molecular-review-workflow

Generates academic reviews for molecules in diseases using PubMed research. Invoke when user needs biomedical literature review with Vancouver citation format.

Quality

51%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Fix and improve this skill with Tessl

tessl review fix ./scientific-skills/Academic Writing/molecular-review-workflow/SKILL.md

Quality

Content

27%

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

The body is dominated by generic boilerplate that restates process discipline Claude already knows, and it references scripts absent from the bundle. Workflow steps and validation exist but are fragmented across redundant sections, and the executable invocation for the molecule task is incomplete.

Suggestions

Strip the generic boilerplate sections (When to Use, Implementation Details, Validation and Safety Rules, Deterministic Output Rules, etc.) that restate process discipline Claude already knows, keeping only the molecule-review-specific content.

Consolidate the overlapping workflow sections (Workflow Process, Recommended Workflow, Example run plan, Completion Checklist) into one sequenced procedure with explicit validation checkpoints.

Either add the referenced scripts (scripts/pubmed_api.py, scripts/validate_skill.py) to the bundle or remove the broken references, and document the actual command for invoking the skill with disease and molecule arguments.

Dimension	Reasoning	Score
Conciseness	The ~160-line body is padded with generic boilerplate restating process discipline Claude already knows ('Use this skill when the request matches its documented task boundary', 'Execution model: validate the request, choose the packaged workflow'), and redundant sections (Validation Shortcut, Quick Validation, Example run plan, Recommended Workflow) restate the same guidance, matching the verbose level-1 anchor.	1 / 3
Actionability	Concrete commands appear (env-var exports, 'python scripts/pubmed_api.py --help'), but the key invocation showing how to pass the required disease and molecule arguments is missing and the referenced scripts are absent from the bundle, leaving guidance incomplete per the level-2 anchor.	2 / 3
Workflow Clarity	Steps and validation checkpoints are present (5-step Workflow Process, Completion Checklist, 'If validation fails' feedback), but they are fragmented across redundant workflow sections, creating ambiguity about which sequence to follow and capping clarity at level 2.	2 / 3
Progressive Disclosure	No bundle files exist (references/, scripts/, assets/ are absent), yet the body references scripts/pubmed_api.py and scripts/validate_skill.py that are not present, making this a monolithic wall of text with broken references per the level-1 anchor rather than a structured overview pointing to real materials.	1 / 3
	Total	6 / 12 Passed

Description

75%

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 clearly states what the skill does and when to invoke it, and occupies a distinctive biomedical niche. It could enumerate more concrete actions and broaden the natural trigger-term coverage.

Suggestions

List multiple concrete actions (e.g., 'search PubMed, translate terms, format Vancouver citations, generate a structured review') to raise specificity to level 3.

Add common user phrasings like 'literature search', 'systematic review', or 'evidence review' alongside 'biomedical literature review' to broaden trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Quotes 'Generates academic reviews' and 'using PubMed research' name the domain and a couple of actions, but it is a single capability statement rather than a list of multiple concrete actions, so it stops short of the level-3 anchor.	2 / 3
Completeness	It explicitly answers what ('Generates academic reviews for molecules in diseases using PubMed research') and when ('Invoke when user needs biomedical literature review...'), matching the level-3 anchor with an explicit trigger clause.	3 / 3
Trigger Term Quality	The trigger 'Invoke when user needs biomedical literature review with Vancouver citation format' supplies relevant terms but misses common variations users would say such as 'literature search', 'systematic review', or 'evidence review'.	2 / 3
Distinctiveness Conflict Risk	The biomedical molecule-in-disease review niche with PubMed and Vancouver citations is a clear, distinct scope unlikely to trigger for unrelated skills, matching the level-3 anchor.	3 / 3
	Total	10 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
referenced_paths_exist	Referenced path issues: 7 missing	Warning

	Total	14 / 16 Passed

Repository: aipoch/medical-research-skills
Commit: 7cc5680

Reviewed: 3 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.