Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/Rheinmir/setupnpx agentmods add skills/rheinmir/setup/dym-scientific-agent-skills-cai-dat-skillsWrote 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/rheinmir/setup/dym-scientific-agent-skills-cai-dat-skills)<a href="https://agentmods.dev/skills/rheinmir/setup/dym-scientific-agent-skills-cai-dat-skills"><img src="https://agentmods.dev/badge/skills/rheinmir/setup/dym-scientific-agent-skills-cai-dat-skills/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/rheinmir/setup/dym-scientific-agent-skills-cai-dat-skills"><img src="https://agentmods.dev/badge/skills/rheinmir/setup/dym-scientific-agent-skills-cai-dat-skills.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00075 | $0.01923 |
| Opus 5.5 | $0.00030 | $0.00769 |
| Sonnet 5.5 | $0.00015 | $0.00385 |
| Haiku 4.5 | $0.00007 | $0.00192 |
Grade B, and why
dym-scientific-agent-skills-cai-dat-skills 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 yesterday.
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.
Enumerates other installed skillsmediumAgent snooping
Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.
ls .claude/skills/ .agents/skills/ 2>/dev/null How it starts
The opening of the file, as written. The whole thing — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: dym-scientific-agent-skills-cai-dat-skills — Cài Scientific Agent Skills vào agent của bạn
Vì sao dùng: đưa một subset trong 163 skill khoa học vào agent (Claude Code / Cursor / Codex / Gemini CLI / Antigravity…) để nó có quy trình sẵn cho bioinformatics, cheminformatics, tra cứu database, viết báo khoa học…
Sinh ra cái gì: các thư mục <skill-name>/SKILL.md (kèm references/, scripts/, assets/ nếu có) nằm trong thư mục skill của host, cộng metadata truy vết được chèn vào frontmatter.
⚠️ Chạy 02-tham-dinh-truoc-khi-cai.md trước. Chính repo khuyến cáo không cài cả bộ, và 16/163 skill hiện mang finding CRITICAL/HIGH trong báo cáo quét của họ.
Đường A — npx skills (khuyến nghị, hỗ trợ chọn subset)
Xem repo có gì mà không cài gì:
npx -y skills add K-Dense-AI/scientific-agent-skills --list
Đã chạy thật: in Found 163 skills rồi liệt kê từng skill kèm description. Lệnh này clone repo vào cache tạm, không ghi vào thư mục skill.
Cài đúng vài skill bạn cần (đây là cách nên dùng):
# project scope (mặc định) — cài vào dự án hiện tại
npx -y skills add K-Dense-AI/scientific-agent-skills -s "depmap,paper-lookup,database-lookup" -y
# user scope — dùng được ở mọi dự án
npx -y skills add K-Dense-AI/scientific-agent-skills -g -s "depmap,paper-lookup" -y
# chỉ định host cụ thể
npx -y skills add K-Dense-AI/scientific-agent-skills -a claude-code -s "depmap" -y
Cờ đã kiểm chứng qua npx [email protected] --help:
| Cờ | Ý nghĩa |
|---|---|
-s, --skill <skills> |
chọn skill (dùng '*' cho tất cả) |
-a, --agent <agents> |
chọn host (dùng '*' cho tất cả) |
-g, --global |
user scope thay vì project scope |
-l, --list |
chỉ liệt kê, không cài |
--copy |
copy file thay vì symlink vào thư mục agent |
-y, --yes |
bỏ qua prompt |
--all |
viết tắt của --skill '*' --agent '*' -y — đừng dùng với repo này |
Muốn thử một skill mà không cài gì cả:
npx -y skills use K-Dense-AI/scientific-agent-skills@depmap
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.
- yesterday First seen · 146 lines · 75 tokens per session scan B 2acf11aefb85
dym-scientific-agent-skills-cai-dat-skills is a skill published in the GitHub repository Rheinmir/setup (11 stars, last pushed 20d ago), licensed MIT. It adds 75 tokens to every session and 1,923 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it B with 1 finding (enumerates other installed skills). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-11-07.
dym-scientific-agent-skills-cai-dat-skills compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| dym-scientific-agent-skills-cai-dat-skillsRheinmir/setup | Skill | 11 | 20d ago | MIT | B | 75 | Claude Code |
| instrument-data-to-allotropeanthropics/knowledge-work-plugins | Skill | 35k | yesterday | Apache-2.0 | A | 123 | Claude Code |
| matlabK-Dense-AI/scientific-agent-skills | Skill | 56k | 6d ago | MIT | A | 44 | Claude Code |
| exploratory-data-analysisK-Dense-AI/scientific-agent-skills | Skill | 56k | 6d ago | MIT | A | 83 | Claude Code |
| phylogeneticsK-Dense-AI/scientific-agent-skills | Skill | 56k | 6d 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 | today | Apache-2.0 | A | 205 | Claude Code |