AI Agent Skills

Marine Research Poster is a image workflow available on Skillry. Its source catalog highlights Create Explainer Graphics · Create Infographic · Cool Gradient · Marine Editorial · Scientific Infographic. Compare the public examples with your brief before choosing this skill.

Optical Bench Diagram is a image workflow available on Skillry. Its source catalog highlights Create Explainer Graphics · Create Diagrams · Technical Isometric · Minimalist · Scientific Editorial. Compare the public examples with your brief before choosing this skill.

Skin Mechanism Visual is a image workflow available on Skillry. Its source catalog highlights Create Explainer Graphics · Create Diagrams · Clinical Editorial · Soft Gradient · Scientific Cutaway. Compare the public examples with your brief before choosing this skill.

A general purpose scientific writer

Turn any AI agent into an AI Scientist. The #1 Agent Skills library for science, used by 160,000+ scientists worldwide. 140 ready-to-use skills plus 100+ scientific data…

A set of ready to use Agent Skills for research, science, engineering, analysis, finance and writing.

This skill should be used when scientists need help with research problem selection, project ideation, troubleshooting stuck projects, or strategic scientific decisions.…

Core skill for the deep research and writing tool. Write scientific manuscripts in full paragraphs (never bullet points). Use two-stage process with (1) section outlines…

Prose-quality rules for writing scientific manuscript text — abstract, introduction, results, discussion. The headline rule is a strict em-dash budget: the long dash (—)…

Diagnose and repair the clarity and logic of manuscript prose, journal-agnostic. Use when a passage is technically correct but hard to follow: buried topic sent

Better Scientific Software Homepage

When a symptom has several plausible causes, rank falsifiable hypotheses and run the cheapest discriminating observation first; prefer least-assumptive survivors only af…

Autonomously improve a real artifact (code, training recipe, agent harness, data pipeline, prompt) against an objective and an evaluator, using Hypothesis Tree Refinemen…

Observe the user's screen via screenpipe, detect repeated research workflows, match them against existing scientific-agent-skills, and draft new skills (or composition r…

Retrieves, versions, and publishes scientific datasets with DataLad and git-annex, and captures computational provenance with datalad run, rerun, and containers-run. Use…

Query documented public database APIs with explicit endpoints, filters, pagination, and provenance. Use when a scientific, regulatory, financial, or other database-backe…