CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

medical-research-literature-reader-pro

A medical-research-native literature reading skill for users with clinical, bioinformatics, translational, and basic experimental backgrounds. Use this skill whenever a user wants to read, analyze, critique, or interpret a medical or scientific paper — whether they provide a PDF, abstract, DOI, PMID, or just a title. Triggers include requests like \"analyze this paper\", \"critique this study\", \"is this a strong paper?\", \"give me similar studies\", \"prepare me for journal club\", \"help me understand this bioinformatics paper\", \"what are the weaknesses here?\", or \"turn this into a mind map\". Also activate for any downstream deliverables such as journal club kits, comparison tables, PI decision briefs, replication starters, or follow-up experiment designs. Do NOT treat as a generic summarizer — this skill performs structured evidence-type classification, track-specific critical appraisal, interpretation-boundary judgment, and research-grade follow-up generation.

Quality

91%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

86%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.

A well-structured, highly actionable skill body with excellent progressive disclosure into six real, clearly-signaled reference files. The main costs are duplicated reference-module listings and a small amount of self-promotional padding, plus the absence of an explicit final-report verification step.

Suggestions

Collapse the 'Reference Module Integration' section or the inline reference links into a single canonical list to remove duplication and save tokens.

Trim or remove the 'Composability' section — it describes marketing-style connections rather than executable guidance.

Add an explicit end-of-report self-check step (e.g., verify every applicable template section is present and each cited reference module was actually loaded) before closing with the natural end-of-report offer.

DimensionReasoningScore

Conciseness

The body is efficient — routing tables, behavioral rules, and a tight template, with no teaching of concepts Claude already knows. However, the six reference-module links are listed twice (inline throughout plus a full "Reference Module Integration" section), and the "Composability" section is promotional padding.

4 / 5

Actionability

Fully actionable for an instruction-only skill: a copy-paste 14-section output template, concrete routing examples ("NHANES + ML → Primary: A · Secondary: B"), scripted user-facing sentences for insufficient input, bias requests, and out-of-scope redirects.

5 / 5

Workflow Clarity

The decision logic is clearly sequenced (classify → assign roles → choose depth → plugins), and the Minimum Viable Input rule plus the "treat the output as incomplete" rule provide validation checkpoints. It falls short of the top anchor because there is no explicit final-report self-check step.

4 / 5

Progressive Disclosure

The body is a well-organized overview that splits detail into six one-level-deep reference files, all of which exist, each clearly signaled with markdown links and an explicit statement of which report section requires it.

5 / 5

Total

18

/

20

Passed

Description

95%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.

A strong description that clearly states what the skill does, when to use it with natural user-quoted triggers, and how it differs from a generic summarizer. The only weakness is mild jargon density in the capability phrasing.

DimensionReasoningScore

Specificity

Names several concrete operations ("structured evidence-type classification, track-specific critical appraisal, interpretation-boundary judgment") and concrete deliverables ("journal club kits, comparison tables, PI decision briefs, replication starters"), but openers like "read, analyze, critique, or interpret" and jargon like "research-grade follow-up generation" keep it a notch below fully comprehensive and concrete.

4 / 5

Completeness

Explicitly answers both what (classification, appraisal, interpretation-boundary judgment, follow-up generation) and when ("Use this skill whenever a user wants to read, analyze, critique, or interpret a medical or scientific paper" with a concrete trigger list), matching the top anchor.

5 / 5

Trigger Term Quality

Comprehensive natural trigger phrases users would actually say ("analyze this paper", "is this a strong paper?", "prepare me for journal club", "turn this into a mind map") plus input-format synonyms (PDF, abstract, DOI, PMID, title).

5 / 5

Distinctiveness Conflict Risk

Clear medical/scientific-paper niche with distinct trigger phrases and an explicit negative boundary ("Do NOT treat as a generic summarizer"), minimizing overlap with generic summarization skills.

5 / 5

Total

19

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

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

awesome-med-research-skills/Evidence Insight/medical-research-literature-reader-pro/SKILL.md

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.