Skills
autoresearch-skill
by wjgoarxiv
Autonomous research loop skill for LLM agents — inspired by Karpathy's autoresearch. Define a goal, let the agent iterate.
Our verdict
We have not reviewed autoresearch-skill 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 autoresearch-skill
autoresearch-skill is an autonomous research loop skill for LLM agents, inspired by Karpathy's autoresearch. It lets users define a goal and the agent iterates through research steps automatically. Written in Python and distributed via GitHub.
Best for
Developers seeking a minimal autonomous research loop to embed in LLM agent evaluations.
Use cases
- Automating multi-step research tasks from a single user-defined goal
- Building LLM agents that require iterative information gathering
- Prototyping evaluation scenarios that stress agent autonomy
Notes
41 stars on GitHub. Last updated 2026-06-21. Licensed MIT.
Pros
- Simple goal-driven loop reduces manual orchestration
- Python-centric design integrates with existing agent tooling
- Open-source with a clear inspirational lineage for credibility
Cons
- Small community with 41 stars indicates limited adoption or validation
- No documentation or usage examples provided
- Not a full framework; only a skill that may need integration work
Key facts
What we have checked
- Days since the last commit
- 145
- GitHub forks
- 5
- GitHub stars
- 42
- Open issues
- 0
- 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 autoresearch-skill is growing
40 to 42
Health and security
Is autoresearch-skill looked after, and what do its setup files show
Health score
33 out of 100
| Part | Points | What we saw |
|---|---|---|
| Recent activity | 19.7 of 30 | Last push 145 days ago |
| Releases | 0 of 15 | 0 releases in 90 days |
| Issue replies | Not counted | The latest check has no issue response reading (fewer than 3 measured issues, or issues switched off) |
| Maintainer | 0 of 15 | Owned by a single user |
| Official source | Not counted | MCP servers only |
Security check static checks
90 out of 100
- Medium Tells the agent to skip permission or approval prompts: CONTRIBUTING.md, line 57.
- Note 26 files were not read (over 512 KB, or past the 60 file cap): references/visualization-guide.md, .github/workflows/validate.yml, examples/code-optimization/final_report.md and more.
- Note 1 of 1 packages are not pinned to one version, so only the malicious packages list was checked for them, not version advisories.
Alternatives
Alternatives to autoresearch-skill
| Record | Type | How we know | Checked |
|---|---|---|---|
| autoresearch-universalAlternative to this | Skill | Matched from the listing text |
Compare
Compare autoresearch-skill 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.
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.