Home / andreibesleaga / gabbe · GitHub

eval-driven-development SKILL.md skillA

eval-driven-development from andreibesleaga/gabbe is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned

mdr add andreibesleaga/gabbe/eval-driven-development@git:20261014.de0823c

Pins git:20261014.de0823c in mdr.lock. Pin the fingerprint instead.

Audit grade: A, 17 of 17 checks passed
Kind: SKILL.md skill
Repository: andreibesleaga/gabbe
Path: plugins/gabbe-coding/skills/eval-driven-development/SKILL.md
Versions recorded: 1
Latest version: git:20261014.de0823c, committed Oct 14, 2026
Size: 7,153 bytes
Repository stars: 23
License: a license file GitHub does not identify

Build offline evaluation suites that score probabilistic LLM/agent quality, distinct from deterministic tests. Use when: build eval suite, score llm quality, golden dataset eval, eval-driven ci, prompt drift regression, pass at k reliability.

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

# Eval-Driven Development

## Goal
Build offline evaluation suites that *score* the quality of probabilistic LLM and agent
outputs, as opposed to tests that *verify* deterministic code. A unit test asserts a fixed
truth (`add(2,2) == 4`). An eval measures a distribution: "across 200 diverse inputs, how
often does the agent produce an acceptable answer, and how reliable is that across repeated
runs?" Evals raise confidence in a behavior that has no single correct output. They do not
prove correctness — be explicit about that throughout.

## Steps
1. **Define a golden dataset.**
   - Collect 100-300 input→expected cases that are *diverse* (cover edge cases, failure
     modes, and the long tail — not just the happy path) and *mutually exclusive* (no two
     cases test the same behavior, so a single regression does not silently fail ten rows).
   - Source from real production logs, known past bugs, and adversarial hand-authored cases.
   - Version-control the dataset alongside code so every change is reviewable and revertible.
   - Record, per case, the input, the expected output (or acceptance criteria), and which
     assertion tier applies.
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint

mdr add andreibesleaga/gabbe/eval-driven-development@sha256:4a9a8e0f5cbc608f

The line at the top of this page pins the label git:20261014.de0823c, 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_kddky6ild2h7miim.svg)](https://markdownregistry.com/a/art_kddky6ild2h7miim)

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

Versions

The registry has recorded 1 version of this file, committed on Oct 14, 2026.

version	committed	commit	size	audit
git:20261014.de0823c latest	2026-10-14	de0823c	7,153 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 (7153 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

andreibesleaga/gabbe · 23 stars · license a license file GitHub does not identify · pushed 2026-11-02 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_kddky6ild2h7miim
GET https://markdownregistry.com/api/v1/resolve?ref=andreibesleaga/gabbe/eval-driven-development
GET https://markdownregistry.com/api/v1/blob/4a9a8e0f5cbc608f32a3d7d36ec85e3a88dd14b4382a07d01eba67e886072e32

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 andreibesleaga/gabbe

AGENTS.md AGENTS.md file

andreibesleaga/gabbe · AGENTS.md

git:20261029.5ebfbf5 · audit A · 23 stars

AGENTS.md@agents AGENTS.md file

andreibesleaga/gabbe · agents/AGENTS.md

git:20261029.ce4317a · audit A · 23 stars

llms.txt llms.txt file

andreibesleaga/gabbe · llms.txt

git:20261029.d5d23d8 · audit C · 23 stars

a2ui-protocols SKILL.md skill

andreibesleaga/gabbe · plugins/gabbe-ai/skills/a2ui-protocols/SKILL.md · Design and enforce Agent-to-UI communication protocols. Use when: design agent ui protocol, implement a2ui, build genui.