evals-ops SKILL.md skillA
evals-ops from 0xdarkmatter/claude-mods is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add 0xdarkmatter/claude-mods/evals-ops@git:20260830.74aaaf6Pins git:20260830.74aaaf6 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- 0xdarkmatter/claude-mods
- Path
skills/evals-ops/SKILL.md- Versions recorded
- 3
- Latest version
- git:20260830.74aaaf6, committed Aug 30, 2026
- First version recorded
- Aug 30, 2026
- Size
- 17,838 bytes
- Repository stars
- 68
- License
- MIT
Build and run evals for LLM and agent systems: golden datasets, LLM-as-a-judge with bias control, trajectory/step/outcome scoring, adversarial refuters, and CI regression gates. Triggers on: eval, evals, eval harness, golden dataset, golden set, LLM-as-a-judge, judge rubric, judge bias, judge calibration, Cohen kappa, agreement with human labels, pass@k, pass^k, trajectory eval, step-level eval, tool-call accuracy, regression gate, eval CI, blocking vs advisory eval, faithfulness score…
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
# Evals Ops **Evals are the prerequisite, not the polish.** You cannot tune a prompt, a retriever, a compaction strategy or a memory layer without a harness that says whether the change made things better. Teams that skip this ship vibes and learn about regressions from users. This skill is the operational layer: what to measure, how to build the dataset, how to make a judge trustworthy, and how to gate CI on it without teaching everyone to ignore red. ## Route first | The ask | Go to | |---|---| | "What should I even measure?" | [Three levels](#three-levels-of-agent-eval) → `references/eval-taxonomy.md` | | "Where do the test cases come from?" | [Golden set](#the-golden-set) → `references/golden-datasets.md` | | "My judge disagrees with me / is it any good?" | [Judges](#llm-as-a-judge) → `references/llm-judge.md` | | "Verify a finding is real, not plausible" | [Refuters](#adversarial-verification) → `references/adversarial-verification.md` | | "Is my RAG retrieval any good?" | [Retrieval](#retrieval) → `references/retrieval-eval.md` | | "Where do the human labels come from?" | `references/annotation-workflow.md` | …
Read the whole file at its exact version.
How to install
mdr add 0xdarkmatter/claude-mods/evals-ops@sha256:80089054569cd635The line at the top of this page pins the label git:20260830.74aaaf6, 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_edzrx3dtvpik73m4)
1 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 3 versions of this file, all committed on Aug 30, 2026.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260830.74aaaf6 latest | 2026-08-30 | 74aaaf6 | 17,838 B | A | view · diff |
| git:20260830.d166a49 | 2026-08-30 | d166a49 | 15,676 B | A | view · diff |
| git:20260830.c38138b | 2026-08-30 | c38138b | 11,642 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 (17838 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
0xdarkmatter/claude-mods · 68 stars · license MIT · pushed 2026-10-14 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_edzrx3dtvpik73m4 GET https://markdownregistry.com/api/v1/resolve?ref=0xdarkmatter/claude-mods/evals-ops GET https://markdownregistry.com/api/v1/blob/80089054569cd635d90060dc2d5061986951c65736f7f186f64f4ece4e3063c6
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.