AU

autoresearch

Persistent research agent that runs until validation criteria are met.

Install

mkdir -p .claude/skills/autoresearch && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/13502" && unzip -o skill.zip -d .claude/skills/autoresearch && rm skill.zip

Installs to .claude/skills/autoresearch

Activation

This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.

Stateful validator-gated research loop with native-hook persistence
67 charsno explicit “when” trigger
Advanced

Key capabilities

  • Choose validation mode at initialization
  • Persist mode state in `.omx/state/.../autoresearch-state.json`
  • Ensure completion is artifact-gated
  • Clarify mission and evaluator via `$deep-interview --autoresearch`
  • Materialize mission, sandbox, and result files

How it works

The skill initializes with a chosen validation mode, persists its state, and continues a research loop until a completion artifact satisfies the specified validation criteria.

Inputs & outputs

You give it
Research mission and chosen validation mode
You get back
Completion artifact satisfying the chosen validation mode

When to use autoresearch

  • Run multi-turn research
  • Verify automated task completion
  • Execute research mission

About this skill

Autoresearch

Autoresearch is the skill-first replacement for the deprecated omx autoresearch command. It keeps the useful measured-research loop, but it now runs as a native-hook stateful workflow instead of a direct CLI or tmux launch surface.

Use when

  • You want a Ralph-ish persistent research loop
  • The task should keep nudging until explicit validation evidence exists
  • You want init-time choice between script validation and prompt+architect validation

Do not use when

  • You want the old omx autoresearch command surface (hard-deprecated)
  • You want detached tmux or split-pane launch parity
  • You have not decided the validation regime yet

Core contract

  1. Init chooses validation mode. Pick exactly one:
    • mission-validator-script
    • prompt-architect-artifact
  2. Persist mode state in .omx/state/.../autoresearch-state.json including:
    • validation_mode
    • completion_artifact_path
    • mission_validator_command or validator_prompt
    • optional output_artifact_path
  3. Completion is artifact-gated. The loop does not stop because the model says “done”, because a stop hook fired once, or because several turns were no-ops.
  4. Direct CLI launch is gone. Use $deep-interview --autoresearch for intake and $autoresearch for execution.

Completion artifact contract

mission-validator-script

The completion artifact must exist and record a passing validator result, for example:

{
  "status": "passed",
  "passed": true,
  "summary": "metric improved beyond baseline"
}

prompt-architect-artifact

The completion artifact must include both an architect approval verdict and an output artifact path, for example:

{
  "validator_prompt": "Review the research output against the mission.",
  "architect_review": { "verdict": "approved" },
  "output_artifact_path": ".omx/specs/autoresearch-demo/report.md"
}

Recommended flow

  1. Run $deep-interview --autoresearch to clarify mission + evaluator.
  2. Materialize .omx/specs/autoresearch-{slug}/mission.md, sandbox.md, and result.json.
  3. Start $autoresearch with the chosen validation mode stored in mode state.
  4. Let stop-hook / auto-nudge continue until the completion artifact satisfies the chosen validation mode.
  5. Finish only after the validator artifact is complete.

Migration note

  • omx autoresearch is hard-deprecated.
  • No direct CLI launch.
  • No tmux split-pane launch.
  • No noop-count completion gate.

When not to use it

  • When the user wants the old `omx autoresearch` command surface
  • When the user wants detached tmux or split-pane launch parity
  • When the validation regime has not been decided yet

Limitations

  • Completion is artifact-gated; the loop does not stop because the model says “done”
  • Direct CLI launch is gone; use `$deep-interview --autoresearch` for intake and `$autoresearch` for execution

How it compares

This skill provides a stateful, validator-gated research loop with native-hook persistence, ensuring task completion based on explicit evidence, unlike a simple command execution.

Compared to similar skills

autoresearch side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
autoresearch (this skill)03moNo flagsAdvanced
auto03moNo flagsAdvanced
idea-discovery02moReviewAdvanced
learn-new-things01moReviewAdvanced

Try saying

Example prompts that trigger this skill in your AI assistant.

You might also like

auto

RintaroMasaoka

Autonomously execute research cycles. Specify the cycle limit as an argument (e.g., /auto 2). Default: 5.

00

idea-discovery

Shallow-W

Workflow 1: Full idea discovery pipeline. Orchestrates research-lit → idea-creator → novelty-check → research-review to go from a broad research direction to validated, pilot-tested ideas. Use when user says \"找idea全流程\", \"idea discovery pipeline\", \"从零开始找方向\", or wants the complete idea explorati

00

learn-new-things

Abilityai

Continuous learning heartbeat - autonomously researches, extracts insights, and expands knowledge base

00

nlm-skill

jacob-bd

Expert guide for the NotebookLM CLI (`nlm`) and MCP server - interfaces for Google NotebookLM. Use this skill when users want to interact with NotebookLM programmatically, including: creating/managing notebooks, adding sources (URLs, YouTube, text, Google Drive), generating content (podcasts, reports, quizzes, flashcards, mind maps, slides, infographics, videos, data tables), conducting research, chatting with sources, or automating NotebookLM workflows. Triggers on mentions of "nlm", "notebooklm", "notebook lm", "podcast generation", "audio overview", or any NotebookLM-related automation task.

895

deep-research

davidorex

Multi-agent parallel investigation for complex VCV Rack problems

35163

scientific-brainstorming

davila7

Research ideation partner. Generate hypotheses, explore interdisciplinary connections, challenge assumptions, develop methodologies, identify research gaps, for creative scientific problem-solving.

37155

Search skills

Search the agent skills registry