LLM Benchmarking with lm-evaluation-harness
Orchestra-Research/AI-Research-SKILLs
Runs lm-evaluation-harness to benchmark language models on academic suites such as MMLU, GSM8K and HumanEval, compare models and track training checkpoints.
A skill your agent uses when writing, editing, or reviewing evalite-scored agent evals in packages/core/compute/assistant-evals/src/evals.
Install Agent Eval Tests
$ npx skills add dxos/dxos --skill agent-eval-tests -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install dxos/dxos agent-eval-tests --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/dxos/dxos.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/agent-eval-tests .claude/skills/agent-eval-tests && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "agent-eval-tests" agent skill from https://github.com/dxos/dxos/tree/main/.agents/skills/agent-eval-tests into .claude/skills/agent-eval-tests/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-eval-tests", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/dxos/dxos/tree/main/.agents/skills/agent-eval-testsType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add dxos/dxos --skill agent-eval-tests -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install dxos/dxos agent-eval-tests --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/dxos/dxos.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.agents/skills/agent-eval-tests .agents/skills/agent-eval-tests && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "agent-eval-tests" agent skill from https://github.com/dxos/dxos/tree/main/.agents/skills/agent-eval-tests into .agents/skills/agent-eval-tests/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-eval-tests", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add dxos/dxos --skill agent-eval-tests -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install dxos/dxos agent-eval-tests --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/dxos/dxos.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.agents/skills/agent-eval-tests .cursor/skills/agent-eval-tests && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "agent-eval-tests" agent skill from https://github.com/dxos/dxos/tree/main/.agents/skills/agent-eval-tests into .cursor/skills/agent-eval-tests/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-eval-tests", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/dxos/dxos.git --path .agents/skills/agent-eval-tests--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add dxos/dxos --skill agent-eval-tests -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install dxos/dxos agent-eval-tests --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/dxos/dxos.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.agents/skills/agent-eval-tests .gemini/skills/agent-eval-tests && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "agent-eval-tests" agent skill from https://github.com/dxos/dxos/tree/main/.agents/skills/agent-eval-tests into .gemini/skills/agent-eval-tests/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-eval-tests", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install dxos/dxos agent-eval-testsInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add dxos/dxos --skill agent-eval-tests -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/dxos/dxos.git skills-src && mkdir -p .github/skills && cp -r skills-src/.agents/skills/agent-eval-tests .github/skills/agent-eval-tests && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "agent-eval-tests" agent skill from https://github.com/dxos/dxos/tree/main/.agents/skills/agent-eval-tests into .github/skills/agent-eval-tests/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-eval-tests", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add dxos/dxos --skill agent-eval-tests -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install dxos/dxos agent-eval-tests --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/dxos/dxos.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.agents/skills/agent-eval-tests .opencode/skills/agent-eval-tests && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "agent-eval-tests" agent skill from https://github.com/dxos/dxos/tree/main/.agents/skills/agent-eval-tests into .opencode/skills/agent-eval-tests/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-eval-tests", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
agent-eval-tests- GitHub stars
- 525
- Token cost
- ~4.1k tokens
- SKILL.md length
- 1,655 words
- Files
- 1
- Skills in repo
- 41
- Repo updated
- First seen
- Licence
- Custom licence
At a glance
A skill your agent uses when writing, editing, or reviewing evalite-scored agent evals in packages/core/compute/assistant-evals/src/evals.
- Reviewing evalite-scored agent evals in packages/core/compute/assistant-evals/src/evals
- SKILL.md covers Overview, Eval File Structure, Running Evals and Gotchas (found the hard way —…, plus 1 more section
- Calls pnpm; needs DX_ANTHROPIC_API_KEY
- Creating new eval files
What it does
Agent Eval Tests is an agent skill from dxos/dxos. Use when writing, editing, or reviewing evalite-scored agent evals in packages/core/compute/assistant-evals/src/evals. Use when creating new eval files, adding deterministic assertions or an LLM-judge scorer, or fixing a failing/mis-scoring eval.
Its SKILL.md is about 4.1k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in AI & LLM Engineering, covering LLM evaluation. The repository describes itself as: TypeScript implementation of the DXOS protocols, SDK, toolchain and Composer.
When your agent uses it
- Reviewing evalite-scored agent evals in packages/core/compute/assistant-evals/src/evals
- Creating new eval files
- Adding deterministic assertions
- An LLM-judge scorer
Example prompts
- “/agent-eval-tests”
Requirements
- A credential in DX_ANTHROPIC_API_KEY
What it can do on your machine
Read from SKILL.md and the folder at commit 64f1a7a. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
pnpm
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use pnpm, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names these keys or tokens, usually read from environment variables:
DX_ANTHROPIC_API_KEY
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Agent Eval Tests loads about 4.1k tokens when it runs. Until then it costs about 66 tokens; SKILL.md has 1,655 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 1,655 words (~4,087 tokens).
“Evals verify assistant behavior by running a real prompt against the full agent stack, live, then grading the outcome with a Scorer — code that checks the real DB/tool-invocation effect (deterministic, "dimension G") or an LLM judge for open-ended quality…”
- name
- agent-eval-tests
Files
Just SKILL.md in .agents/skills/agent-eval-tests of dxos/dxos.
Open the folder on GitHubat commit 64f1a7a
Compare with similar skills
Agent Eval Tests next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Agent Eval Tests this skilldxos/dxos | 525 | — | ~4.1k | Automated safety check: Pass | Custom licence | |
| LLM Benchmarking with lm-evaluation-harnessOrchestra-Research/AI-Research-SKILLs | 13k | 8 repos | ~3k | Automated safety check: Pass | MIT | |
| Azure AI Projects Python SDKmicrosoft/skills | 3.1k | 6 repos | ~2.8k | Automated safety check: Pass | MIT | |
| Fine-Tuning ExpertJeffallan/claude-skills | 12k | 1 repos | ~1.7k | Automated safety check: Pass | MIT | |
| Looperksimback/looper | 710 | — | ~2.7k | Automated safety check: Notes | MIT | |
| Hugging Face Local Model Evalshuggingface/skills | 11k | 2 repos | ~1.6k | Automated safety check: Pass | Apache-2.0 |
Similar skills
- Official
Azure AI Projects Python SDK
microsoft/skills
Reference for building on Microsoft Foundry with the azure-ai-projects Python SDK: project clients, versioned agents, evaluations, connections, datasets and indexes.
Fine-Tuning Expert
Jeffallan/claude-skills
Guides LLM fine-tuning with LoRA and QLoRA through Hugging Face PEFT, from dataset validation and training checks to adapter merging, quantization and deployment.
Looper
ksimback/looper
Scaffold a well-designed agent loop with best-practice coaching and a cross-model review council.
- Official
Hugging Face Local Model Evals
huggingface/skills
Runs evaluations of Hugging Face Hub models on local hardware with inspect-ai or lighteval, and helps choose between vLLM, Transformers and accelerate backends.
- Official
Agent Eval Engineering
langchain-ai/langchain-skills
Builds agent evaluations in stages: inspect the repository and traces, agree a Task Spec with you, then build, audit and run a Harbor task with an independent verifier.
More from dxos/dxos
All 41 skills in this repoAgentic Review
dxos/dxos
Run the rule-driven agentic code review — discover rule blocks in the repo's .mdl files, prepare per-rule review groups (full project by default; diff-only with --pr-only), spawn one focused Sonnet…
Composer Forensics
dxos/dxos
Forensically inspect and repair Composer browser profiles — offline (Chrome OPFS / SQLite extract) or live via /recovery.html debug port.
Migrate Oxfmt
dxos/dxos
Guide for migrating a project from Prettier or Biome to Oxfmt.
Moon
dxos/dxos
This skill should be used when the user asks to "configure moon", "set up moonrepo", "create moon tasks", "run moon commands", "configure moon workspace", "add moon project", "moon ci setup", "moon…
Subduction Policy
dxos/dxos
Reference for SubductionPolicy (the four hooks authorizeConnect, authorizeFetch, authorizePut, filterAuthorizedFetch passed via Subduction.hydrate(..., policy) or new Repo({ subductionPolicy })).
Autocue
dxos/dxos
Record a demo of the running app that the agent drives itself — a .mdl QA test or an ad-hoc walkthrough — as a captioned .webm (or a screenshot), trimmed of dead air and ready to attach.
Related
Categories
Questions about Agent Eval Tests
What does Agent Eval Tests do?
A skill your agent uses when writing, editing, or reviewing evalite-scored agent evals in packages/core/compute/assistant-evals/src/evals. Agent Eval Tests is an agent skill from dxos/dxos. Use when writing, editing, or reviewing evalite-scored agent evals in packages/core/compute/assistant-evals/src/evals.
When should I use Agent Eval Tests?
Agent Eval Tests fits situations like: reviewing evalite-scored agent evals in packages/core/compute/assistant-evals/src/evals; creating new eval files; adding deterministic assertions; an LLM-judge scorer.
How do I install Agent Eval Tests in Claude Code?
Run `npx skills add dxos/dxos --skill agent-eval-tests -a claude-code`. Or copy the skill folder (.agents/skills/agent-eval-tests in dxos/dxos) into .claude/skills/agent-eval-tests in your project. Claude Code loads it when a task matches its description.
How do I install Agent Eval Tests in Codex?
Run `npx skills add dxos/dxos --skill agent-eval-tests -a codex`. Or copy the skill folder (.agents/skills/agent-eval-tests in dxos/dxos) into .agents/skills/agent-eval-tests in your project. Codex loads it when a task matches its description.
Can I use Agent Eval Tests in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add dxos/dxos --skill agent-eval-tests -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/agent-eval-tests, .gemini/skills/agent-eval-tests, .github/skills/agent-eval-tests and .opencode/skills/agent-eval-tests in your project.
What does Agent Eval Tests need to run?
Going by SKILL.md and its folder, Agent Eval Tests needs the command-line tools its instructions call (pnpm) and credentials named DX_ANTHROPIC_API_KEY. Our summary lists: A credential in DX_ANTHROPIC_API_KEY.
Does Agent Eval Tests access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Agent Eval Tests safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Agent Eval Tests use?
Agent Eval Tests has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.
How many tokens does Agent Eval Tests use?
About 4.1k tokens (SKILL.md is roughly 16k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Agent Eval Tests?
Skills that share tags, products or a category with Agent Eval Tests: LLM Benchmarking with lm-evaluation-harness (Orchestra-Research/AI-Research-SKILLs, 13k stars), Azure AI Projects Python SDK (microsoft/skills, 3.1k stars), Fine-Tuning Expert (Jeffallan/claude-skills, 12k stars) and Looper (ksimback/looper, 710 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Agent Eval Tests?
dxos (a GitHub organization) maintains it in dxos/dxos, which has 525 GitHub stars. The repository holds 41 skills in this directory. The repository was last updated on October 7, 2026.
Source: dxos/dxos on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.