scientific-agent-skills
Turn any AI agent into an AI Scientist. The #1 Agent Skills library for science, used by 250,000+ scientists worldwide. 177 ready-to-use validated skills plus 100+ scientific databases covering biology, chemistry, medicine, and drug discovery. Compatible with Cursor, Claude Code, Codex, Pi, Antigravity, and the open Agent Skills standard.
Runs with mockssource: GitHubhomepagePythonMITcommit 92ace75ac21e
Python, MIT licensed. The project labels itself: agent skills, ai scientist, bioinformatics, chemoinformatics, claude, claude skills, claudecode and clinical research.
scientific-agent-skills runs, with stand-ins for the services it depends on. An Argusic agent installed it in 2.5 minutes and hit 6 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
Repo installs cleanly. All 177 skills pass skills-ref validation. The meta test suite (18/18) passes. 75 skill test suites pass (70 standard + 5 isolated), 81 are empty (expected for scriptless skills). Security scanner works. Skill image generator works.
What the agent ended up with on a clean machine, in its own words. How this is measured
Measured by Argusic on a fresh machine every time. Every number links to its evidence. Argusic Score 92 of 100 (the mean of this project's run scores).
At a glance
Subject data from GitHub, linked at the top of this page, refreshed . Test data by Argusic (CC BY 4.0); every number links to a run page with the full log, the recording, and their sha256 hashes.
What was measured
From the run that decided this verdict. Every line is a recorded value, not an estimate.
What went wrong, in the agent's own words
The agent's own words, worst first, never rewritten into advice.
- pip install uv failed: externally-managed-environment1 minute
- uv sync did not install dev dependency group (pytest, jsonschema, skills-ref)0.5 minutes
- npm install -g uv failed: permissions error0.5 minutes
- System Python 3.12.3 is below pyproject.toml requires-python >=3.13
- 5 test suites failed in non-isolated mode (cellprofiler, geomaster, relion, scientific-slides, scikit-bio)
- skill_scanner.scan() not directly importable from Python
- Install time
- 3 minutes
- Cold machine to finish
- 17 minutes
- Errors hit and fixed
- 6 hit, 6 fixed with no human help
- How the result was proved
- uv sync installed all deps; uv run skills-ref validate on all 177 skills (all valid); uv run python -m pytest tests/_meta -q exited 0 (18 passed); uv run python tests/run_all.py showed 70 suites pass + 5 isolated-only + 81 empty (expected); skill-scanner scan citation-management returned OK SAFE; generate_skill_image.py --dry-run processed correctly
- Model tokens used
- 78,541
- Exact commit tested
- 92ace75ac21e
- Container image
- sha256:cdd920bce783
What was not measured
The other half, so you can see exactly how far this evidence goes. A gap is printed as a gap and never filled in.
- Peak GPU memory
- this ran on a CPU machine, so there was no GPU to sample
- Behaviour over a long run
- each attempt uses the smallest documented settings and a fixed time budget, so this measures whether it runs, not how it holds up under load
- Behaviour against real services
- this run was verified against stand-in services only
The end of the recording
The last lines of the terminal session that decided this verdict, exactly as they were recorded.
}
],
'test_depth': 'tier2_mock',
'verified_how': 'uv sync installed all deps; uv run skills-ref validate on all 177 skills (all …
'final_state': 'Repo installs cleanly. All 177 skills pass skills-ref validation. The meta test…
'notes': 'The repo is a skill distribution package, not a standalone application. Verification …
}
import json; print('ARGUSIC_RESULT:' + json.dumps(result))
\"" in /work/repo
succeeded in 0ms:
tokens used
78,541Replay the whole session, every command from a clean machine to this point.
How it was tested
One agent, one container, no human help. It installs the project the way its own documentation says to, runs it, and fixes what breaks. Everything below is recorded as it happened: the terminal session, the log and the exact commit. The full method.
Strengths and limits
Measured facts, not opinions. How this is written.
What went well
- Recovered from all 6 errors without a human stepping in, which says the failures are documented well enough to solve.
- Licensed MIT, as reported by its host.
What did not, or is not known
- Only reached a running state against stand-in services, so nothing here proves it works against the real ones.
- Took 2.5 minutes to install, slower than the median of the 45 comparable projects Argusic has measured.
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
Of the 46 agent-skills projects Argusic has installed and timed, scientific-agent-skills was the 24th fastest to reach a running state, and 32 of 46 reached one at all.
Also tested, in the same area
Every one of these was installed and run by Argusic on a clean machine. Nothing appears here that was not tested.
Run history
| tested by | attempt | outcome | score | cost USD | when |
|---|---|---|---|---|---|
| Argusic Runner | 1/3 | Runs with mocks | 92.00 | 0.07 |
Topics (from GitHub)
agent-skillsai-scientistbioinformaticschemoinformaticsclaudeclaude-skillsclaudecodeclinical-researchcomputational-biologydata-analysisdrug-discoverygenomicsmaterials-sciencemetabolomicsproteomicsscientific-computingscientific-visualization
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/scientific-agent-skills)Questions
- Does scientific-agent-skills run?
- scientific-agent-skills runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 3 minutes, hitting 6 errors on the way, and recorded the session.
- How did Argusic test scientific-agent-skills?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 92ace75ac21e. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test scientific-agent-skills?
- The run that produced this verdict cost $0.07: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does scientific-agent-skills take to install?
- 2.5 minutes in the run that decided this verdict, from a clean machine to a running state. That is one measured attempt, not an average.
- Does scientific-agent-skills need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing scientific-agent-skills?
- 6 things broke in the recorded run, and 6 were fixed without human help. Each one, and the time it cost, is listed on this page.
- How does scientific-agent-skills compare with the alternatives?
- Of the 46 agent-skills projects Argusic has installed and timed, scientific-agent-skills was the 24th fastest to reach a running state, and 32 of 46 reached one at all.
- Where is the evidence for scientific-agent-skills?
- The recorded run is on this page, each linking to its full log and terminal recording, stored with a sha256 fingerprint so it cannot be quietly altered.