate SKILL.md skillA

calibrate from grainulation/grainulator is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned

mdr add grainulation/grainulator/calibrate@git:20260922.e702f49

Pins git:20260922.e702f49 in mdr.lock. Pin the fingerprint instead.

Audit grade: A, 17 of 17 checks passed
Kind: SKILL.md skill
Repository: grainulation/grainulator
Path: skills/calibrate/SKILL.md
Versions recorded: 3
Latest version: git:20260922.e702f49, committed Sep 22, 2026
First version recorded: Apr 7, 2026
Size: 5,036 bytes
Repository stars: 86
License: MIT

Score past predictions against actual outcomes. Closes the feedback loop.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# /calibrate -- Score predictions vs outcomes

The user wants to check what actually happened after a sprint's recommendations were implemented.

## Arguments

$ARGUMENTS

Expected format: `/calibrate --outcome "what happened"` or `/calibrate <claim_id> "actual result"`

## Instructions

1. **Parse the outcome**: The user provides outcome data as free text or claim-specific results.

2. **Match outcomes to predictions**: Use `grainulator.search` to find the original estimate, recommendation, or risk claims that predicted something. For explicit IDs use `id` and `full: true` with the sprint `dir`, not a text query. Read complete prediction and source context. Compare prediction to actual outcome.

3. **Create calibration claims** as `cal###` claims with the evidence tier supported by the source: use `stated` for stakeholder reports, `tested` for checks actually run, and `production` only for observed production measurements. Do not promote an assertion merely because it describes an outcome:
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint

mdr add grainulation/grainulator/calibrate@sha256:4f9af9beeda5c14a

The line at the top of this page pins the label git:20260922.e702f49, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

[![mdr](https://markdownregistry.com/badge/art_e7yoj76upzoefut4.svg)](https://markdownregistry.com/a/art_e7yoj76upzoefut4)

6 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 3 versions of this file, between Apr 7, 2026 and Sep 22, 2026, about one every 84 days.

version	committed	commit	size	audit
git:20260922.e702f49 latest	2026-09-22	e702f49	5,036 B	A	view · diff
git:20260908.608fac0	2026-09-08	608fac0	3,625 B	A	view · diff
git:20260407.59ecbc6	2026-04-07	59ecbc6	1,889 B	A	view

Audit of the latest version

A 17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.

pass: Frontmatter block present
pass: Frontmatter declares a name
pass: Frontmatter declares a description
pass: Size between 200 bytes and 200 KB (5036 bytes)
pass: No zero-width or bidi control characters
pass: No instruction hidden inside an HTML comment
pass: No link to an exfiltration or paste host
pass: No credential-shaped string
pass: No instruction to send local credentials anywhere
pass: No text hidden with inline styles
pass: No prompt-injection phrasing
pass: No curl or wget piped into a shell
pass: No recursive delete of root, home or parent
pass: No instruction to read or print local credentials
pass: No base64 blob over 200 characters
pass: No link to a raw IP address
pass: No script tag

Source

GitHub

grainulation/grainulator · 86 stars · license MIT · pushed 2026-11-05 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_e7yoj76upzoefut4
GET https://markdownregistry.com/api/v1/resolve?ref=grainulation/grainulator/calibrate
GET https://markdownregistry.com/api/v1/blob/4f9af9beeda5c14af123cb5b78ca105c74be62239ff8e173b5a9621493e9db95

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from grainulation/grainulator

AGENTS.md AGENTS.md file

grainulation/grainulator · AGENTS.md

git:20261103.2b1463d · audit A · 86 stars

AGENTS.md@packages/evidence AGENTS.md file

grainulation/grainulator · packages/evidence/AGENTS.md

git:20260908.608fac0 · audit A · 86 stars

bean SKILL.md skill

grainulation/grainulator · packages/runtime/skills/bean/SKILL.md · Run a task as a recursive convergence loop, not a fixed checklist: investigate the most decisive open question, record…

git:20260908.608fac0 · audit A · 86 stars

analytics SKILL.md skill

grainulation/grainulator · skills/analytics/SKILL.md · Sprint analytics — type distributions, stale claims, velocity, prediction scoring