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.

2.96x

Quality

75%

Does it follow best practices?

Impact

95%

2.96x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./scientific-skills/Evidence insights/blockbuster-therapy-predictor/SKILL.md

Quality

Discovery

100%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

This is a strong skill description that clearly defines a specialized niche in biotechnology platform analysis. It excels at specificity by naming concrete platforms and analysis methods, includes explicit trigger guidance, and occupies a distinctive domain that minimizes conflict risk with other skills.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions: 'Predict which early-stage biotechnology platforms...have the highest potential', 'Analyzes clinical trial progression, patent landscape maturity, and venture capital funding trends', 'generate investment and R&D prioritization scores'. Names specific platforms (PROTAC, mRNA, gene editing).	3 / 3
Completeness	Clearly answers both what (predict biotech platform potential, analyze trials/patents/funding, generate scores) AND when with explicit 'Trigger when:' clause specifying technology investment potential, platform selection, or therapeutic modality comparison.	3 / 3
Trigger Term Quality	Includes natural keywords users would say: 'technology investment potential', 'platform selection', 'therapeutic modality comparison', plus domain-specific terms like 'PROTAC', 'mRNA', 'gene editing', 'blockbuster therapies', 'clinical trial', 'venture capital funding'.	3 / 3
Distinctiveness Conflict Risk	Highly distinctive niche combining biotechnology platforms, clinical trials, patent analysis, and VC funding trends. The specific domain (early-stage biotech) and output type (investment/R&D prioritization scores) make it unlikely to conflict with other skills.	3 / 3
	Total	12 / 12 Passed

Implementation

50%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The skill provides excellent actionable CLI documentation with concrete examples and clear parameter tables, but is severely bloated with unnecessary sections (security checklists, risk assessments, lifecycle status) that Claude doesn't need. The content would be far more effective at 1/3 the length, focusing only on usage patterns and the scoring methodology.

Suggestions

Remove boilerplate sections (Risk Assessment, Security Checklist, Lifecycle Status, Evaluation Criteria, Prerequisites) that don't help Claude execute the skill

Move the full technology table and detailed scoring methodology to separate reference files, keeping only a brief summary in the main skill

Add a validation step showing how to verify the output is correct (e.g., checking JSON schema, validating score ranges)

Remove the disclaimer and limitations sections - Claude can add appropriate caveats contextually without being told

Dimension	Reasoning	Score
Conciseness	Extremely verbose with extensive boilerplate sections (Risk Assessment, Security Checklist, Lifecycle Status, Evaluation Criteria) that add no value for Claude. Explains obvious concepts and includes redundant information like listing 'dataclasses' and 'enum' as dependencies (Python stdlib).	1 / 3
Actionability	Provides fully executable CLI commands with clear parameter documentation, concrete examples with expected outputs, and copy-paste ready bash commands for various use cases.	3 / 3
Workflow Clarity	Usage examples are clear but there's no validation workflow for verifying outputs or handling errors. The skill describes what to run but not how to verify results or troubleshoot failures.	2 / 3
Progressive Disclosure	References external files (references/) but the main document is a monolithic wall of text with sections that should be separate (full parameter tables, all supported technologies, security checklists). The structure exists but content is not appropriately split.	2 / 3
	Total	8 / 12 Passed

Validation

90%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 10 / 11 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	10 / 11 Passed

Repository: aipoch/medical-research-skills
Commit: ca9aaa4

Reviewed: 27 days ago

Table of Contents

Discovery Implementation Validation

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.