Skills
evaluating-llms-harness
by Orchestra-Research
Comprehensive open-source library of AI research and engineering skills for any AI model.
Our verdict
We have not reviewed evaluating-llms-harness yet
No one at Enterprise DNA has checked this listing against its sources. The description comes from public listings gathered automatically. Any fact below shows where it came from and when it was last checked.
From the listing
About evaluating-llms-harness
Comprehensive open-source library of AI research and engineering skills for any AI model. Package the skills and your claude code/codex/gemini agent will be an AI research agent with full horsepower. Maintained by Orchestra Research.
Best for
Developers building AI research agents on top of Claude Code, Codex, or Gemini.
Use cases
- Enhance coding agents with research and engineering skills
- Build custom AI research agents using existing skill packages
- Integrate evaluation harnesses into agent workflows
Notes
14,387 stars on GitHub. Last updated 2026-10-11. Licensed MIT.
Indexed from github-skill-repos. Verified against the live GitHub repo.
Pros
- Comprehensive collection of skills
- Model-agnostic, works with multiple agents
- Open-source and actively maintained
Cons
- Written in TeX, may limit accessibility
- Requires integration with specific agent frameworks
- Documentation may be sparse for non-research users
Key facts
What we have checked
- Days since the last commit
- 34
- GitHub forks
- 1,003
- GitHub stars
- 14,537
- Days to a first reply on issues
- 62.4
- Open issues
- 11
- Releases in the last 90 days
- 0
Each value shows when we last confirmed it and where it came from. Values we have not confirmed are left out, never guessed.
Stars and usage
How evaluating-llms-harness is growing
14,169 to 14,537
Health and security
Is evaluating-llms-harness looked after, and what do its setup files show
Health score
56 out of 100
| Part | Points | What we saw |
|---|---|---|
| Recent activity | 29.6 of 30 | Last push 34 days ago |
| Releases | 0 of 15 | 0 releases in 90 days |
| Issue replies | 0 of 20 | First reply in 62.4 days (median) |
| Maintainer | 15 of 15 | Owned by an organisation |
| Official source | Not counted | MCP servers only |
Security check static checks
100 out of 100
- Note 3 of 3 packages are not pinned to one version, so only the malicious packages list was checked for them, not version advisories.
Alternatives
Alternatives to evaluating-llms-harness
| Record | Type | How we know | Checked |
|---|---|---|---|
| google-agents-cli-evalAlternative to this | Skill | Matched from the listing text | |
| nemo-evaluator-sdkAlternative to this | Skill | Matched from the listing text | |
| NVIDIA Model Optimizer EvaluationAlternative to this | Skill | Matched from the listing text | |
| skill-doctorAlternative to this | Skill | Matched from the listing text |
Compare
Compare evaluating-llms-harness side by side
Sources
Where this comes from
- GitHubRegistry
A source shows what was published when we checked it. It does not certify security, performance or a working installation. Read our method.
Changelog
What changed
No changes recorded yet. Releases, price changes and deprecations appear here, with their dates, once we track them for this record.
Open-source & AI alternatives
Swap-in tools that solve the same job. Weigh the trade-offs before you commit.
NVIDIA Model Optimizer Evaluation
NVIDIA
Evaluate the accuracy of quantized or full LLMs with NVIDIA NeMo Evaluator, from config to benchmark scores.
google-agents-cli-eval
The CLI and skills that turn any coding assistant into an expert at creating, evaluating, and deploying AI agents on Google Cloud.
nemo-evaluator-sdk
Orchestra-Research
Comprehensive open-source library of AI research and engineering skills for any AI model. Package the skills and your claude code/codex/gemini agent will be an AI research agent wi
skill-doctor
warpdotdev
Grades agent skills by scoring agent conversations for efficiency, code quality, procedure compliance, and verbosity, then drafts concrete skill edits and a shareable…
Pairs with
Other entries in the index that connect to this one. Click through to see the chain.
autoresearch-universal
balukosuri
Self-improving prompt optimization using the Karpathy autoresearch pattern. Scans any repo, suggests optimization targets, auto-defines binary eval metrics, and runs an…
claw-bench
claw-bench
The Definitive AI Agent Benchmark
error-discovery
ai-evals-course
Skills that guide AI coding agents to help you build product-specific AI evals.
eval-engineering
langchain-ai
Inspect an agent repository and optional traces, interview the user, write reviewed Task Specs, build and audit Harbor tasks, and bootstrap reusable project World Knowledge…
evolving-ai-agents
Orchestra-Research
Comprehensive open-source library of AI research and engineering skills for any AI model. Package the skills and your claude code/codex/gemini agent will be an AI research agent wi
google-agents-cli-eval
The CLI and skills that turn any coding assistant into an expert at creating, evaluating, and deploying AI agents on Google Cloud.
nemo-evaluator-sdk
Orchestra-Research
Comprehensive open-source library of AI research and engineering skills for any AI model. Package the skills and your claude code/codex/gemini agent will be an AI research agent wi
nemo-guardrails
Orchestra-Research
Comprehensive open-source library of AI research and engineering skills for any AI model. Package the skills and your claude code/codex/gemini agent will be an AI research agent wi
skill-doctor
warpdotdev
Grades agent skills by scoring agent conversations for efficiency, code quality, procedure compliance, and verbosity, then drafts concrete skill edits and a shareable…
review
zby
"Extend with llm, stabilise with code" - Prompts when you're exploring, Python when you're certain. Workers and tools form one function space—refactor between them.
Get the free Developer’s Field Guide
A 27-page field guide to the AI coding workflow with Claude. Claude Code, MCP servers, the prompt patterns that work, and what to delegate. Free.
Enter your work email. We send it straight over, plus a few short notes worth knowing. Unsubscribe any time.