AutoSci is an AI research platform organized around a wiki, with an agent that supports stages of scientific work such as reading, experimentation, writing, and retaining knowledge across projects. It is for people building or using AI-assisted research workflows, with Claude Code, Codex, and OpenCode adaptations available. The catalogue add-ons extend those agent-specific workflows.
Borrowing it
Nothing to install: this file belongs to skyllwt/AutoSci. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/skyllwt/AutoSci/main/.claude/skills/research/SKILL.mdgit clone --depth 1 https://github.com/skyllwt/AutoSciWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/skyllwt/autosci/research)<a href="https://agentmods.dev/skills/skyllwt/autosci/research"><img src="https://agentmods.dev/badge/skills/skyllwt/autosci/research/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/skyllwt/autosci/research"><img src="https://agentmods.dev/badge/skills/skyllwt/autosci/research.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high System Prompt Leakage · line 287 Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.Fix: Remove any instructions that reveal, print, or output system prompts or internal rules. System instructions should never be exposed to end users.
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00029 | $0.05953 |
| Opus 5.5 | $0.00012 | $0.02381 |
| Sonnet 5.5 | $0.00006 | $0.01191 |
| Haiku 4.5 | $0.00003 | $0.00595 |
Grade B, and why
research scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Asks the agent to reveal its instructionsmediumSystem prompt leakage
Directions to print, repeat or translate the system prompt extract configuration the operator did not intend to expose.
4. Output instructions then **end current session**: How it starts
The opening of the file, as written. The whole thing — 553 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/research
End-to-end research orchestrator that composes all skills into a complete research workflow. Stage 0 (Bootstrap) + 5 Stages + 2 Human Gates, covering the full pipeline from empty wiki to paper submission. Zero-friction entry: if the wiki is empty, Bootstrap is triggered automatically (search + auto-ingest 5 papers); no need to run /init manually. Every Gate and Stage saves progress to
wiki/outputs/pipeline-progress.md, supporting cross-session recovery.Stage 3 is non-blocking: experiments are deployed and control returns immediately (
--automode automatically sets up a CronCreate to monitor every 30 minutes). When all experiments finish, Stage 4 is triggered automatically. Use/exp-statusat any time to check progress.
--automode skips manual confirmation (automatically selects the top-1 idea).--skip-paperruns the research without writing a paper.
Inputs
direction: research direction description or path to aRESEARCH_BRIEF.mdfile- Text form: one-sentence description of the research direction (e.g. "sparse LoRA for edge devices")
- File form: structured RESEARCH_BRIEF.md (containing domain, constraints, target venues)
--auto(optional): fully automatic mode; Gate 1 auto-selects top-1 idea, Gate 2 auto-continues, Stage 3b auto-creates CronCreate--start-from <stage>(optional): resume execution from the specified stage- Valid values:
stage1,stage2,stage3,stage3-collect,stage3-check,stage4,stage5 stage3-collect: skip deploy, go directly to Stage 3c (collect results from already-deployed experiments)stage3-check: check experiment status only (equivalent to/exp-status --pipeline {slug}), do not continue execution- Requires
wiki/outputs/pipeline-progress.mdto exist
- Valid values:
--skip-paper(optional): run research only (Stages 1-4), skip paper writing (Stage 5), but still run /exp-eval (Stage 4)--venue(optional): target conference (ICLR / NeurIPS / ICML / ACL / CVPR), passed to /paper-plan
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2mo ago First seen · 553 lines · 29 tokens per session scan B 6d57ac518758
research is a skill published in the GitHub repository skyllwt/AutoSci (1,706 stars, last pushed 1mo ago), licensed MIT. It adds 29 tokens to every session and 5,953 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it B with 1 finding (asks the agent to reveal its instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
research compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| researchskyllwt/AutoSci | Skill | 1.7k | 1mo ago | MIT | B | 29 | Claude Code |
| instrument-data-to-allotropeanthropics/knowledge-work-plugins | Skill | 35k | 2d ago | Apache-2.0 | A | 123 | Claude Code |
| exploratory-data-analysisK-Dense-AI/scientific-agent-skills | Skill | 56k | 4d ago | MIT | A | 83 | Claude Code |
| matlabK-Dense-AI/scientific-agent-skills | Skill | 56k | 4d ago | MIT | A | 44 | Claude Code |
| phylogeneticsK-Dense-AI/scientific-agent-skills | Skill | 56k | 4d ago | MIT | A | 71 | Claude Code, Codex |
| research-engineerdavila7/claude-code-templates | Skill | 33k | today | MIT | A | 43 | Claude Code, Codex |
| mapping-to-snomedmaziyarpanahi/openmed | Skill | 5.8k | yesterday | Apache-2.0 | A | 205 | Claude Code |