blockbuster-therapy-predictor

Comprehensive analytics tool for forecasting breakthrough therapeutic technologies by integrating multi-dimensional data sources including clinical development pipelines, intellectual property landscapes, and capital mar.

Quality

55%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./scientific-skills/Evidence Insight/blockbuster-therapy-predictor/SKILL.md

Quality

Content

56%Weight 40%Scale 1-5

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

The body is strong on actionability with concrete commands and output examples and has a reasonably clear sequenced workflow with validation, but it is held back by verbosity from repeated description text, placeholder 'see above' sections, and duplicated boilerplate. Progressive disclosure is adequate but the monolithic inlined content and duplicate References sections leave room for better file splitting.

Suggestions

Remove the three verbatim repeats of the truncated description and the placeholder 'See `## ...` above' stub sections (Key Features, Example Usage, Implementation Details) that point to sections already present.

Deduplicate the prerequisite/install guidance (it appears in both 'Required Python Packages' and 'Prerequisites') and merge the two '## References' sections into one.

Move the large output examples, scoring methodology, and full technology/risk tables into a reference file under `references/`, keeping SKILL.md as a lean overview with one-level-deep links.

Dimension	Reasoning	Score
Conciseness	The ~343-line body is noticeably verbose: the truncated description is repeated verbatim three times (lines 11, 15, 23), several sections are placeholder cross-references ('See `## Features` above', 'See `## Usage` above', 'See `## Workflow` above'), prerequisites are duplicated, and generic boilerplate ('Output Requirements', 'Response Template', 'Input Validation') pads the file.	2 / 5
Actionability	Concrete copy-paste commands are provided throughout (`python scripts/main.py --tech PROTAC,mRNA,CRISPR`, `--output json`, `--threshold 70`, `--save`), backed by a parameters table, detailed console/JSON output examples, a scoring formula, and threshold/recommendation tables.	4 / 5
Workflow Clarity	The Workflow section gives a clear 5-step sequence with a scope-validation checkpoint (step 2) and a fallback path (step 5), plus a Quick Check (`py_compile`) and error-handling guidance; it stops short of an explicit validate->fix->retry loop, leaving a minor gap.	4 / 5
Progressive Disclosure	A real one-level-deep reference exists and is linked (`references/audit-reference.md` at line 335) with a listing section, but the body inlines large blocks (output examples, scoring methodology, full technology/risk/security tables) that could be split out, and there are two duplicated '## References' sections indicating organization gaps.	3 / 5
	Total	13 / 20 Passed

Description

53%Weight 40%Scale 1-5

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

The description conveys a clear specialized purpose but omits any 'Use when...' trigger guidance and is truncated mid-word, leaving completeness and trigger quality at mid-level. It is reasonably distinct within its niche but would benefit from natural trigger phrases and a completed sentence.

Suggestions

Complete the truncated sentence ('capital mar.' -> 'capital market indicators') so the description is grammatically whole.

Add an explicit 'Use when...' clause with natural triggers such as 'blockbuster therapy', 'biotech investment scoring', or 'therapeutic technology forecasting'.

Surface the skill's concrete outputs (Blockbuster Index, rankings, recommendations) so the 'what' lists specific actions rather than only data sources.

Dimension	Reasoning	Score
Specificity	Names the domain ('forecasting breakthrough therapeutic technologies') and a couple of actions ('forecasting', 'integrating multi-dimensional data sources') with concrete data-source categories, but action coverage is limited to integration/forecasting rather than a comprehensive action list.	3 / 5
Completeness	There is a clear 'what' (forecasting therapeutic technologies via multi-source integration) but no 'when' / 'Use when...' trigger clause, which caps completeness at 3 per the rubric guideline; the text is also truncated at 'capital mar.'.	3 / 5
Trigger Term Quality	Relevant specialist keywords ('clinical development pipelines', 'intellectual property landscapes') are present, but natural user phrases like 'blockbuster therapy' and common synonyms are missing and the language leans technical.	3 / 5
Distinctiveness Conflict Risk	The therapeutic-technology forecasting niche is fairly distinct with low conflict risk, though it could overlap with adjacent biotech/market-analysis skills and lacks explicit distinct triggers for a 5.	4 / 5
	Total	13 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

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

	Total	15 / 16 Passed

Repository: aipoch/medical-research-skills
Path: scientific-skills/Evidence Insight/blockbuster-therapy-predictor/SKILL.md
Commit: 63c61d3

Reviewed: 4 hours 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.