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/refine/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/refine)<a href="https://agentmods.dev/skills/skyllwt/autosci/refine"><img src="https://agentmods.dev/badge/skills/skyllwt/autosci/refine/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/refine"><img src="https://agentmods.dev/badge/skills/skyllwt/autosci/refine.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
SkillSpector: 1 finding, up to low
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 →
- low Excessive Agency · line 201 Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.Fix: Limit the skill's scope to its documented purpose. Remove instructions that enable the agent to perform actions outside its stated functionality.
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 | $0.00031 | $0.02442 |
| Opus 5.5 | $0.00012 | $0.00977 |
| Sonnet 5.5 | $0.00006 | $0.00488 |
| Haiku 4.5 | $0.00003 | $0.00244 |
Grade A, and why
refine 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 — 233 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/refine
General-purpose multi-round iterative improvement loop for any research artifact (idea, proposal, experiment plan, paper draft). Each round calls /review for structured feedback → parses actionable items → Claude fixes the artifact → updates wiki entities → re-reviews, until the score reaches the target or the maximum rounds are exhausted. Outputs an improvement history and the final review score.
Inputs
artifact: the artifact to improve, one of:- slug of a wiki page (searched in ideas/experiments/methods/outputs/)
- file path (e.g.
wiki/outputs/paper-draft-v1.md)
--max-rounds N(optional, default 4): maximum iteration rounds--target-score N(optional, default 8): target review score (1-10); stop when reached--difficulty(optional, defaulthard): difficulty level passed to /review--focus(optional): review focus passed to /review
Outputs
- Improved artifact (wiki page or file, updated in place)
- Wiki entity updates (if review finds ideas/methods needing strengthening or identifies gaps)
- REFINE_REPORT (output to terminal):
- Score trajectory across all rounds
- Cumulative list of fixed issues
- Final review score and verdict
- Unresolved issues (if any)
Wiki Interaction
Reads
wiki/ideas/*.md— if artifact is an ideawiki/experiments/*.md— if artifact is an experiment planwiki/methods/*.md— methods referenced by the reviewwiki/papers/*.md— papers referenced by the reviewwiki/outputs/*.md— if artifact is a paper draft or outputwiki/graph/context_brief.md— global context passed to /reviewwiki/graph/open_questions.md— check whether new gaps need recording
Writes
wiki/ideas/{slug}.md— if artifact is an idea, fix issues found by reviewwiki/experiments/{slug}.md— if artifact is an experiment planwiki/methods/{slug}.md— if review flags a method gap (e.g. missing source_papers, weak Procedure)wiki/outputs/*.md— if artifact is a paper draft or outputwiki/graph/edges.jsonl— if new relationships are discovered during fixeswiki/graph/context_brief.md— rebuild after each round if wiki changes were madewiki/graph/open_questions.md— rebuild after each round if wiki changes were madewiki/log.md— append operation log
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 · 233 lines · 31 tokens per session scan A da78a43b202e
refine is a skill published in the GitHub repository skyllwt/AutoSci (1,706 stars, last pushed 1mo ago), licensed MIT. It adds 31 tokens to every session and 2,442 once invoked, about $0.0001 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.
refine compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| refineskyllwt/AutoSci | Skill | 1.7k | 1mo ago | MIT | A | 31 | 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 |