calibrate SKILL.md skillA
calibrate from borda/ai-rig is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add borda/ai-rig/calibrate@git:20261012.8e6b67ePins git:20261012.8e6b67e in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- borda/ai-rig
- Path
plugins/cc_foundry/skills/calibrate/SKILL.md- Versions recorded
- 17
- Latest version
- git:20261012.8e6b67e, committed Oct 12, 2026
- First version recorded
- Aug 6, 2026
- Size
- 50,638 bytes
- Repository stars
- 28
- License
- Apache-2.0
Calibration testing for agents and skills. Generates synthetic problems with known outcomes (quasi-ground-truth), runs targets against them, measures recall, precision, confidence calibration — reveals whether self-reported confidence scores track actual quality.
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
<objective> Validate agents and skills by measuring outputs against synthetic problems with defined ground truth. Primary signal: **calibration bias** — gap between self-reported confidence and actual recall. Well-calibrated agent reports 0.9 when it finds ~90% of issues. Miscalibrated: reports 0.9, finds 60%. Calibration data drives improvement loop: systematic gaps: instruction updates; persistent overconfidence: adjusted re-run thresholds in MEMORY.md. NOT for: static routing overlap analysis (use /foundry:audit); manually reviewing skill output quality (use /develop:review (requires `develop` plugin)). </objective> <inputs> - **$ARGUMENTS**: parse `--flags` first, then resolve remaining tokens as scope targets **Flags** (order independent): - `--fast` — 3 problems per target (default when neither pace flag passed) - `--full` — 10 problems per target; mutually exclusive with `--fast` - `--ab-test` — also run `general-purpose` baseline and report delta metrics; requires benchmark (default `--fast` if no pace flag); mutually exclusive with `--apply` …
Read the whole file at its exact version.
How to install
mdr add borda/ai-rig/calibrate@sha256:f37bfa73825f121eThe line at the top of this page pins the label git:20261012.8e6b67e, 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.
[](https://markdownregistry.com/a/art_ngiiycxozt4kp6ml)
4 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 17 versions of this file, between Aug 6, 2026 and Oct 12, 2026, about one every 4 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261012.8e6b67e latest | 2026-10-12 | 8e6b67e | 50,638 B | A | view · diff |
| git:20261009.253fdb3 | 2026-10-09 | 253fdb3 | 50,485 B | A | view · diff |
| git:20261005.6367f83 | 2026-10-05 | 6367f83 | 49,677 B | A | view · diff |
| git:20261002.e974f38 | 2026-10-02 | e974f38 | 49,495 B | A | view · diff |
| git:20261002.381549d | 2026-10-02 | 381549d | 48,341 B | A | view · diff |
| git:20260930.5b12456 | 2026-09-30 | 5b12456 | 46,488 B | A | view · diff |
| git:20260929.98a9e77 | 2026-09-29 | 98a9e77 | 46,476 B | A | view · diff |
| git:20260923.39e3a48 | 2026-09-23 | 39e3a48 | 46,274 B | A | view · diff |
| git:20260918.3e1a63d | 2026-09-18 | 3e1a63d | 45,092 B | A | view · diff |
| git:20260912.65e8e29 | 2026-09-12 | 65e8e29 | 45,426 B | A | view · diff |
| git:20260911.be7b308 | 2026-09-11 | be7b308 | 45,689 B | A | view · diff |
| git:20260911.182df57 | 2026-09-11 | 182df57 | 45,608 B | A | view · diff |
| git:20260904.9c1cbe2 | 2026-09-04 | 9c1cbe2 | 47,653 B | A | view · diff |
| git:20260822.a5f4fd6 | 2026-08-22 | a5f4fd6 | 47,643 B | A | view · diff |
| git:20260821.d979319 | 2026-08-21 | d979319 | 46,910 B | A | view · diff |
| git:20260808.5143e56 | 2026-08-08 | 5143e56 | 46,926 B | A | view · diff |
| git:20260806.848a170 | 2026-08-06 | 848a170 | 46,952 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (50638 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
borda/ai-rig · 28 stars · license Apache-2.0 · pushed 2026-10-21 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_ngiiycxozt4kp6ml GET https://markdownregistry.com/api/v1/resolve?ref=borda/ai-rig/calibrate GET https://markdownregistry.com/api/v1/blob/f37bfa73825f121ec81bf04aac09c0850e42a2bb5d78d079ef2efdf99c40b81a
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.