CtrlK
BlogDocsLog inGet started
Tessl Logo

hippocrates

Evidence-based medical knowledge and research mentor. Trigger this skill when users ask any question related to medicine, clinical science, pharmacology, pathology, epidemiology, or health sciences. Covers: disease mechanisms, drug actions and interactions, differential diagnosis reasoning, clinical guideline interpretation, medical literature appraisal (including GRADE assessment), treatment comparisons, lab and imaging interpretation, public health analysis, and medical terminology. Even if the user doesn't explicitly say "evidence-based" or "medical research," trigger this skill whenever the topic touches health, disease, drugs, or therapeutics. Part of the AIPOCH Medical Research Skill Hub.

72

Quality

89%

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

78%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 a well-structured, highly actionable persona skill with excellent progressive disclosure via a clear reference table. Its main weakness is verbosity in the illustrative "Mentor's Voice" quote collections, which exceed what is needed to convey the register.

Suggestions

Trim the "Mentor's Voice" blockquote collection to one or two representative quotes per principle; the current stack (Hippocratic register, rhythm, probe, metformin example) re-demonstrates the same tone repeatedly.

Condense the metformin worked example or relocate it to references/persona-guide.md so the core SKILL.md stays a lean overview.

Consider moving the longer contemplative register guidance into persona-guide.md and keeping SKILL.md focused on the workflow, voice rules, and reference pointers.

DimensionReasoningScore

Conciseness

Mostly efficient and free of Claude-known-concept padding, but the "Mentor's Voice" section stacks many illustrative blockquotes and a long metformin example that illustrate the same register redundantly and could be trimmed to one or two representative quotes.

3 / 5

Actionability

Concrete and executable throughout for an instruction-only persona skill: a four-step workflow, per-level student calibration, defined evidence-quality tiers with natural-language translations, explicit format rules ("One question at a time," "Default to flowing prose"), and a worked ❌/✅ metformin example covering a common case.

5 / 5

Workflow Clarity

A clearly sequenced four-step process (Classify → Structure → Evidence-quality → GRADE) with routing checkpoints (personal-health context → read safety-framework.md before responding), though the explicit validate→fix→retry feedback-loop pattern is only loosely present since outputs are conversational prose rather than fragile operations.

4 / 5

Progressive Disclosure

A well-signaled Reference Files table with a "When to read" column points one level deep to three real, verified files, the body is organized into clear sections, and planned future files are explicitly marked "(planned)" — easy to navigate.

5 / 5

Total

17

/

20

Passed

Description

100%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 is exemplary: it concisely states what the skill does, lists concrete capabilities, and gives explicit, natural-language trigger conditions with synonyms. It cleanly satisfies the what/when requirement with minimal conflict risk.

DimensionReasoningScore

Specificity

Lists many concrete capabilities — "differential diagnosis reasoning," "clinical guideline interpretation," "medical literature appraisal (including GRADE assessment)," "treatment comparisons," "lab and imaging interpretation," "public health analysis" — giving comprehensive coverage of specific actions rather than vague abstraction.

5 / 5

Completeness

Explicitly answers both "what" (an evidence-based medical knowledge and research mentor with listed capabilities) and "when" ("Trigger this skill when users ask any question related to medicine..." and "trigger this skill whenever the topic touches health, disease, drugs, or therapeutics").

5 / 5

Trigger Term Quality

Covers natural terms users actually say — "medicine," "pharmacology," "drugs," "health," "disease," "therapeutics," "medical research" — with strong synonyms across the domain; the file-extension criterion is not applicable to a non-file medical skill.

5 / 5

Distinctiveness Conflict Risk

Occupies a clear niche as an evidence-based medical research mentor with distinct domain triggers (medicine, pharmacology, pathology, epidemiology), giving minimal overlap risk with unrelated skills.

5 / 5

Total

20

/

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.

Validation15 / 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
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.