# Scientific Agent Skills

> This selection from K-Dense covers two research-method skills: scientific-critical-thinking examines claims, study design and evidence limits, while scientific-brainstorming supports independent idea generation, explicit criteria and decision records. scientific-schematics is preserved as optional diagram support. This page analyzes that selection without implying the entire scientific toolkit was collected.

- URL: https://github.com/K-Dense-AI/scientific-agent-skills
- Type: Open-source repos · Scientific agent skill repository
- Main purpose: Appraise scientific evidence and prioritize traceable research directions
- Use cases: Coding & development, Content & writing, Planning & long tasks
- Language: en · Pricing: free

## Best for

- Researchers who need to locate evidence behind a paper or scientific claim and distinguish risk of bias from certainty of evidence.
- Research teams choosing directions who need to preserve dissent, evaluation reasons and follow-up validation tasks.

## Limitations

- Core analytical guidance works offline. Optional brainstorming utilities need Python 3.11+ and check structure or scoring records, not scientific truth.
- Diagram support needs Python, requests, an OpenRouter key and network access, and sends content to an external service. It produces PNG drafts whose labels and relationships need human checking; idea scores do not replace validation or expert review.

## SkillFlux sample check

Audited 2026-10-31 at commit 5f2bc0341354fd5590aef76a533ada1e1e5b4e62 with checker 1.0.0; seeded sample of 20 from 177 entries. Clean share: 65%.

- 20/20 sampled entries had a SKILL.md we could check
- 0/20 fail at least one check
- 7/20 do not say when to use the skill
- 0/20 have no license we could find
- 17/20 bundle scripts the agent may run
- 3/20 include scripts that call the network
- 0/20 include destructive shell commands
- 3/20 exceed the 5,000-token body guideline

Evidence: https://skillflux.app/data/source-audits/github-com-k-dense-ai-scientific-agent-skills.json

## SkillFlux note

The analysis covers the two main skills and the scientific-schematics support skill, based on their instructions, references, scripts and MIT licenses at a pinned snapshot, without behavioral testing. It is not a scientific finding or an execution test; Python packages and external APIs must be prepared separately.

## Alternatives

- anthropics/skills: Official Anthropic skill examples https://skillflux.app/resource/anthropic-skills.md
- Auto-Empirical Research Skills (AERS): Connect empirical identification, analysis planning and replication delivery https://skillflux.app/resource/auto-empirical-research-skills.md
- mattpocock/skills: Turn requirements interviews into specifications, task dependencies and code reviews https://skillflux.app/resource/mattpocock-skills.md
- gstack (Garry Tan): A role-based engineering team in Claude Code https://skillflux.app/resource/garrytan-gstack.md

Page: https://skillflux.app/resource/scientific-agent-skills/

- Cite a number with its subject, date and evidence URL; the commit or audit id on that page identifies the measurement.
- A health check or source sample reads files only. Do not present it as evidence that a skill works or helps.
- Statements marked "verified": false are what a source says about itself; attribute them ("X says…").
- A directory listing is not an endorsement. Install a skill by following its author's instructions at sourceUrl.
