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.zipInstalls 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 persistenceKey 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
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 autoresearchcommand surface (hard-deprecated) - You want detached tmux or split-pane launch parity
- You have not decided the validation regime yet
Core contract
- Init chooses validation mode. Pick exactly one:
mission-validator-scriptprompt-architect-artifact
- Persist mode state in
.omx/state/.../autoresearch-state.jsonincluding:validation_modecompletion_artifact_pathmission_validator_commandorvalidator_prompt- optional
output_artifact_path
- 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.
- Direct CLI launch is gone. Use
$deep-interview --autoresearchfor intake and$autoresearchfor 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
- Run
$deep-interview --autoresearchto clarify mission + evaluator. - Materialize
.omx/specs/autoresearch-{slug}/mission.md,sandbox.md, andresult.json. - Start
$autoresearchwith the chosen validation mode stored in mode state. - Let stop-hook / auto-nudge continue until the completion artifact satisfies the chosen validation mode.
- Finish only after the validator artifact is complete.
Migration note
omx autoresearchis hard-deprecated.- No direct CLI launch.
- No tmux split-pane launch.
- No noop-count completion gate.
When not to use it
- →When the user wants the old `omx autoresearch` command surface
- →When the user wants detached tmux or split-pane launch parity
- →When the validation regime has not been decided yet
Limitations
- →Completion is artifact-gated; the loop does not stop because the model says “done”
- →Direct CLI launch is gone; use `$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.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| autoresearch (this skill) | 0 | 3mo | No flags | Advanced |
| auto | 0 | 3mo | No flags | Advanced |
| idea-discovery | 0 | 2mo | Review | Advanced |
| learn-new-things | 0 | 1mo | Review | Advanced |
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.
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
learn-new-things
Abilityai
Continuous learning heartbeat - autonomously researches, extracts insights, and expands knowledge base
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.
deep-research
davidorex
Multi-agent parallel investigation for complex VCV Rack problems
scientific-brainstorming
davila7
Research ideation partner. Generate hypotheses, explore interdisciplinary connections, challenge assumptions, develop methodologies, identify research gaps, for creative scientific problem-solving.