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/discover/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/discover)<a href="https://agentmods.dev/skills/skyllwt/autosci/discover"><img src="https://agentmods.dev/badge/skills/skyllwt/autosci/discover/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/discover"><img src="https://agentmods.dev/badge/skills/skyllwt/autosci/discover.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00091 | $0.02998 |
| Opus 5.5 | $0.00036 | $0.01199 |
| Sonnet 5.5 | $0.00018 | $0.00600 |
| Haiku 4.5 | $0.00009 | $0.00300 |
Grade A, and why
discover scanned grade A with 0 findings 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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/discover
Produce a ranked shortlist of paper candidates from one of four seed modes. Surface them to the user (or to the calling skill) with rationales. Never auto-ingest —
/discoveris a proposal stage,/ingestis the action stage.
Use these local references on demand:
references/seed-modes.md— when to pick anchor / topic / wiki / venue mode and how to translate the user's phrasing into onereferences/ranking-signals.md— whattools/discover.pyscores on and why discovery does not share/init's survey preferencereferences/wiki-dedup.md— how candidates are filtered againstwiki/papers/and what to do with matches
Inputs
--anchor <id>(repeatable): one or more anchor paper IDs (arXiv IDs preferred; S2 paperIds also accepted). Drives the anchor mode — the primary use case, including the post-/ingest"what to read next" flow.--negative <id>(repeatable, optional): IDs to push recommendations away from. Only meaningful with--anchor.--topic "<str>": a topic / query string. Drives the topic mode — lighter alternative to/init's planner.--from-wiki: derive seeds automatically from the wiki's most recently modified papers. Drives the wiki mode.--venue <slug>+--year <int>: venue slug and year (e.g.neurips2024). Drives the venue mode — ranks papers from that venue/year by relevance to the existing wiki.--limit N(optional, default 10): max shortlist size.
Exactly one of --anchor, --topic, --from-wiki, or --venue must be given.
Outputs
.checkpoints/discover-{seed-slug}-{YYYY-MM-DD}.json— full shortlist payload, machine-readable; the seed slug is derived from the first anchor or the topic- a human-readable markdown summary printed to the user with rationale per candidate
wiki/log.md— one append line viatools/research_wiki.py logfor anchor/topic/wiki runs only
/discover does not write anywhere else in wiki/ and does not touch raw/. from-venue is stricter: it does not write to wiki/ at all, including wiki/log.md. Whether to actually pull a candidate into the wiki is the caller's decision (a follow-up /ingest).
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 180 lines · 91 tokens per session scan A c4468afd7289
discover is a skill published in the GitHub repository skyllwt/AutoSci (1,706 stars, last pushed 1mo ago), licensed MIT. It adds 91 tokens to every session and 2,998 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
discover compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| discoverskyllwt/AutoSci | Skill | 1.7k | 1mo ago | MIT | A | 91 | Claude Code |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 103 | Claude Code |