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/edit/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/edit)<a href="https://agentmods.dev/skills/skyllwt/autosci/edit"><img src="https://agentmods.dev/badge/skills/skyllwt/autosci/edit/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/edit"><img src="https://agentmods.dev/badge/skills/skyllwt/autosci/edit.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 | $0.00016 | $0.00429 |
| Opus 5.5 | $0.00006 | $0.00172 |
| Sonnet 5.5 | $0.00003 | $0.00086 |
| Haiku 4.5 | $0.00002 | $0.00043 |
Grade A, and why
edit 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.
What it actually says
/edit
Add or remove raw sources, or update wiki content, per user request.
Trigger
User manual: /edit <user request>
Inputs
User request, for example:
- "Download this paper to raw/papers/"
- "Delete raw/papers/xxx.pdf"
- "Update the SOTA tracker in topics/efficient-llm-adaptation"
- "Add a new variant to concepts/lora"
Outputs
Updated wiki files, index.md, log.md
Steps
STEP 1: Parse User Intent
- Add raw sources:
- If the user provides a local path: copy to the corresponding directory under
raw/ - If the user provides an arXiv URL: download to
raw/papers/ - If the user provides a web URL: fetch content with markdownify and save to
raw/web/
- If the user provides a local path: copy to the corresponding directory under
- Delete raw sources:
- Confirm then execute deletion
- Update wiki:
- Read the relevant pages and modify content per user instructions
STEP 2: Execute Updates
- Newly added raw sources can later be incorporated into the wiki via
/ingest - Direct wiki modifications: update the specified fields/content in specific pages per user instructions
- When writing forward links, simultaneously write reverse links
STEP 3: Update Navigation
EDIT wiki/index.md: update relevant entriesAPPEND wiki/log.md:## [{date}] update | {description}
STEP 4: Report
- List all changes made
- Suggest follow-up actions (e.g. ingest newly added raw sources if applicable)
Constraints
raw/is read-only for existing files (this skill may add files toraw/, but must not modify existing ones)- Wiki modifications must follow template structure
- Bidirectional links must be kept in sync
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 · 61 lines · 16 tokens per session scan A d6ef90f3da81
edit is a skill published in the GitHub repository skyllwt/AutoSci (1,706 stars, last pushed 1mo ago), licensed MIT. It adds 16 tokens to every session and 429 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.
edit compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| editskyllwt/AutoSci | Skill | 1.7k | 1mo ago | MIT | A | 16 | Claude Code |
| imagegenopenai/codex | Skill | 133k | today | 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 |