bjcoombs/ai-native-toolkit · skills/ab-equivalence/SKILL.md

ab-equivalence skillA

ab-equivalence is agent-read markdown (skill) from bjcoombs/ai-native-toolkit: Compare two versions of an LLM-directed document - an original (teacher) and a candidate (student) - across a transfer set and return a per-case behavioural-equivalence verdict plus an efficiency signal. A transform-agnostic library capability other skills compose to gate a transform on behavioural sameness. TRIGGER when asked to A/B test two versions of a prompt / instruction / skill, to check whether a rewritten or compressed document still behaves the same as the original, to validate behavio.

Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.

How to install

Latest version
mdr add bjcoombs/ai-native-toolkit/ab-equivalence@git:20260625.d42d180
Exact content
mdr add bjcoombs/ai-native-toolkit/ab-equivalence@sha256:e7021fc39dd14390

Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_fods5pdtyjavbxfg.svg)](https://markdownregistry.com/a/art_fods5pdtyjavbxfg)

0 badge views in 30 days

Versions

versioncommittedcommitsizeaudit
git:20260625.d42d180 latest2026-06-25 d42d180 12,915 BA view · diff
git:20260624.87091612026-06-24 8709161 13,302 BA view · diff
git:20260618.9c357352026-06-18 9c35735 12,515 BA view · diff
git:20260617.d990bfb2026-06-17 d990bfb 11,859 BA view · diff
git:20260603.ad374972026-06-03 ad37497 11,752 BA view

Audit of the latest version

A  17 of 17 checks passed. Deterministic, no model, 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 (12915 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

bjcoombs/ai-native-toolkit · 30 stars · license Apache-2.0 · pushed 2026-09-14 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_fods5pdtyjavbxfg
GET https://markdownregistry.com/api/v1/resolve?ref=bjcoombs/ai-native-toolkit/ab-equivalence
GET https://markdownregistry.com/api/v1/blob/e7021fc39dd14390e044160ad4190c8f433fd095b4e84cd437553b75d5302bf8

Agents talk at modelranch.com: hand yours the instructions there and it joins the network that reads files like this one.