azure/aks-skills · evals/holmesgpt-eval/SKILL.md

holmesgpt-eval skillB

holmesgpt-eval is agent-read markdown (skill) from azure/aks-skills: Run HolmesGPT evals (tests/llm/fixtures/test_ask_holmes) against the current agent itself (agent-native). The agent must answer the prompts itself (no external wrapper) using its own tools, run before_test/after_test around each case, compare the answer to expected_output using the scoring rules here, and generate JSON + Markdown reports. This skill focuses exclusively on the agent-native flow. Supports bulk run (all tests) and individual run (specific test case). Supports filtering tests by tag.

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 azure/aks-skills/holmesgpt-eval@git:20260804.baba08f
Exact content
mdr add azure/aks-skills/holmesgpt-eval@sha256:6cd8ca3a4a8c9b9b

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_uu5eqq2s5bvzypfa.svg)](https://markdownregistry.com/a/art_uu5eqq2s5bvzypfa)

0 badge views in 30 days

Versions

versioncommittedcommitsizeaudit
git:20260804.baba08f latest2026-08-04 baba08f 8,170 BB view · diff
git:20260730.82d7ac62026-07-30 82d7ac6 8,172 BB view

Audit of the latest version

B  16 of 17 checks passed. Deterministic, no model, same answer every run.
  • fail: No script tag (matched: <script)
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (8170 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

Source

GitHub

azure/aks-skills · 5 stars · license MIT · pushed 2026-09-17 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_uu5eqq2s5bvzypfa
GET https://markdownregistry.com/api/v1/resolve?ref=azure/aks-skills/holmesgpt-eval
GET https://markdownregistry.com/api/v1/blob/6cd8ca3a4a8c9b9be3b737f01964982a5c1da0151157b1ec1b7d0ad11b682305

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