Agent skill

Clinical Diagnostic Reasoning

by curiositech in curiositech/some_claude_skills

Identify and counteract cognitive biases in medical decision-making through systematic error analysis and contextual algorithm application.

MITAuto-check passed

Install Clinical Diagnostic Reasoning

skills CLI
$ npx skills add curiositech/some_claude_skills --skill clinical-diagnostic-reasoning -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install curiositech/some_claude_skills clinical-diagnostic-reasoning --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/curiositech/some_claude_skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/clinical-diagnostic-reasoning .claude/skills/clinical-diagnostic-reasoning && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
clinical-diagnostic-reasoning
GitHub stars
244
Used in
2 other repos
Token cost
~2.8k tokens
SKILL.md length
848 words
Files
2
Skills in repo
95
Repo updated
First seen
Licence
MIT

At a glance

Identify and counteract cognitive biases in medical decision-making through systematic error analysis and contextual algorithm application.

  • SKILL.md covers When to Use, Core Process, Anti-Patterns and Mental Models & Shibboleths, plus 1 more section
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Clinical Diagnostic Reasoning is an agent skill from curiositech/some_claude_skills. Identify and counteract cognitive biases in medical decision-making through systematic error analysis and contextual algorithm application. For diagnostic reasoning, treatment decisions, and clinical judgment improvement. NOT for basic medical knowledge, technical procedures, or non-clinical healthcare domains.

Its SKILL.md is about 2.8k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `.claude-plugin/plugin.json`).

The repository describes itself as: Claude skills that make my life easier. The licence is MIT.

Example prompts

  • “/clinical-diagnostic-reasoning”

Requirements

  • Pre-approved tools (allowed-tools): Read

What it can do on your machine

Read from SKILL.md and the folder at commit 6713fc7. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Read

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Clinical Diagnostic Reasoning loads about 2.8k tokens when it runs. Until then it costs about 86 tokens; SKILL.md has 848 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~86
When it runs · the whole SKILL.md, loaded when a task matches
~2.8k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from curiositech/some_claude_skills at commit 6713fc7, republished under its MIT licence (© curiositech). 848 words, ~2,801 tokens.

Download SKILL.mdSave it as .claude/skills/clinical-diagnostic-reasoning/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
clinical-diagnostic-reasoning
description
Identify and counteract cognitive biases in medical decision-making through systematic error analysis and contextual algorithm application. For diagnostic reasoning, treatment decisions, and clinical judgment improvement. NOT for basic medical knowledge, technical procedures, or non-clinical healthcare domains.
allowed-tools
Read
metadata.tags
clinical, diagnostic, reasoning

Clinical Diagnostic Reasoning

Improve diagnostic accuracy and treatment decisions by recognizing and overcoming systematic cognitive errors in clinical thinking.

When to Use

✅ Use for:

  • Diagnostic decision-making in clinical practice
  • Treatment planning and therapeutic choices
  • Case review and error analysis
  • Medical education on clinical reasoning
  • Patient communication and shared decision-making
  • Quality improvement and patient safety initiatives

❌ NOT for:

  • Learning basic medical facts or pathophysiology
  • Technical procedures or surgical skills
  • Healthcare administration or policy
  • Non-physician clinical roles without diagnostic responsibility
  • Population health management without individual patient focus

Core Process

Diagnostic Reasoning Flow
New patient presentation
    ↓
┌───[Gather information through language/history]
│   ↓
│   Does presentation suggest standard algorithm?
│   ├─ NO → Continue hypothesis generation
│   │         ↓
│   │         Develop differential diagnosis
│   │         ↓
│   │         [Proceed to bias check]
│   │
│   └─ YES → Does patient context match algorithm assumptions?
│             ├─ YES → Apply algorithm
│             │         ↓
│             │         Monitor outcomes
│             │         ↓
│             │         [Proceed to bias check]
│             │
│             └─ NO → What patient-specific factors differ?
│                     ↓
│                     Does evidence justify deviation?
│                     ├─ YES → Document rationale and modify
│                     └─ NO → Apply algorithm; reconsider if new data
│
└─── [BIAS CHECK - Always perform]
     ↓
     Am I anchored to initial impression?
     ├─ POSSIBLY → Reassess case without initial anchor
     │
     Have I found one explanation and stopped searching?
     ├─ YES → Continue search: "What else could this be?"
     │         "Does this explain ALL findings?"
     │
     Am I pattern-matching from recent/memorable case?
     ├─ YES → List specific differences between cases
     │
     Am I stereotyping this patient?
     ├─ POSSIBLY → Reset: Evaluate symptoms independently
     │
     Do I feel compelled to "do something"?
     ├─ YES → Is action justified by evidence or anxiety?
     │         Is watchful waiting appropriate?
     │
     Have I sought disconfirming evidence?
     └─ NO → Actively look for data that contradicts working diagnosis
Case-Based Error Analysis Flow
Clinical error occurred
    ↓
What was the error?
    ├─ Wrong diagnosis
    ├─ Inappropriate treatment
    └─ Missed diagnosis
    ↓
Was this a knowledge gap or thinking error?
    ├─ KNOWLEDGE GAP → Address through study
    │                   (Not the focus of this skill)
    │
    └─ THINKING ERROR → Which cognitive bias operated?
                        ↓
                        ┌─ Anchoring? (stuck on initial impression)
                        ├─ Satisfaction of search? (stopped too early)
                        ├─ Availability? (recent case pattern-match)
                        ├─ Attribution? (stereotyped patient)
                        └─ Commission? (unnecessary action)
                        ↓
                        Was error preventable with current knowledge?
                        ├─ YES → How could bias have been recognized?
                        │         ↓
                        │         Extract generalizable lesson
                        │         ↓
                        │         Apply to future similar situations
                        │
                        └─ NO → Document for learning, not applicable
Patient Communication Flow
Need to present medical information
    ↓
What decision does patient need to make?
    ↓
Identify equivalent framings:
    - Positive frame (% success/survival)
    - Negative frame (% failure/mortality)
    - Absolute numbers
    - Relative risk
    ↓
Which framing facilitates genuine understanding?
    ↓
Is my framing choice unintentionally biasing decision?
    ├─ YES → Present multiple equivalent framings
    │         Allow patient to process from different angles
    │
    └─ UNCERTAIN → Present both positive and negative frames
                    Verify patient comprehension
                    ↓
                    "What is your understanding of the risks/benefits?"

Anti-Patterns

Novice approach: Finds one clinically interesting explanation and stops diagnostic inquiry. "The patient has pneumonia, that explains the fever and cough."

Expert approach: After finding initial explanation, explicitly asks: "What else could be present? Does this explain ALL findings? Could there be a coexisting condition?"

Timeline: Develops over years of clinical experience through cases where initial findings were incomplete or coincidental. Critical moment comes when missing a second diagnosis causes patient harm—realization that "not finding everything is suboptimal."

Anchoring Error

Novice approach: Initial symptoms or emergency department triage note establishes diagnosis that persists despite contradictory information. "ED said anxiety attack, so I'm treating anxiety."

Expert approach: Periodically resets evaluation without reference to initial impressions. "If I saw this patient fresh right now, what would I think?" Actively seeks information contradicting initial hypothesis.

Timeline: Requires recognizing pattern across multiple cases where initial impression proved misleading. Breakthrough occurs when physician catches themselves defending an anchor despite mounting contrary evidence.

Commission Bias

Novice approach: Feels compelled to take action because "doing something" feels better than watchful waiting, even without clear indication. Treats borderline abnormal labs, adjusts medications unnecessarily.

Expert approach: Explicitly evaluates whether action is justified by evidence or driven by psychological need to intervene. Comfortable with watchful waiting when appropriate. Asks: "Will treatment help more than harm?"

Timeline: Often develops after causing harm through unnecessary intervention. Turning point is recognizing that action carries its own risks and that inaction is sometimes the most appropriate decision.

Availability Error

Novice approach: "I just saw three patients with Lyme disease, so this patient's fatigue must be Lyme too." Pattern-matches based on superficial similarities without considering differences.

Expert approach: When noticing similarity to recent case, explicitly lists differences: "How is this patient NOT like that case?" Questions whether similarities are clinically meaningful or coincidental.

Timeline: Accumulates through experience with similar-seeming cases that proved different. Key insight comes when a "just like the last patient" case turns out completely different upon deeper investigation.

Attribution Error

Novice approach: Accepts colleague's characterization that patient is "drug-seeking" or "anxious" and dismisses symptoms without independent evaluation. Stereotypes based on demographics.

Expert approach: Approaches each patient as individual regardless of others' characterizations. "What does THIS patient's presentation tell me?" Separates objective findings from attributed motivations.

Timeline: Often requires personal experience of misjudging a patient or discovering that a dismissed patient had serious pathology. Recognition that stereotypes prevented seeing actual clinical presentation.

Show full SKILL.md (348 more words)Show less
Algorithm Rigidity

Novice approach: Either follows algorithms without contextual consideration ("The guideline says X, so I must do X") OR abandons them based on gut feeling without justification.

Expert approach: Recognizes algorithms as population-based tools requiring interpretation. Can articulate why specific patient context justifies deviation when it does. Documents reasoning.

Timeline: Develops through repeated experience applying guidelines to diverse patients. Critical learning occurs when rigid application causes harm OR when appropriate deviation leads to better outcome—recognizing that expertise lies in knowing which mode applies when.

Mental Models & Shibboleths

Core Shibboleths
  • "Not finding everything is suboptimal" — Expert recognition that diagnostic search shouldn't stop at first finding
  • "Understanding why we get things wrong is essential to understanding how to get things right" — Expert frame that errors reveal cognitive patterns, not just knowledge gaps
  • Semantic equivalence awareness — Expert automatically recognizes that "30% chance of improvement" and "70% chance of failure" are clinically identical but psychologically different
Expert vs Novice Markers

Novice says: "The patient has [single diagnosis]" Expert says: "The primary issue is [diagnosis], but I'm also considering [alternatives] and haven't ruled out [other possibilities]"

Novice says: "We need to do something" Expert says: "The question is whether intervention offers more benefit than harm compared to watchful waiting"

Novice says: "The protocol says..." Expert says: "The protocol applies when [conditions], but this patient differs in [specific ways]"

Navigation Metaphor

Clinical reasoning requires navigating between two extremes:

  • Rigid shore: Algorithmic medicine without contextual adaptation
  • Chaos shore: Intuition-based medicine without evidence grounding
  • Expert navigation: Knowing when to sail closer to structure (standard presentations) versus when context requires deviation (atypical patients)
Trap Metaphor

Cognitive biases are predictable traps on the diagnostic path:

  • Recognizable once you know what to look for
  • Avoidable with deliberate countermeasures
  • Universal (even experts fall in, but recognize and escape faster)
  • The map of traps can be taught and learned

References

  • Source: "How Doctors Think" by Jerome Groopman
  • Domain: Clinical decision-making, diagnostic reasoning, medical cognitive science
  • Key insight: Medical errors stem primarily from systematic thinking patterns (cognitive biases) rather than knowledge deficits, and these patterns can be identified, taught, and corrected

© curiositech, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file in .claude/skills/clinical-diagnostic-reasoning of curiositech/some_claude_skills.

  • SKILL.md
  • .claude-plugin/plugin.json

Open the folder on GitHubat commit 6713fc7

Used in 2 other repositories

We found 2 copies of this SKILL.md (exact, near-identical or edited) in other folders, from 2 other GitHub owners. This page covers the copy in curiositech/some_claude_skills, which our catalogue first saw on October 7, 2026.

Compare with similar skills

Clinical Diagnostic Reasoning next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Clinical Diagnostic Reasoning compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Clinical Diagnostic Reasoning this skillcuriositech/some_claude_skills2442 repos~2.8kAutomated safety check: PassMIT
Clinical Diagnostic Reasoningaipoch/medical-research-skills1.9k—~2.8kAutomated safety check: PassMIT
Diagnostic Reasoningkunchenguid/firstmate7.8k—~963Automated safety check: PassMIT
Clinical Reportsdavila7/claude-code-templates33k11 repos~9.9kAutomated safety check: NotesMIT
Cognitive Patternruvnet/ruflo74k—~384Automated safety check: NotesMIT
Deepseek Reasonruvnet/ruflo74k—~626Automated safety check: NotesMIT

Similar skills

  • Clinical Diagnostic Reasoning

    aipoch/medical-research-skills

    Identify and counteract cognitive biases in medical decision-making through systematic error analysis and contextual algorithm application.

    1.9k GitHub stars~2.8k tokensUpdated 24 days ago
    Research & ScienceAuto-check passed
  • Diagnostic Reasoning

    kunchenguid/firstmate

    Agent-only procedure for diagnosing reported bugs. An agent skill from kunchenguid/firstmate.

    7.8k GitHub stars~963 tokensUpdated today
    Auto-check passed
  • Clinical Reports

    davila7/claude-code-templates

    Write comprehensive clinical reports including case reports (CARE guidelines), diagnostic reports (radiology/pathology/lab), clinical trial reports (ICH-E3, SAE, CSR), and patient documentation…

    33k GitHub starsUsed in 11 repos~9.9k tokens
    Legal & ComplianceAuto-check: notes
  • Cognitive Pattern

    ruvnet/ruflo

    Define and manage cognitive patterns for agent reasoning and decision-making

    74k GitHub stars~384 tokensUpdated yesterday
    Auto-check: notes
  • Deepseek Reason

    ruvnet/ruflo

    Reasoning-mode completion against DeepSeek's deepseek-reasoner model (R1) via /v1/chat/completions.

    74k GitHub stars~626 tokensUpdated yesterday
    AI & LLM EngineeringAuto-check: notes
  • Clinical Research

    alirezarezvani/claude-skills

    A skill your agent uses when designing a prospective clinical study before submission — selecting and classifying endpoints (primary / key-secondary / exploratory, with surrogate-endpoint flagging)…

    28k GitHub stars~2.7k tokensUpdated 1 mo ago
    Research & ScienceAuto-check passed

More from curiositech/some_claude_skills

All 95 skills in this repo
  • Crisis Detection Intervention AI

    curiositech/some_claude_skills

    Detect crisis signals in user content using NLP, mental health sentiment analysis, and safe intervention protocols.

    244 GitHub starsUsed in 2 repos~3.8k tokens
    Auto-check passed
  • Form Validation Architect

    curiositech/some_claude_skills

    End-to-end form handling with react-hook-form, Zod schemas, validation patterns, error messaging, field arrays, and multi-step wizards.

    244 GitHub stars~3.8k tokensUpdated 1 mo ago
    Auto-check passed
  • GitHub Actions Pipeline Builder

    curiositech/some_claude_skills

    Build production CI/CD pipelines with GitHub Actions. An agent skill from curiositech/some_claude_skills.

    244 GitHub stars~2.8k tokensUpdated 1 mo ago
    Auto-check: notes
  • Background Job Orchestrator

    curiositech/some_claude_skills

    Expert in background job processing with Bull/BullMQ (Redis), Celery, and cloud queues.

    244 GitHub stars~3.2k tokensUpdated 1 mo ago
    Auto-check passed
  • Competitive Cartographer

    curiositech/some_claude_skills

    Strategic analyst that maps competitive landscapes, identifies white space opportunities, and provides positioning recommendations.

    244 GitHub stars~1.3k tokensUpdated 1 mo ago
    Auto-check passed
  • Computer Vision Pipeline

    curiositech/some_claude_skills

    Build production computer vision pipelines for object detection, tracking, and video analysis.

    244 GitHub stars~4k tokensUpdated 1 mo ago
    Auto-check passed

Questions about Clinical Diagnostic Reasoning

What does Clinical Diagnostic Reasoning do?

Identify and counteract cognitive biases in medical decision-making through systematic error analysis and contextual algorithm application. Clinical Diagnostic Reasoning is an agent skill from curiositech/some_claude_skills. Identify and counteract cognitive biases in medical decision-making through systematic error analysis and contextual algorithm application.

How do I install Clinical Diagnostic Reasoning in Claude Code?

Run `npx skills add curiositech/some_claude_skills --skill clinical-diagnostic-reasoning -a claude-code`. Or copy the skill folder (.claude/skills/clinical-diagnostic-reasoning in curiositech/some_claude_skills) into .claude/skills/clinical-diagnostic-reasoning in your project. Claude Code loads it when a task matches its description.

How do I install Clinical Diagnostic Reasoning in Codex?

Run `npx skills add curiositech/some_claude_skills --skill clinical-diagnostic-reasoning -a codex`. Or copy the skill folder (.claude/skills/clinical-diagnostic-reasoning in curiositech/some_claude_skills) into .agents/skills/clinical-diagnostic-reasoning in your project. Codex loads it when a task matches its description.

Can I use Clinical Diagnostic Reasoning in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add curiositech/some_claude_skills --skill clinical-diagnostic-reasoning -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/clinical-diagnostic-reasoning, .gemini/skills/clinical-diagnostic-reasoning, .github/skills/clinical-diagnostic-reasoning and .opencode/skills/clinical-diagnostic-reasoning in your project.

What does Clinical Diagnostic Reasoning need to run?

SKILL.md names no scripts, command-line tools or credentials: Clinical Diagnostic Reasoning is instructions for the agent only. Its frontmatter pre-approves these tools: Read.

Does Clinical Diagnostic Reasoning access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Clinical Diagnostic Reasoning safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Clinical Diagnostic Reasoning use?

Clinical Diagnostic Reasoning is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Clinical Diagnostic Reasoning use?

About 2.8k tokens (SKILL.md is roughly 11k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Clinical Diagnostic Reasoning?

Skills that share tags, products or a category with Clinical Diagnostic Reasoning: Clinical Diagnostic Reasoning (aipoch/medical-research-skills, 1.9k stars), Diagnostic Reasoning (kunchenguid/firstmate, 7.8k stars), Clinical Reports (davila7/claude-code-templates, 33k stars) and Cognitive Pattern (ruvnet/ruflo, 74k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Clinical Diagnostic Reasoning?

curiositech (a GitHub organization) maintains it in curiositech/some_claude_skills, which has 244 GitHub stars. The repository holds 95 skills in this directory. The repository was last updated on September 6, 2026.

Source: curiositech/some_claude_skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.