CtrlK
BlogDocsLog inGet started
Tessl Logo

molecular-review-workflow

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

54

Quality

62%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

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

Quality

Content

42%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 skill-specific core (Inputs, Workflow Process, Quality Rules, env setup) is sound, but it is buried under generic boilerplate, lacks a copy-paste invocation, and cites scripts that are not bundled. Tightening and verifying references would lift most dimensions.

Suggestions

Remove the generic boilerplate sections (When to Use, Recommended Workflow, Output Contract, Deterministic Output Rules, Completion Checklist) that restate process guidance Claude already knows, keeping only the skill-specific Molecular Review Workflow content to improve conciseness.

Replace 'Then invoke the skill with disease and molecule parameters' with the actual executable command and argument syntax so the core action is copy-paste ready.

Either ship scripts/pubmed_api.py and scripts/validate_skill.py in a scripts/ bundle or remove the references, since the body currently cites files that do not exist.

DimensionReasoningScore

Conciseness

Roughly half the body is generic templated process guidance Claude already knows ('Use this skill when the request matches its documented task boundary', 'Execution model: validate the request, choose the packaged workflow'), constituting several padded sections per the level-2 anchor rather than the mostly-efficient level 3.

2 / 5

Actionability

Concrete commands exist for setup and checks (export NCBI_EMAIL/API_KEY, py_compile, --help), but the core action is vague ('Then invoke the skill with disease and molecule parameters') with no copy-paste run command, and the referenced scripts do not exist in the bundle.

3 / 5

Workflow Clarity

The 5-step Workflow Process is sequenced but stated descriptively ('Translates...', 'Creates...', 'Executes...') with implicit rather than explicit checkpoints between steps, fitting the level-3 anchor; validation framing exists elsewhere but is not wired into the step sequence.

3 / 5

Progressive Disclosure

The body is sectioned with headers (some structure) but all content is inlined in one 160-line file with no real split, and references to scripts/pubmed_api.py and scripts/validate_skill.py point to files absent from the bundle, matching the level-3 'references present but not clearly signaled / should be separate is inline' anchor.

3 / 5

Total

11

/

20

Passed

Description

82%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 cleanly answers both what the skill does and when to invoke it, with a distinct, low-conflict niche and good natural trigger terms. Its only weakness is moderate action specificity, listing one core action rather than a comprehensive set.

DimensionReasoningScore

Specificity

Names the domain ('academic reviews for molecules in diseases') and one concrete action ('Generates academic reviews... using PubMed research'), but does not enumerate several specific actions, matching the '1-2 concrete actions, not comprehensive' anchor rather than the multi-action level 4.

3 / 5

Completeness

Explicitly states both what ('Generates academic reviews for molecules in diseases using PubMed research') and when ('Invoke when user needs biomedical literature review with Vancouver citation format'), with concrete trigger phrases matching the top anchor.

5 / 5

Trigger Term Quality

Includes natural user-facing terms ('PubMed', 'biomedical literature review', 'Vancouver citation format') with good coverage, but lacks synonyms and file-extension variants required for the comprehensive level-5 anchor.

4 / 5

Distinctiveness Conflict Risk

The molecule-in-disease + PubMed + Vancouver-citation niche is specific and unlikely to fire for unrelated skills, giving minimal conflict risk per the level-5 anchor.

5 / 5

Total

17

/

20

Passed

Validation

87%

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

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

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
Reviewed

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.