Agent skill

Ronald C Kessler

by K-Dense-AI in K-Dense-AI/mimeographs

This skill applies the analytical frameworks of Ronald C. An agent skill from K-Dense-AI/mimeographs.

MITAuto-check passedResearch & Science

Install Ronald C Kessler

skills CLI
$ npx skills add K-Dense-AI/mimeographs --skill ronald-c-kessler -a claude-code

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

GitHub CLI
$ gh skill install K-Dense-AI/mimeographs ronald-c-kessler --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/K-Dense-AI/mimeographs.git skills-src && mkdir -p .claude/skills && cp -r skills-src/mimeographs/ronald-c-kessler .claude/skills/ronald-c-kessler && 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
ronald-c-kessler
GitHub stars
129
Token cost
~1.6k tokens
SKILL.md length
776 words
Files
72 (incl. references)
Skills in repo
60
Repo updated
First seen
Licence
MIT

At a glance

This skill applies the analytical frameworks of Ronald C. An agent skill from K-Dense-AI/mimeographs.

  • Works in 4 steps: Gather comprehensive predictor sets,… → Make comprehensive comparisons across… → Utilize much bigger sample sizes via… → …
  • You are designing clinical trials
  • SKILL.md covers Core principles, How Ronald C. Kessler reasons, Applying the frameworks and Anti-patterns they push against, plus 1 more section
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Ronald C Kessler is an agent skill from K-Dense-AI/mimeographs. This skill applies the analytical frameworks of Ronald C. Kessler, psychiatric epidemiologist at Harvard University, to problems in precision psychiatry, clinical trial design, and healthcare machine learning. Use this skill whenever you are designing clinical trials, evaluating mental health interventions, analyzing epidemiological survey data, or building clinical decision support algorithms. It is highly relevant when the user asks about sample sizes, treatment matching, patient attrition, suicide prevention…

Its SKILL.md is about 1.6k tokens, which your agent loads only when the skill is triggered. The skill folder holds 74 other files, including reference files (for example `AGENTS.md`, `_workspace/agents_output.e584bd6c.json` and `_workspace/clustered_corpus.e584bd6c.json`).

It sits in Research & Science, covering Clinical and healthcare research, Experimental design and Health and fitness tracking. The repository describes itself as: Ready-to-use agent skills that clone the thinking of founders, philosophers, and scientists into your agent. Generated with K-Dense-AI/mimeo. The licence is MIT.

When your agent uses it

  • You are designing clinical trials
  • Evaluating mental health interventions
  • Analyzing epidemiological survey data
  • Building clinical decision support algorithms

Example prompts

  • “/ronald-c-kessler”

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

  1. Gather comprehensive predictor sets, including long baseline assessments.
  2. Make comprehensive comparisons across the full range of available treatments.
  3. Utilize much bigger sample sizes via comparative effectiveness research on observational data.
  4. Apply improved statistical methods, such as ensemble machine learning.

What it can do on your machine

Read from SKILL.md and the folder at commit a38f5fc. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    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

Ronald C Kessler loads about 1.6k tokens when it runs, and up to ~5.5k if it reads all its reference files. Until then it costs about 190 tokens; SKILL.md has 776 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~190
When it runs · the whole SKILL.md, loaded when a task matches
~1.6k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~5.5k

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 K-Dense-AI/mimeographs at commit a38f5fc, republished under its MIT licence (© K-Dense-AI). 776 words, ~1,644 tokens.

Download SKILL.mdSave it as .claude/skills/ronald-c-kessler/SKILL.md (or your agent's skills folder). This skill also uses 71 other files; get the full folder from GitHub.
name
ronald-c-kessler
description
This skill applies the analytical frameworks of Ronald C. Kessler, psychiatric epidemiologist at Harvard University, to problems in precision psychiatry, clinical trial design, and healthcare machine learning. Use this skill whenever you are designing clinical trials, evaluating mental health interventions, analyzing epidemiological survey data, or building clinical decision support algorithms. It is highly relevant when the user asks about sample sizes, treatment matching, patient attrition, suicide prevention, or predictive modeling in healthcare. Trigger this skill to prioritize massive observational data, tiered predictive models, and human-in-the-loop AI over underpowered randomized trials and expensive, unscalable biomarkers.

Thinking like Ronald C. Kessler

Ronald C. Kessler's thinking bridges the gap between massive-scale epidemiological data and individualized clinical care. As a psychiatric epidemiologist, his approach is defined by a relentless focus on statistical power, pragmatic real-world evidence, and the brutal realities of patient attrition. He views mental health treatment not as a single acute intervention, but as a complex, sequential matching problem where the greatest risk is a patient giving up before finding what works.

His reasoning consistently pushes back against the traditional "gold standard" of small randomized clinical trials, arguing they are hopelessly underpowered for precision medicine. Instead, he advocates for leveraging massive observational datasets, tiered predictive modeling, and human-computer collaboration to get the right treatment to the right patient immediately.

Reach for this skill whenever you're designing clinical trials, evaluating mental health interventions, analyzing epidemiological survey data, or building clinical decision support algorithms.

Core principles

  • Massive Sample Sizes for Precision Psychiatry: Reject small clinical trials for precision matching; rely instead on comparative effectiveness research using massive observational data to find true signals over statistical noise.
  • Human-Computer Collaboration in Clinical Decisions: Design clinical algorithms to augment and interact with thoughtful human clinicians, rather than attempting to replace them.
  • Treatment Persistence and Immediate Matching: Optimize systems to match patients with the right treatment on day one, because the primary bottleneck in psychiatric care is fatal patient drop-out, not a lack of effective treatments.
  • Tiered Predictive Modeling: Exhaust scalable, inexpensive predictors (like self-reported adherence or clinical notes) before allocating resources to expensive biomarker tests.
  • Measurement-Based Care and Cutting Losses: Mandate objective symptom tracking to identify and abandon failing treatments at three weeks instead of torturing the patient for eight weeks.

For detailed rationale and quotes, see references/principles.md.

How Ronald C. Kessler reasons

Kessler approaches clinical and epidemiological problems by first asking about statistical power and real-world attrition. He dismisses small-n studies and expensive, unscalable biomarkers. Instead, he looks for the cheapest, most predictive variables (like a 2-minute adherence scale) and insists on massive sample sizes (the 300-500 Minimum Case Rule per arm).

His reasoning is heavily influenced by The Centaur Model, viewing AI as a decision support tool that requires a human clinician's contextual understanding to succeed. He also relies on Survival Curves for Treatment Persistence, viewing treatment success as a cumulative probability over multiple attempts rather than a single event, which highlights the urgency of immediate precision matching. For a deeper dive into these lenses, see references/mental-models.md.

Applying the frameworks

Four Requirements for Precision Treatment Research

When to use: Use this when designing or critiquing a study intended to match mental health patients to optimal treatments.

  1. Gather comprehensive predictor sets, including long baseline assessments.
  2. Make comprehensive comparisons across the full range of available treatments.
  3. Utilize much bigger sample sizes via comparative effectiveness research on observational data.
  4. Apply improved statistical methods, such as ensemble machine learning.
Show full SKILL.md (296 more words)Show less
Precision Treatment Modeling

When to use: Use this when allocating limited healthcare resources or optimizing treatment selection algorithms.

  1. Develop risk models to identify individuals at the highest risk of a negative outcome (e.g., suicide) for targeted intensive interventions.
  2. Develop comparative risk models to predict which specific treatment a patient is most likely to respond to.
  3. Splice the models together to optimize allocation based on efficacy probabilities and costs.

For the full catalog of frameworks, see references/frameworks.md.

Anti-patterns they push against

  • Conducting Underpowered Biomarker Studies: Relying on small randomized clinical trials (e.g., 80 people per arm) that merely capture and replicate statistical noise.
  • Jumping Straight to Expensive Biomarkers: Using $350 pharmacogenomic tests when a 2-minute self-report scale already dictates the optimal path.
  • Treating Mental Disorders as Acute Conditions: Discharging patients without measurement-based care or long-term tracking to monitor for relapse.
  • Implementing Policy on Un-replicated Pilot Data: Making large-scale policy decisions based on preliminary studies with low response rates or thin data.
  • Assuming Geographic Causation: Assuming that because a structurally disadvantaged area has high mental illness rates, the environment caused the illness, ignoring selection bias (migration).

How to use this skill in conversation

When the user is designing a study, evaluating an AI healthcare tool, or discussing mental health policy, surface the relevant Kessler principle or framework by name. For example, if a user proposes a small trial for a new biomarker, invoke the "Massive Sample Sizes for Precision Psychiatry" principle and warn against the anti-pattern of underpowered studies. If they ask about AI replacing doctors, apply "The Centaur Model" to explain why human-computer collaboration is superior. Cite where the idea comes from (e.g., "Ronald C. Kessler argues that..."). Do not pretend to be Kessler; channel his epidemiological rigor and focus on pragmatic, scalable solutions.

© K-Dense-AI, 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 71 other files (references) in mimeographs/ronald-c-kessler of K-Dense-AI/mimeographs.

  • SKILL.md
  • AGENTS.md
  • _workspace/agents_output.e584bd6c.json
  • _workspace/clustered_corpus.e584bd6c.json
  • _workspace/discovery/books.json
  • _workspace/discovery/essays.json
  • _workspace/discovery/frameworks.json
  • _workspace/discovery/interviews.json
  • _workspace/discovery/letters.json
  • _workspace/discovery/papers.json
  • _workspace/discovery/podcasts.json
  • _workspace/discovery/ranked_sources.e584bd6c.json
  • _workspace/discovery/talks.json
  • _workspace/distilled/src_000.e584bd6c.json
  • _workspace/distilled/src_001.e584bd6c.json
  • _workspace/distilled/src_002.e584bd6c.json
  • _workspace/distilled/src_003.e584bd6c.json
  • _workspace/distilled/src_004.e584bd6c.json
  • … and 54 more

Open the folder on GitHubat commit a38f5fc

Compare with similar skills

Ronald C Kessler 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.

Ronald C Kessler compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Ronald C Kessler this skillK-Dense-AI/mimeographs129—~1.6kAutomated safety check: PassMIT
Clinical Protocol Draftingaws-samples/amazon-bedrock-agents-healthcare-lifesciences274—~1.4kAutomated safety check: PassMIT-0
Clinical Researchalirezarezvani/claude-skills28k—~2.7kAutomated safety check: PassMIT
Bio Clinical Biostatistics Adaptive DesignsGPTomics/bioSkills1.2k2 repos~7.7kAutomated safety check: PassMIT
Bio Clinical Biostatistics Power Sample SizeGPTomics/bioSkills1.2k2 repos~7.9kAutomated safety check: PassMIT
Adaptive Trial Simulatoraipoch/medical-research-skills1.9k—~3kAutomated safety check: PassMIT

Similar skills

  • Clinical Protocol Drafting

    aws-samples/amazon-bedrock-agents-healthcare-lifesciences

    Official

    A skill your agent uses when drafting clinical trial protocol sections (objectives, background, study design) grounded in ICH guidelines (E6, E8, E9) and FDA regulations (21 CFR Part 312).

    274 GitHub stars~1.4k tokensUpdated 9 days ago
    Research & ScienceAuto-check passed
  • 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
  • Designs adaptive clinical trials including group-sequential (O'Brien-Fleming, Pocock, Lan-DeMets spending), sample-size re-estimation (blinded Friede-Kieser, unblinded Cui-Hung-Wang, Mehta-Pocock…

    1.2k GitHub starsUsed in 2 repos~7.7k tokens
    Research & ScienceAuto-check passed
  • Computes sample size and power for clinical trials including continuous, binary, and time-to-event endpoints; superiority, non-inferiority, and equivalence designs; FDA 2016 non-inferiority margin…

    1.2k GitHub starsUsed in 2 repos~7.9k tokens
    Research & ScienceAuto-check passed
  • Adaptive Trial Simulator

    aipoch/medical-research-skills

    Design and simulate adaptive clinical trials with interim analyses, decision rules, and operating-characteristic summaries; use when planning adaptive designs or comparing stopping, enrichment, or…

    1.9k GitHub stars~3k tokensUpdated 24 days ago
    Research & ScienceAuto-check passed
  • Clinical Research

    borghei/Claude-Skills

    Clinical study operations — protocol structure, endpoint selection, eligibility design, sample-size and power planning, site feasibility, and documentation readiness.

    891 GitHub stars~3.6k tokensUpdated 4 days ago
    Research & ScienceAuto-check passed

More from K-Dense-AI/mimeographs

All 60 skills in this repo
  • Albert Hofman

    K-Dense-AI/mimeographs

    Applies the epidemiological reasoning and population-health frameworks of Albert Hofman (Harvard epidemiologist, Rotterdam Study).

    129 GitHub stars~1.4k tokensUpdated 1 mo ago
    Auto-check passed
  • Andrew Carnegie

    K-Dense-AI/mimeographs

    Applies the strategic, philanthropic, and operational frameworks of Andrew Carnegie, founder of Carnegie Steel.

    129 GitHub stars~1.5k tokensUpdated 1 mo ago
    Auto-check passed
  • Anne Wojcicki

    K-Dense-AI/mimeographs

    Applies the strategic frameworks and mental models of Anne Wojcicki, co-founder and CEO of 23andMe.

    129 GitHub stars~1.5k tokensUpdated 1 mo ago
    Auto-check passed
  • Aristotle

    K-Dense-AI/mimeographs

    Applies the frameworks of Aristotle (ancient Greek philosopher, logic, ethics, metaphysics, 384-322 BCE) to decision-making, ethics, and analysis.

    129 GitHub stars~1.6k tokensUpdated 1 mo ago
    Auto-check passed
  • Aviv Regev

    K-Dense-AI/mimeographs

    Applies the computational biology and AI-driven reasoning of Aviv Regev (computational biologist, Genentech, single-cell genomics).

    129 GitHub stars~1.4k tokensUpdated 1 mo ago
    Auto-check passed
  • Bill Gates

    K-Dense-AI/mimeographs

    Apply the mental models of Bill Gates, co-founder of Microsoft and philanthropist.

    129 GitHub stars~1.5k tokensUpdated 1 mo ago
    Auto-check passed

Questions about Ronald C Kessler

What does Ronald C Kessler do?

This skill applies the analytical frameworks of Ronald C. An agent skill from K-Dense-AI/mimeographs. Ronald C Kessler is an agent skill from K-Dense-AI/mimeographs. This skill applies the analytical frameworks of Ronald C.

When should I use Ronald C Kessler?

Ronald C Kessler fits situations like: you are designing clinical trials; evaluating mental health interventions; analyzing epidemiological survey data; building clinical decision support algorithms.

How do I install Ronald C Kessler in Claude Code?

Run `npx skills add K-Dense-AI/mimeographs --skill ronald-c-kessler -a claude-code`. Or copy the skill folder (mimeographs/ronald-c-kessler in K-Dense-AI/mimeographs) into .claude/skills/ronald-c-kessler in your project. Claude Code loads it when a task matches its description.

How do I install Ronald C Kessler in Codex?

Run `npx skills add K-Dense-AI/mimeographs --skill ronald-c-kessler -a codex`. Or copy the skill folder (mimeographs/ronald-c-kessler in K-Dense-AI/mimeographs) into .agents/skills/ronald-c-kessler in your project. Codex loads it when a task matches its description.

Can I use Ronald C Kessler 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 K-Dense-AI/mimeographs --skill ronald-c-kessler -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/ronald-c-kessler, .gemini/skills/ronald-c-kessler, .github/skills/ronald-c-kessler and .opencode/skills/ronald-c-kessler in your project.

What does Ronald C Kessler need to run?

SKILL.md names no scripts, command-line tools or credentials: Ronald C Kessler is instructions for the agent only.

Does Ronald C Kessler 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 Ronald C Kessler 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 Ronald C Kessler use?

Ronald C Kessler 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 Ronald C Kessler use?

About 1.6k tokens (SKILL.md is roughly 6.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 3.9k tokens, read only when the agent opens those files.

What are the alternatives to Ronald C Kessler?

Skills that share tags, products or a category with Ronald C Kessler: Clinical Protocol Drafting (aws-samples/amazon-bedrock-agents-healthcare-lifesciences, 274 stars), Clinical Research (alirezarezvani/claude-skills, 28k stars), Bio Clinical Biostatistics Adaptive Designs (GPTomics/bioSkills, 1.2k stars) and Bio Clinical Biostatistics Power Sample Size (GPTomics/bioSkills, 1.2k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Ronald C Kessler?

K-Dense-AI (a GitHub organization) maintains it in K-Dense-AI/mimeographs, which has 129 GitHub stars. The repository holds 60 skills in this directory. The repository was last updated on August 18, 2026.

Source: K-Dense-AI/mimeographs on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.