llm-eval-harness SKILL.md skillA
llm-eval-harness from daymade/claude-code-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add daymade/claude-code-skills/llm-eval-harness@git:20261031.c952613Pins git:20261031.c952613 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- daymade/claude-code-skills
- Path
llm-eval-harness/SKILL.md- Versions recorded
- 9
- Latest version
- git:20261031.c952613, committed Oct 31, 2026
- First version recorded
- Jul 20, 2026
- Size
- 20,316 bytes
- Repository stars
- 1,519
- License
- MIT
Tests/benchmarks a third-party LLM endpoint (OpenAI- or Anthropic-compatible): availability, fidelity, speed, concurrency, protocol compliance, quality regression. Use before hand-rolling a curl loop, when onboarding a provider, or debugging "system prompt 不生效" / a tok/s claim — 测评/压测一个模型或渠道. Not for TTS/voice-clone supplier eval (use the audio skill).
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
# LLM Eval Harness ## Overview Give this skill an endpoint (`base_url` + `model` + an API key in an env var) and it measures whether the endpoint actually works and whether the model is fast, stable, protocol-correct, and good enough — instead of trusting the vendor's headline numbers. Choose from the following evaluation dimensions: | Dimension | Script | Answers | |---|---|---| | **Availability** | `scripts/availability_probe.py` | which model IDs work here, with explicit error classification | | **Request fidelity** | `scripts/fidelity_probe.py` | do system prompt / tools / history actually REACH the model? | | **Speed** | `scripts/speed_probe.py` | TTFT + sustained decode tok/s, **thinking-aware** | | **Concurrency / stability** | `scripts/concurrency_probe.py` | success rate, p50/p90 latency, where it breaks | | **Protocol compliance** | `scripts/protocol_probe.py` | does the Anthropic `thinking` block actually fire when requested, AND does the endpoint accept one already sitting in history on a later turn (N≥10, both are separate checks — see Dimension 3)? | …
Read the whole file at its exact version.
How to install
mdr add daymade/claude-code-skills/llm-eval-harness@sha256:c37e75f798816959The line at the top of this page pins the label git:20261031.c952613, 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_33znqcz6i7yp3uqd)
3 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 9 versions of this file, between Jul 20, 2026 and Oct 31, 2026, about one every 13 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261031.c952613 latest | 2026-10-31 | c952613 | 20,316 B | A | view · diff |
| git:20261029.3941627 | 2026-10-29 | 3941627 | 19,760 B | A | view · diff |
| git:20261029.e5a8515 | 2026-10-29 | e5a8515 | 19,992 B | A | view · diff |
| git:20261020.7b7471c | 2026-10-20 | 7b7471c | 19,768 B | A | view · diff |
| git:20260923.943df48 | 2026-09-23 | 943df48 | 19,015 B | A | view · diff |
| git:20260916.72243bd | 2026-09-16 | 72243bd | 19,752 B | A | view · diff |
| git:20260721.20c3adb | 2026-07-21 | 20c3adb | 19,768 B | A | view · diff |
| git:20260721.dda4e14 | 2026-07-21 | dda4e14 | 19,397 B | A | view · diff |
| git:20260720.8a54696 | 2026-07-20 | 8a54696 | 16,294 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 (20316 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
daymade/claude-code-skills · 1,519 stars · license MIT · pushed 2026-11-07 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_33znqcz6i7yp3uqd GET https://markdownregistry.com/api/v1/resolve?ref=daymade/claude-code-skills/llm-eval-harness GET https://markdownregistry.com/api/v1/blob/c37e75f7988169596ac08bd4637ea73efacd914dbf8d54df933d8a8fcab04367
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.