Meta Harness Optimization
Instead of hand-tuning prompts and memory systems, this framework automatically searches over the scaffolding code around your base model: what it stores, retrieves, and sees at each step. You define an evaluation metric and the proposer agent (Claude Code by default) generates and tests harness variants in a loop, evolving everything from memory strategies to context construction. The repo includes reference experiments for text classification and terminal tasks, plus an onboarding doc that walks you through adapting it to new domains. Think of it as automated hyperparameter search, but for the entire wrapper around your LLM instead of just numerical configs. Works with uv for dependency management, and each experiment is self-contained.
- skills.sh installs
- 306
- GitHub stars
- 26
- last updated
- Jun 3, 2026
Install
$ npx -y skills add aradotso/trending-skills --skill meta-harness-optimization --agent claude-codeInstalls into .claude/skills of the current project.
Files
Meta-Harness Optimization
Skill by ara.so — Daily 2026 Skills collection.
Meta-Harness is a framework for automated end-to-end search over model harnesses — the scaffolding code around a fixed base model that controls what the model stores, retrieves, and sees while working on a task. Rather than hand-crafting prompts and memory systems, Meta-Harness proposes, evaluates, and evolves harness implementations automatically.
Paper: Meta-Harness: End-to-End Optimization of Model Harnesses
Homepage: https://yoonholee.com/meta-harness/
Core Concepts
| Term | Meaning |
|---|---|
| Harness | All code around the base model: memory, retrieval, prompt construction, tool use |
| Proposer Agent | LLM (e.g. Claude Code) that proposes new harness variants |
| Evaluator | Runs proposed harnesses on a benchmark, returns a score |
| Meta-Loop | Iterative propose → evaluate → feedback cycle |
Installation
Meta-Harness uses uv for dependency management. Each reference experiment is self-contained:
# Text classification experiment
cd reference_examples/text_classification
uv sync
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageDetails
- Repository
- github.com/aradotso/trending-skills
- First seen
- Jun 3, 2026
More from aradotso/trending-skills
All 251- Border Beam React304
- Wx Favorites Report299
- Cc Design Html Prototyping297
- Pgque Postgres Queue296
- Huashu Design Html Native290
- Freebuff2api Openai Proxy289
- Aube Package Manager286
- Permiso Accessibility Permissions283
- Mdv Markdown Visualization282
- Create Simulated Aeronautics Mod281
- Kami Document Design277
- Gpt2api Openai Gateway276
- Opengame Agentic Game Creation268
- Oransim Causal Marketing Twin267
- Aglais Xqvm Quantum Vm266
- Cairn Ai Pentest265
- Flashkda Delta Attention261
- Openai Privacy Filter261
- Masterhttprelayvpn Proxy259
- Crabtrap Llm Proxy257
- Masterhttprelayvpn Rust256
- Tilekernels Gpu Kernels256
- Text To Cad Harness250
- Freellmapi Proxy212
Recommended
cavemanjuliusbrussee/cavemanUltra-compressed communication mode. Cuts output tokens 65% (measured) by speaking like caveman while keeping full technical accuracy. Supports intensity levels618.3Kskills.sh installs
improveshadcn/improveSurvey any codebase as a senior advisor and produce prioritized, self-contained implementation plans for OTHER models/agents to execute. Strictly read-only on s40Kskills.sh installs
systematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes326.7Kskills.sh installs
karpathy-guidelinesforrestchang/andrej-karpathy-skillsBehavioral guidelines to reduce common LLM coding mistakes through explicit assumptions, simplicity, and verifiable success criteria.17.9Kskills.sh installs
find-skillsvercel-labs/skillsHelps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express int4.3Mskills.sh installs