blockbuster-therapy-predictor
Predict which early-stage biotechnology platforms (PROTAC, mRNA, gene editing, etc.) have the highest potential to become blockbuster therapies. Analyzes clinical trial progression, patent landscape maturity, and venture capital funding trends to generate investment and R&D prioritization scores. Trigger when: User asks about technology investment potential, platform selection, or therapeutic modality comparison.
Install with Tessl CLI
npx tessl i github:aipoch/medical-research-skills --skill blockbuster-therapy-predictor79
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillValidation for skill structure
Evaluation results
90%
65%Biotech Investment Portfolio Screening
Threshold filtering and JSON report generation
Correct script invocation
50%
100%
Threshold flag used
0%
100%
JSON output flag used
0%
100%
Save flag used
0%
80%
high_potential_report.json exists
100%
100%
JSON structure correct
25%
100%
Rankings contain required fields
25%
100%
Only high-threshold techs included
100%
100%
Strongly Recommended threshold correct
0%
100%
Recommended threshold correct
0%
100%
Watch threshold correct
0%
0%
Without context: $0.6175 · 2m 46s · 28 turns · 1,808 in / 9,906 out tokens
With context: $0.3924 · 1m 12s · 18 turns · 145 in / 3,346 out tokens
97%
49%Nucleic Acid Platform Head-to-Head Analysis
Technology filtering and component score interpretation
Correct tech names
50%
100%
Tech filter applied
30%
100%
Quick mode used
0%
100%
Save flag used
0%
87%
JSON file present
100%
100%
Three platforms in JSON
100%
100%
Formula weights correct
0%
100%
Three component scores listed
100%
100%
Correct script entry point
87%
75%
JSON rankings fields present
0%
100%
No extra platforms
100%
100%
Without context: $0.6903 · 3m 13s · 37 turns · 44 in / 10,173 out tokens
With context: $0.5373 · 1m 38s · 22 turns · 151 in / 4,295 out tokens
99%
74%R&D Prioritization Study: Full Technology Landscape
Full analysis execution and scoring methodology
Correct script invocation
100%
87%
JSON output flag
0%
100%
Save flag with correct filename
0%
100%
JSON file present
100%
100%
All 10 platforms in JSON
40%
100%
Market Potential weight
0%
100%
Maturity weight
0%
100%
Momentum weight
0%
100%
Strongly Recommended tier described
0%
100%
Watch tier described
0%
100%
Cautious tier described
0%
100%
Timeline fields used
70%
100%
Without context: $0.5911 · 3m 12s · 26 turns · 255 in / 10,613 out tokens
With context: $0.6163 · 1m 51s · 23 turns · 151 in / 5,931 out tokens
- Evaluated
- Agent
- Claude Code
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.