CsSAFE
🔬 A curated collection of 23,000+ agent skills for empirical research across 8 social science disciplines. | 精选 23,000+ AI Agent 技能库,覆盖8大社会科学学科的实证研究。CoPaper.AI 20分钟完成一篇可复现的规范实证论文,并支持用户上传 Skills。-- Maintained by CoPaper.AI from Stanford REAP.
Overview
🔬 A curated collection of 23,000+ agent skills for empirical research across 8 social science disciplines. | 精选 23,000+ AI Agent 技能库,覆盖8大社会科学学科的实证研究。CoPaper.AI 20分钟完成一篇可复现的规范实证论文,并支持用户上传 Skills。-- Maintained by CoPaper.AI from Stanford REAP.
e1ba289846fdOBSERVED · 2026-10-08Install
Commands as the repository documents them. They are shown, not run.
git clone https://github.com/graphdeco-inria/gaussian-splatting
pip install -r requirements.txt
Host compatibility
What the documentation claims. We have not run a compatibility test.
| Host | Status | Notes |
|---|---|---|
| codex | mentioned | |
| openclaw | mentioned |
What it tells the agent
The instruction file, verbatim from the audited commit — this is the text the model reads, and the surface the audit's instruction layer examines. Quoted here so you can judge it without cloning anything.
--- name: cs-skills description: "10 computer science skills. Trigger: algorithms, systems research, software engineering, security papers. Design: theory, complexity analysis, code-centric research, and security methods." --- # Computer Science — 10 Skills Select the skill matching the user's need, then `read` its SKILL.md. | Skill | Description | |-------|-------------| | [ai-security-papers-guide](./ai-security-papers-guide/SKILL.md) | AI security papers from top-4 security conferences | | [algorithms-complexity-guide](./algorithms-complexity-guide/SKILL.md) | Analyze algorithm complexity and computational efficiency for research | | [code-llm-papers-guide](./code-llm-papers-guide/SKILL.md) | Survey and paper collection on LLMs for code generation | | [dblp-api](./dblp-api/SKILL.md) | Search computer science publications, authors, and venues via DBLP | | [distributed-systems-guide](./distributed-systems-guide/SKILL.md) | Distributed systems design patterns and analysis for CS research | | [formal-verification-guide](./formal-verification-guide/SKILL.md) | Formal methods, theorem proving, and model checking for CS research | | [gaussian-splatting-papers-guide](./gaussian-splatting-papers-guide/SKILL.md) | Curated papers and resources for 3D Gaussian Splatting | | [llm-aiops-guide](./llm-aiops-guide/SKILL.md) | Papers on LLMs for IT operations and AIOps research | | [software-engineering-research](./software-engineering-research/SKILL.md) | Guide to software engineering research topics and methodologies | | [software-heritage-api](./software-heritage-api/SKILL.md) | Archive and retrieve source code history via Software Heritage API |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | NA |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- none-observed
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (0)
No findings outside the package's declared scope.
Gates applied: no_behavioural_pass.
e1ba289846fdfull audit observations/trust-audit/skill/brycewang-stanford__cs.json · Report an issue / request a re-scanAudit history
Every audit this skill has had.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-08 | e1ba289846fd | SAFE | B | 89 | first audit |
Questions
What does the Cs skill do?
🔬 A curated collection of 23,000+ agent skills for empirical research across 8 social science disciplines. | 精选 23,000+ AI Agent 技能库,覆盖8大社会科学学科的实证研究。CoPaper.AI 20分钟完成一篇可复现的规范实证论文,并支持用户上传 Skills。-- Maintained by CoPaper.AI from Stanford REAP.
Is Cs safe to install?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean skill reads B.
What can Cs access on my machine?
The audit observed no filesystem, network or shell use at all in its source.
What do I need installed to use Cs?
Its own instructions reference read. Dependencies are pinned to exact versions.
Which assistants does Cs work with?
Its documentation mentions codex and openclaw. That is what the text claims, not a compatibility test we ran.
How current is this page?
The grade is for one exact copy of the source (e1ba289846fd), read on 2026-10-08. The repository is watched, and a new audit runs when it changes — this is the first audit.