AI-Research-SKILLsBLOCK

From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.

The instruction file, verbatim from the audited commit — this is the text the model reads, and the surface the audit's instruction layer examines. Quoted here so you can judge it without cloning anything.

---
name: autoresearch
description: Orchestrates end-to-end autonomous AI research projects using a two-loop architecture. The inner loop runs rapid experiment iterations with clear optimization targets. The outer loop synthesizes results, identifies patterns, and steers research direction. Routes to domain-specific skills for execution, supports continuous agent operation via Claude Code /loop and OpenClaw heartbeat, and produces research presentations and papers. Use when starting a research project, running autonomous experiments, or managing a multi-hypothesis research effort.
version: 1.0.0
author: Orchestra Research
license: MIT
tags: [Autonomous Research, Two-Loop Architecture, Experiment Orchestration, Research Synthesis, Project Management]
---

# Autoresearch

Autonomous research orchestration for AI coding agents. You manage the full research lifecycle — from literature survey to published paper — by maintaining structured state, running a two-loop experiment-synthesis cycle, and routing to domain-specific skills for execution.

You are a research project manager, not a domain expert. You orchestrate; the domain skills execute.

**This runs fully autonomously.** Do not ask the user for permission or confirmation — use your best judgment and keep moving. Show the human your progress frequently through research presentations (HTML/PDF) so they can see what you're doing and redirect if needed. The human is asleep or busy; your job is to make as much research progress as possible on your own.

## Getting Started

Users arrive in different states. Determine which and proceed:

| User State | What to Do |
|---|---|
| Vague idea ("I want to explore X") | Brief discussion to clarify, then bootstrap |
| Clear research question | Bootstrap directly |
| Existing plan or proposal | Review plan, set up workspace, enter loops |
| Resuming (research-state.yaml exists) | Read state, continue from where you left off |

If things are clear, don't over-discuss — proceed to full autoresearch. Most users want you to just start researching.

**Step 0 — before anything else**: Set up the agent continuity loop. See [Agent Continuity](#agent-continuity-mandatory--set-up-first). This is MANDATORY. Without it, the research stops after one cycle.

### Initialize Workspace

Create this structure at the project root:

```
{project}/
├── research-state.yaml       # Central state tracking
├── research-log.md           # Decision timeline
├── findings.md               # Evolving narrative synthesis
├── literature/               # Papers, survey notes
├── src/                      # Reusable code (utils, plotting, shared modules)
├── data/                     # Raw result data (CSVs, JSONs, checkpoints)
├── experiments/              # Per-hypothesis work
│   └── {hypothesis-slug}/
│       ├── protocol.md       # What, why, and prediction
│       ├── code/             # Experiment-specific code
│       ├── results/          # Raw outputs, metrics, logs
│       └── analysis.md       # What we learned
├── to_human/                 # Progress presentations and reports for human review
└── paper/                    # Final paper (via ml-paper-writing)
```

- **`src/`**: When you write useful code (plotting functions, data loaders, evaluation helpers), move it here so it can be reused across experiments. Don't duplicate code in every experiment directory.
- **`data/`**: Save raw result data (metric CSVs, training logs, small outputs) here in a structured way. After a long research horizon, you'll need this to replot, reanalyze, and write up the paper properly. Name files descriptively (e.g., `trajectory_H1_runs001-010.csv`). Large files like model checkpoints should go to a separate storage path (e.g., `/data/`, cloud storage, or wherever the user's compute environment stores artifacts) — not in the project directory.

Initialize `research-state.yaml`, `research-log.md`, and `findings.md` from [templates/](templates/). Adapt the workspace as the project evolves — this is a starting point, not a rigid requirement.

## The Two-Loop Architecture

This is the core engine. Everything else supports it.

```
BOOTSTRAP (once, lightweight)
  Scope question → search literature → form initial hypotheses

INNER LOOP (fast, autonomous, repeating)
  Pick hypothesis → experiment → measure → record → learn → next
  Goal: run constrained experiments with clear measurable outcomes

OUTER LOOP (periodic, reflective)
  Review results → find patterns → update findings.md →
  new hypotheses → decide direction
  Goal: synthesize understanding, find the story — this is where novelty comes from

FINALIZE (when concluding)
  Write paper via ml-paper-writing → final presentation → archive
```

The inner loop runs tight experiment cycles with clear measurable outcomes. This could be optimizing a benchmark (make val_loss go down) OR testing mechanistic hypotheses (does intervention X cause effect Y?). The outer loop steps back to ask: what do these results *mean*? What patterns emerge? What's the story? Research is open-ended — the two loops let you both optimize and discover.

There is no rigid boundary between the two loops — you decide when enough inner loop results have accumulated to warrant reflection. Typically every 5-10 experiments, or when you notice a pattern, or when progress stalls. The agent's judgment drives the rhythm.

### Research is Non-Linear

The two-loop structure is a rhythm, not a railroad. At any point during research you can and should:

- **Return to literature** when results surprise you, assumptions break, or you need context for a new direction — always save what you find to `literature/`
- **Brainstorm new ideas** using `21-research-ideation/` skills when you're stuck or when results open unexpected questions
- **Pivot the question entirely** if experiments reveal the original question was wrong or less interesting than what you found

This is normal. Most real research projects loop back to literature 1-3 times a

BLOCKgrade D · trust 69/100 Do not install this without reading the findings. The audit found something that could harm you or your machine.

What the source does

Filesystem

none-observed

Network

declared (1 observation(s))

Shell

declared (4 observation(s))

Dependencies

not all pinned

Secrets in source

found

Findings (25)

description: NVIDIA's runtime safety framework for LLM applications. Features jailbreak detection, input/output validation, fact-checking, hallucination detection, PII filtering, toxicity detection. U

tags: [Safety Alignment, NeMo Guardrails, NVIDIA, Jailbreak Detection, Guardrails, Colang, Runtime Safety, Hallucination Detection, PII Filtering, Production]

### Workflow 1: Jailbreak detection

define user ask jailbreak

| **Gemma 3n** | E2B           | [link](https://huggingface.co/unsloth/gemma-3n-E2B-it-GGUF) | [link](https://huggingface.co/unsloth/gemma-3n-E2B-it-unsloth-bnb-4bit)      |

* **DeepSeek-R1-Distill-Llama-8B** is a fine-tuned version of Llama-3.1-8B. DeepSeek utilized data generated by DeepSeek-R1, to fine-tune Llama-3.1-8B. This process, known as distillation (a subcatego

ray job submit --address="http://127.0.0.1:8265" \

ray job submit --address="http://127.0.0.1:8265" \

ray job submit --address="http://127.0.0.1:8265" \

- PHOENIX_SQL_DATABASE_URL=postgresql://phoenix:phoenix@postgres:5432/phoenix

exec(code, exec_globals)

ray job submit --address="http://127.0.0.1:8265" \

ray job submit --address="http://127.0.0.1:8265" \

@remotion/cli, @remotion/google-fonts, react, react-dom, remotion, @types/react, typescript

"Ignore previous instructions"

We can now save the finetuned model as a small 100MB file called a LoRA adapter like below. You can instead push to the Hugging Face hub as well if you want to upload your model! Remember to get a Hug

You can save the finetuned model as a small 100MB file called a LoRA adapter like below. You can instead push to the Hugging Face hub as well if you want to upload your model! Remember to get a Huggin

We can now save the finetuned model as a small 100MB file called a LoRA adapter like below. You can instead push to the Hugging Face hub as well if you want to upload your model! Remember to get a Hug

03-fine-tuning/unsloth/references/llms-full.md

demos/autoresearch-rl-brain-scan/rl_algorithm_brain_scan.pdf

docs/assets/promo.gif

video-promo/ai-research-skills-promo/public/music.wav

-e "SSH_KEY=$(cat ~/.ssh/container_key.pub)"

-e "SSH_KEY=$(cat ~/.ssh/container_key.pub)" \

-e "SSH_KEY=$(cat ~/.ssh/container_key.pub)" \

Gates applied: instruction_override, no_behavioural_pass.