CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

bianque

Evidence-based medical knowledge and research mentor grounded in the Bian Que tradition. Covers clinical reasoning, diagnostic thinking (望闻问切), pharmacology, pathology, differential diagnosis, medical literature appraisal, and the philosophy of early intervention. Trigger whenever users ask about medicine, clinical science, drugs, disease mechanisms, diagnosis, lab interpretation, treatment comparison, or health sciences. Even without explicit research framing, trigger on any topic touching disease, therapeutics, or clinical decision-making. Part of the AIPOCH Medical Research Skill Hub.

Quality

82%

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.

A well-structured persona skill: lean body, concrete behavioral rules, an ordered diagnostic workflow, and exemplary progressive disclosure with all references real and clearly signaled. Remaining improvements are minor — tightening repeated persona/framework passages and making the diagnostic sequence more procedurally explicit.

DimensionReasoningScore

Conciseness

The ~45-line body is efficient and assumes Claude's competence — no explanation of concepts Claude already knows; persona material is novel and purposeful. It sits at anchor 4 rather than 5 because of minor repetition: the 腠理→骨髓 progression is explained in both Core Persona and Diagnostic Philosophy, and voice traits ("You do not flatter. You do not hedge") recur as "unflinching clarity".

4 / 5

Actionability

Concrete behavioral directives are present: "apply the four axes before pronouncing. Ask the one question that will clarify the picture, then wait for the answer", "When the evidence is weak, say so explicitly", "Use this connection sparingly, only when it clarifies". For an instruction-only skill this is mostly executable guidance (anchor 4); it falls short of 5 because a few directives stay abstract ("integrate physical and quantitative findings") and no worked example is shown inline — they are delegated to the references.

4 / 5

Workflow Clarity

The four diagnostic axes (望闻问切) give an explicit ordered reasoning sequence, with checkpoints like "then wait for the answer" and a clear teaching protocol ("explain what made it matter and what its limits are"). This matches anchor 4's clear sequence with minor gaps; it is not 5 because the diagnostic procedure is woven into philosophy prose rather than an explicit step-by-step with validation, and not 3 because the sequence and pause points are unambiguous. No destructive/batch operations, so the validation cap does not apply.

4 / 5

Progressive Disclosure

A clear overview with well-signaled, one-level-deep references: each of the three reference files is invoked at its point of use ("For voice calibration... read `references/persona-guide.md`") and all three exist on disk, plus a Reference Files index with one-line descriptions. This matches anchor 5 exactly.

5 / 5

Total

17

/

20

Passed

Description

80%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: explicit what and when, rich natural trigger terms, and a distinct persona grounding. Its main weakness is conflict risk — the instruction to trigger on any disease/therapeutics topic, combined with hub membership, creates real overlap risk with closely related medical skills. Specificity is solid but framed as topic coverage rather than discrete actions.

Suggestions

Narrow the catch-all trigger ("trigger on any topic touching disease, therapeutics, or clinical decision-making") or add a distinguishing qualifier, e.g. limit to cases needing clinical reasoning, research mentorship, or evidence appraisal, so sibling skills in the AIPOCH hub don't collide.

Add missing high-frequency natural trigger terms such as "symptoms", "illness", "medication", "side effects", and plain "treatment" to the when-clause.

Convert one or two "Covers ..." topics into concrete action verbs (e.g., "Appraises medical literature using GRADE" or "Works through differential diagnoses step by step") to strengthen action specificity.

DimensionReasoningScore

Specificity

"Covers clinical reasoning, diagnostic thinking (望闻问切), pharmacology, pathology, differential diagnosis, medical literature appraisal, and the philosophy of early intervention" lists seven specific capability areas with only minor gaps. It sits at anchor 4 rather than 5 because the framing is a single verb ("Covers") plus a topic list, not multiple distinct concrete actions like "extract text, fill forms, merge documents"; it is well above anchor 3's 1-2 concrete actions.

4 / 5

Completeness

It explicitly answers both: what ("Evidence-based medical knowledge and research mentor... Covers clinical reasoning, ... pharmacology, ...") and when ("Trigger whenever users ask about medicine... Even without explicit research framing, trigger on any topic touching disease, therapeutics, or clinical decision-making"). This matches anchor 5: both what and when stated explicitly with concrete trigger phrases.

5 / 5

Trigger Term Quality

Natural phrases users would actually say are present: "medicine, clinical science, drugs, disease mechanisms, diagnosis, lab interpretation, treatment comparison, or health sciences" and "disease, therapeutics, or clinical decision-making". This fits anchor 4's 'good keyword coverage; a few natural terms missing' — common user phrasings like "symptoms", "illness", "medication", or plain "treatment" are absent — but is stronger than anchor 3's partial coverage.

4 / 5

Distinctiveness Conflict Risk

The Bian Que persona niche is distinctive, but "trigger on any topic touching disease, therapeutics, or clinical decision-making" claims maximal breadth, and the description places the skill inside a hub ("Part of the AIPOCH Medical Research Skill Hub") with likely sibling medical skills it would collide with. That is anchor 3's 'somewhat specific but could still overlap with similar skills' rather than anchor 4's minor-overlap.

3 / 5

Total

16

/

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/Other/bianque/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.