eval-driven-dev SKILL.md skillA
eval-driven-dev from marielynneblock/arcanum-artifex is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add marielynneblock/arcanum-artifex/eval-driven-dev@v0.8.4Pins v0.8.4 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- marielynneblock/arcanum-artifex
- Path
skills/agentic/evaluation/eval-driven-dev/SKILL.md- Versions recorded
- 4
- Latest version
- v0.8.4, committed Jul 10, 2026
- First version recorded
- May 10, 2026
- Size
- 17,688 bytes
- Repository stars
- 4
- License
- none declared
Build an automated evaluation pipeline that tests a Python LLM application end-to-end with pixie test — real code paths, real LLM calls, instrumented external data — and scores outputs with evaluators instead of assertions. Use when adding evals to a Python AI app.
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 for Python LLM Applications You're building an **automated evaluation pipeline** that tests a Python-based AI application end-to-end — running it the same way a real user would, with real inputs — then scoring the outputs using evaluators and producing pass/fail results via `pixie test`. **What you're testing is the app itself** — its request handling, context assembly (how it gathers data, builds prompts, manages conversation state), routing, and response formatting. The app uses an LLM, which makes outputs non-deterministic — that's why you use evaluators (LLM-as-judge, similarity scores) instead of `assertEqual` — but the thing under test is the app's code, not the LLM. During evaluation, the app's own code runs for real — routing, prompt assembly, LLM calls, response formatting — nothing is mocked or stubbed. But the data the app reads from external sources (databases, caches, third-party APIs, voice streams) is replaced with test-specified values via instrumentations. This means each test case controls exactly what data the app sees, while still exercising the full application code path. …
Read the whole file at its exact version.
How to install
mdr add marielynneblock/arcanum-artifex/eval-driven-dev@sha256:6a6b1ee1d1bf0a29The line at the top of this page pins the label v0.8.4, 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_vljfatud6idrf4pk)
5 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 4 versions of this file, between May 10, 2026 and Jul 10, 2026, about one every 20 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| v0.8.4 latest | 2026-07-10 | 0115f49 | 17,688 B | A | view · diff |
| v0.8.4 | 2026-07-10 | ffb3400 | 17,688 B | A | view · diff |
| v0.8.4 | 2026-05-15 | b861afb | 17,411 B | B | view · diff |
| v0.8.4 | 2026-05-10 | f26bcec | 17,830 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 (17688 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
marielynneblock/arcanum-artifex · 4 stars · license none declared · pushed 2026-09-19 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_vljfatud6idrf4pk GET https://markdownregistry.com/api/v1/resolve?ref=marielynneblock/arcanum-artifex/eval-driven-dev GET https://markdownregistry.com/api/v1/blob/6a6b1ee1d1bf0a29f8e2034982e33e9426d5941fda02dca6afd1b8dd64f7e598
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 marielynneblock/arcanum-artifex
Every file in marielynneblock/arcanum-artifex