CtrlK
BlogDocsLog inGet started
Tessl Logo

clinical-diagnostic-reasoning

Identify and counteract cognitive biases in medical decision-making through systematic error analysis and contextual algorithm application. For diagnostic reasoning, treatment decisions, and

53

Quality

60%

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

Fix and improve this skill with Tessl

tessl review fix ./scientific-skills/Other/clinical-diagnostic-reasoning/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

67%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-organized, actionable clinical-reasoning guide with clear sequenced flows and an explicit bias-check validation loop. Its main weakness is conciseness: narrative "Timeline" sections and explanations of biases Claude already knows add padding. Progressive disclosure is good for a single-file skill, with only minor inlining of detail.

Suggestions

Cut or compress the per-bias "Timeline" narrative paragraphs; they describe skill acquisition over years rather than guiding action and add substantial token cost.

Remove or minimize definitions of well-known cognitive biases (anchoring, availability, commission) and keep only the novice→expert reframe and the specific counteraction question for each.

Consider moving the detailed anti-pattern catalog into a references file (e.g. ANTI_PATTERNS.md) linked from the body to tighten the overview while keeping the detail one level deep.

DimensionReasoningScore

Conciseness

The flows and novice/expert contrasts are efficient, but the per-bias "Timeline" narratives and the explanations of well-known biases (anchoring, availability, etc.) that Claude already knows add padding that could be trimmed.

3 / 5

Actionability

Concrete, executable guidance throughout — specific self-questioning prompts ("Am I anchored to initial impression?", "Have I sought disconfirming evidence?") and explicit novice→expert reframes — with only minor abstract gaps; absence of code is fine for this instruction-only skill.

4 / 5

Workflow Clarity

The three ASCII decision flows are clearly sequenced with an explicit "BIAS CHECK - Always perform" validation loop and an error-recovery path, though a few checkpoints are implicit rather than called out as discrete steps.

4 / 5

Progressive Disclosure

Single-file skill with clean section headers (When to Use, Core Process, Anti-Patterns, Mental Models, Input Validation, References) and no nested/buried references; the only minor gap is that the lengthy anti-pattern detail is fully inlined rather than split into a reference file.

4 / 5

Total

15

/

20

Passed

Description

53%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 states a clear purpose and niche but is truncated mid-sentence and lacks an explicit "Use when..." trigger clause, capping completeness and weakening trigger-term quality. Specificity is moderate because the named actions are somewhat abstract. Distinctiveness is the strongest dimension thanks to the focused clinical-reasoning domain.

Suggestions

Complete the truncated description (it ends with "and") and add an explicit "Use when..." clause with concrete clinical triggers, e.g. "Use when working through a difficult diagnosis, reviewing a diagnostic error, or planning treatment where cognitive bias may be active."

Replace abstract phrases like "systematic error analysis and contextual algorithm application" with concrete verbs tied to recognizable clinical situations to lift specificity.

Add natural trigger synonyms a clinician would say ("diagnostic error", "cognitive bias", "differential diagnosis", "anchoring", "missed diagnosis") to improve trigger-term coverage.

DimensionReasoningScore

Specificity

Names the domain and a few actions ("Identify and counteract cognitive biases", "systematic error analysis", "contextual algorithm application") but the actions skew abstract rather than concrete, and coverage is incomplete because the sentence is cut off mid-phrase.

3 / 5

Completeness

The "what" is clear (counteract cognitive biases in medical decision-making) but there is no explicit "Use when..." clause — only a weakly implied, truncated "when" — so per the cap rule completeness is held at 3.

3 / 5

Trigger Term Quality

Relevant keywords like "diagnostic reasoning" and "treatment decisions" appear, but the trigger list ("For diagnostic reasoning, treatment decisions, and") is truncated, leaving out common variations and synonyms a clinician would naturally say.

3 / 5

Distinctiveness Conflict Risk

The clinical cognitive-bias niche is mostly distinct with limited overlap risk against general reasoning skills, though the unfinished trigger list keeps it from a fully spelled-out, zero-conflict profile.

4 / 5

Total

13

/

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.