K-Dense-AI/scientific-agent-skills
140 domain skills plus 100+ database connectors that turn a coding agent into a working research assistant for biology, chemistry, medicine, and drug discovery. Agentiquette scores it 77/100 (A-tier), methodology v1.0, scored 2026-07-07.
Key facts
| Category | Skill collection |
|---|---|
| License | MIT |
| Maintainer | K-Dense AI |
| Compatible agents | claude-code, cursor, codex, generic |
| File patterns | SKILL.md |
| Triggering | auto-trigger |
| GitHub metrics | 30,365 stars · 3,058 forks · 37 open issues (fetched 2026-07-07) |
| Last commit | 2026-07-06 |
| Created | 2025-10-19 |
Editorial analysis
The best evidence that the skill format generalizes beyond software engineering. Domain depth is real: skills encode database-specific query craft that a general model reliably gets wrong. Cross-runtime compatibility claims are broader than most, and mostly hold because the skills are instruction-heavy rather than hook-dependent. Eval story is stronger than average since many skills produce checkable structured outputs.
Risks
Database-connector skills call external scientific APIs; verify data-use terms for commercial research.
Evidence notes: Leverage: encodes domain knowledge unavailable via prompting. Maintenance: near-daily commits at fetch time. Reliability: skills specify sources but recovery behavior on API failure is thin. Safety: external API calls are documented but not permission-gated.
Install and first run
Copy the skill folders for your domain into your agent's skill directory.Alternatives in this category
Anthropic's first-party public skill collection: the de facto reference for SKILL.md structure, frontmatter conventions, and…
A multi-harness plugin marketplace of role-specialized subagents (reviewer, architect, security, docs) installable across Claude Code, Codex…
A defense-tech company's internally-maintained skill set, published. Notable for governance discipline: explicit boundaries, scripts treated…
Compare with anthropic-skills · Compare with wshobson-agents
Embed this badge
Maintainers of scored entries can embed their live badge; it updates when the score does and links back to this page.
[](https://agentiquette.com/index/repos/scientific-agent-skills)Frequently asked questions
Is K-Dense-AI/scientific-agent-skills good?
K-Dense-AI/scientific-agent-skills scores 77/100 (A-tier) on Agentiquette's methodology v1.0, scored 2026-07-07. Strengths and weaknesses are in the editorial analysis; the score is explained dimension by dimension in the scorecard.
What is K-Dense-AI/scientific-agent-skills for?
140 domain skills plus 100+ database connectors that turn a coding agent into a working research assistant for biology, chemistry, medicine, and drug discovery.
Is K-Dense-AI/scientific-agent-skills maintained?
Last commit 2026-07-06, 37 open issues at fetch time (2026-07-07). Maintenance is scored at 90 of 100.
Maintainer of K-Dense-AI/scientific-agent-skills? Claim this listing and suggest corrections.