Repository
ARA-Labs/Agent-Native-Research-Artifact agent skills
- skills
- 6
- GitHub stars
- 692
GitHub description: “Research Artifact Protocol for Rigorous and Trustworthy AI Scientists”
- Stars
- 692 (53 forks)
- Licence
- MIT
- Last push
- Oct 2026
- Created
- Mar 2026
- Homepage
- agenticresearch.sh
Install all skills
npx skills add ARA-Labs/Agent-Native-Research-ArtifactAdd --skill <name> for a single skill and -a <agent> to choose the agent (see the agent guides).
Skills in ARA-Labs/Agent-Native-Research-Artifact, ranked
Ranked by score. Sort bymost stars,trending,newest,recently updated
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 1 | Treat an open-ended investigation the way a fuzzer treats a program. | ARA-Labs/ | 692 | — | ~2.4k | Automated safety check: Pass | MIT | yesterday |
| 2 | ARA Submitter. An agent skill from ARA-Labs/Agent-Native-Research-Artifact. | ARA-Labs/ | 692 | — | ~2.4k | Automated safety check: Pass | MIT | yesterday |
| 3 | ARA Seal Level 2: Semantic Epistemic Review. An agent skill from ARA-Labs/Agent-Native-Research-Artifact. | ARA-Labs/ | 692 | — | ~4.7k | Automated safety check: Pass | MIT | yesterday |
| 4 | 4.Compiler Universal ARA Compiler. An agent skill from ARA-Labs/Agent-Native-Research-Artifact. | ARA-Labs/ | 692 | — | ~6.4k | Automated safety check: Pass | MIT | yesterday |
| 5 | ARA World Model — read-only reasoning engine over ONE Agent-Native Research Artifact (ARA), run LOCALLY with the coding agent itself as the LLM (no SDK, no API key). | ARA-Labs/ | 692 | — | ~626 | Automated safety check: Pass | MIT | yesterday |
| 6 | End-of-turn research process recorder with progressive crystallization. | ARA-Labs/ | 692 | — | ~9k | Automated safety check: Pass | MIT | yesterday |
Questions, answered from the data.
What is the best skill in ARA-Labs/Agent-Native-Research-Artifact?
Research Fuzzer from ARA-Labs/Agent-Native-Research-Artifact ranks first of the 6 skills in ARA-Labs/Agent-Native-Research-Artifact listed here, with the highest score: its repository has 692 GitHub stars, its SKILL.md loads about 2.4k tokens and it passes the automated safety check with no findings. Next come Submit Ara and Rigor Reviewer.
Are the skills in ARA-Labs/Agent-Native-Research-Artifact official?
None yet. All 6 skills in ARA-Labs/Agent-Native-Research-Artifact listed here come from community repositories; a skill counts as official when the product's own GitHub organization publishes it.
How do I install all skills from ARA-Labs/Agent-Native-Research-Artifact?
Run npx skills add ARA-Labs/Agent-Native-Research-Artifact in your project: the open-source skills CLI installs the repository's skills into your coding agent's skills folder. To install a single skill, open its page here for the exact command.
How are these skills ranked?
By Skill Navigator score, which combines the GitHub stars of the skill's repository (shared across that repo's skills and discounted for large collections), how many other GitHub owners carry a copy of the skill, and automated SKILL.md quality checks, minus penalties for safety-check warnings and for each further skill from the same repository. Skills that fail the safety check are not listed.