Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Comprehensive collection of 128+ ready-to-use scientific skills for Claude enabling research across biology, chemistry, medicine, genomics, and advanced analysis domains.
.claude/skills/microck-claude-scientific-skills/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-07 | ✗→✓ | ▲ Improved | 29% | 0% |
| case-09 | ✗→✓ | ▲ Improved | 47% | 0% |
| case-10 | ✗→✓ | ▲ Improved | 16% | 0% |
| case-01 | ✓→✓ | ＝ Same ✓ | 47% | 0% |
| case-02 | ✓→✓ | ＝ Same ✓ | 28% | 0% |
A comprehensive collection of 128+ ready-to-use scientific skills that transforms Claude into an AI research assistant capable of executing complex multi-step scientific workflows.
Sequence analysis, single-cell RNA-seq, gene regulatory networks, variant annotation, phylogenetic analysis
Molecular property prediction, virtual screening, ADMET analysis, molecular docking, lead optimization
LC-MS/MS processing, peptide identification, spectral matching, protein quantification
Clinical trials, pharmacogenomics, variant interpretation, drug safety, precision therapeutics
EHR analysis, physiological signal processing, medical imaging, clinical prediction models
DICOM processing, whole slide image analysis, computational pathology, radiology workflows
Deep learning, reinforcement learning, time series analysis, model interpretability, Bayesian methods
Crystal structure analysis, phase diagrams, metabolic modeling, computational chemistry
Astronomical data analysis, cosmological calculations, symbolic mathematics, physics computations
Discrete-event simulation, optimization, metabolic engineering, systems modeling
Each skill within this collection includes:
Explore the scientific-skills/ subdirectory for individual skill implementations and detailed documentation.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | pass→pass | 12,100 | 14,302 | +18% | 1 | 1 | 0% | 1,896 | 2,790 | +47% | 0 | 0 | — |
case-02 | pass→pass | 12,158 | 13,873 | +14% | 1 | 1 | 0% | 2,091 | 2,676 | +28% | 0 | 0 | — |
case-03 | pass→pass | 15,813 | 23,228 | +47% | 1 | 1 | 0% | 2,347 | 3,847 | +64% | 0 | 0 | — |
case-04 | pass→pass | 14,338 | 18,366 | +28% | 1 | 1 | 0% | 2,058 | 3,586 | +74% | 0 | 0 | — |
case-05 | pass→pass | 11,941 | 10,177 | -15% | 1 | 1 | 0% | 1,866 | 2,078 | +11% | 0 | 0 | — |
case-06 | pass→pass | 16,886 | 19,001 | +13% | 1 | 1 | 0% | 2,610 | 3,499 | +34% | 0 | 0 | — |
case-07 | fail→pass | 15,110 | 15,962 | +6% | 1 | 1 | 0% | 2,586 | 3,328 | +29% | 0 | 0 | — |
case-08 | pass→pass | 15,274 | 18,754 | +23% | 1 | 1 | 0% | 2,479 | 3,444 | +39% | 0 | 0 | — |
case-09 | fail→pass | 13,759 | 16,542 | +20% | 1 | 1 | 0% | 2,277 | 3,346 | +47% | 0 | 0 | — |
case-10 | fail→pass | 16,925 | 16,338 | -3% | 1 | 1 | 0% | 2,449 | 2,840 | +16% | 0 | 0 | — |
case-11 | pass→pass | 16,326 | 17,675 | +8% | 1 | 1 | 0% | 2,595 | 3,220 | +24% | 0 | 0 | — |
case-12 | pass→pass | 11,535 | 12,410 | +8% | 1 | 1 | 0% | 1,746 | 2,401 | +38% | 0 | 0 | — |
case-13 | pass→pass | 11,116 | 8,899 | -20% | 1 | 1 | 0% | 1,855 | 2,037 | +10% | 0 | 0 | — |
case-14 | pass→pass | 18,916 | 18,732 | -1% | 1 | 1 | 0% | 2,945 | 3,500 | +19% | 0 | 0 | — |
case-15 | pass→pass | 14,713 | 16,149 | +10% | 1 | 1 | 0% | 2,310 | 2,922 | +26% | 0 | 0 | — |
case-16 | pass→pass | 18,270 | 13,226 | -28% | 1 | 1 | 0% | 2,831 | 2,606 | -8% | 0 | 0 | — |
case-17 | pass→pass | 9,263 | 8,724 | -6% | 1 | 1 | 0% | 1,544 | 2,085 | +35% | 0 | 0 | — |
case-18 | pass→pass | 16,220 | 17,884 | +10% | 1 | 1 | 0% | 2,585 | 3,452 | +34% | 0 | 0 | — |
case-19 | pass→pass | 16,598 | 18,295 | +10% | 1 | 1 | 0% | 2,357 | 3,166 | +34% | 0 | 0 | — |
case-20 | pass→pass | 5,739 | 4,752 | -17% | 1 | 1 | 0% | 1,172 | 1,470 | +25% | 0 | 0 | — |
case-21 | pass→pass | 10,009 | 9,125 | -9% | 1 | 1 | 0% | 1,920 | 2,109 | +10% | 0 | 0 | — |
case-22 | pass→pass | 14,924 | 13,666 | -8% | 1 | 1 | 0% | 2,188 | 2,565 | +17% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted. The headline lift of +14 percentage points is the difference between those two pass rates over the 22 comparable cases.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.