Scan reports · Orchestra-Research/AI-Research-SKILLs
autoresearch: scan report
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… An automated scan of this public skill from Orchestra-Research/AI-Research-SKILLs: security, token cost, spec and clarity, with every finding and its fix.
Result
Verdict
60/100 · grade D
Orchestra-Research/AI-Research-SKILLs/0-autoresearch-skill at 773a529
Spec 17 · Efficiency 15 · Clarity 25 · Security 3 (each out of 25)
Always loaded 141 tokens · on trigger 5,982 · on demand 9,230
sec/hidden-commentwarn · templates/progress-presentation.htmlHTML comment carries instructions the user won't see rendered.sec/hidden-commentwarn · templates/research-log.mdHTML comment carries instructions the user won't see rendered.eff/body-tokenswarn · SKILL.md~5982 tokens load every time this triggers. Aim for under 5,000; split into reference files read on demand.spec/non-portable-keyswarn · SKILL.mdNon-spec frontmatter (version, author, tags). claude.ai and the Skills API reject the upload; move them under `metadata` or drop them.spec/broken-refwarn · SKILL.md:286References findings.md, which isn't in the skill folder.eff/orphan-fileinfo · templates/findings.mdtemplates/findings.md is never mentioned in SKILL.md, so the agent won't know to read it.eff/orphan-fileinfo · templates/research-log.mdtemplates/research-log.md is never mentioned in SKILL.md, so the agent won't know to read it.sec/plain-httpinfo · SKILL.mdLinks over plain http.
Where it comes from
Source
| Fact | Value |
|---|---|
| Repository | Orchestra-Research/AI-Research-SKILLs |
| Skill folder | 0-autoresearch-skill |
| Stars | 13,703 |
| License | MIT |
| Commit scanned | 773a529 |
| Scanned | 2026-10-19 |
| Files | 8 |
ProSkills doesn't host or redistribute this skill. Get it from its repository, and check the license before reusing it. Something wrong here? Open an issue for a rescan or removal.
For maintainers
Badge for the README
If you maintain this skill, this badge shows its score and links to this report. Fix findings and the score moves with the next scan.
[](https://proskills.dev/reports/orchestra-research-autoresearch)
Same repository
More from Orchestra-Research/AI-Research-SKILLs
- awq-quantizationGrade B88/100
- axolotlGrade F53/100
- constitutional-aiGrade B80/100
- deepspeedGrade F59/100
- distributed-llm-pretraining-torchtitanGrade A96/100
- fine-tuning-with-trlGrade A96/100
- grpo-rl-trainingGrade F57/100
- huggingface-accelerateGrade B86/100
- huggingface-tokenizersGrade B88/100
- implementing-llms-litgptGrade A96/100
- lambda-labs-gpu-cloudGrade F63/100
- llama-factoryGrade D68/100
FAQ
Questions
- Is autoresearch safe to install?
- No critical findings, some security notes. The scan covers prompt injection, hidden Unicode, remote code execution and credential access in every text file of the skill. It cannot judge intent, so read any flagged line in context before installing.
- How was this score calculated?
- Four checks of 25 points each: spec, efficiency, clarity and security. Findings take points off the check they belong to, and any critical finding caps the grade at F. The same scanner runs in your browser at proskills.dev/scan.
- Is this report current?
- It was made from commit 773a529 on 2026-10-19. If the skill has changed since, paste the new version into the scanner for a fresh score.
- I wrote this skill. Can I fix the score or have the page removed?
- Fix the findings and push. The reports are rebuilt from GitHub on a schedule, so the next run picks the change up. To have the page removed, open an issue on the ProSkills GitHub repo.
Related
Keep reading
Free tool
Scan your own skill
Paste a SKILL.md or drop a folder. It is scored in your browser and nothing is uploaded.
Want a skill that already passes? Start with a free one.