New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Thinking Scientific Method

by tjboudreaux in tjboudreaux/cc-thinking-skills

When a symptom has several plausible causes, rank falsifiable hypotheses and run the cheapest discriminating observation first; prefer least-assumptive survivors only after evidence fit.

MITAuto-check passed

Install Thinking Scientific Method

skills CLI
$ npx skills add tjboudreaux/cc-thinking-skills --skill thinking-scientific-method -a claude-code

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

GitHub CLI
$ gh skill install tjboudreaux/cc-thinking-skills thinking-scientific-method --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/tjboudreaux/cc-thinking-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/thinking-scientific-method .claude/skills/thinking-scientific-method && 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
thinking-scientific-method
GitHub stars
1.6k
Token cost
~1.1k tokens
SKILL.md length
502 words
Files
1
Skills in repo
26
Repo updated
First seen
Licence
MIT

At a glance

When a symptom has several plausible causes, rank falsifiable hypotheses and run the cheapest discriminating observation first; prefer least-assumptive survivors only after evidence fit.

  • Works in 6 steps: State the symptom precisely. Capture… → Enumerate 2–5 competing hypotheses. Name… → Name falsifiers and cheap observations… → …
  • SKILL.md covers When to Use, When NOT to Use, Procedure and Output, plus 1 more section
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Thinking Scientific Method is an agent skill from tjboudreaux/cc-thinking-skills. When a symptom has several plausible causes, rank falsifiable hypotheses and run the cheapest discriminating observation first; prefer least-assumptive survivors only after evidence fit.

Its SKILL.md is about 1.1k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The repository describes itself as: 28 eval-informed mental models and critical-thinking skills for Claude Code, GitHub Copilot, Codex, Cursor, and other Agent Skills-compatible tools. The licence is MIT.

Example prompts

  • “/thinking-scientific-method”

Workflow steps

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

  1. State the symptom precisely. Capture failing behavior, scope, timing, environment, and constraints. Separate observation from…
  2. Enumerate 2–5 competing hypotheses. Name specific files, functions, configs, input conditions, or invariants. Reject vague buckets…
  3. Name falsifiers and cheap observations before looking. For each hypothesis: what result drops it, and what read/grep/diff/log/test check…
  4. Rank observations by discrimination × cheapness. Run the cheapest check that best separates the top contenders. Do not deep-dive the…
  5. Update after each observation. Drop falsified hypotheses. Among survivors that still fit all evidence, prefer the one with the fewest…
  6. Localize and stop. When one hypothesis has direct supporting evidence and key alternatives are ruled out, name the file/function/config to…

What it can do on your machine

Read from SKILL.md and the folder at commit 7b8fece. 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

Thinking Scientific Method loads about 1.1k tokens when it runs. Until then it costs about 53 tokens; SKILL.md has 502 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~53
When it runs · the whole SKILL.md, loaded when a task matches
~1.1k

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 tjboudreaux/cc-thinking-skills at commit 7b8fece, republished under its MIT licence (© tjboudreaux). 502 words, ~1,072 tokens.

Download SKILL.mdSave it as .claude/skills/thinking-scientific-method/SKILL.md (or your agent's skills folder).
name
thinking-scientific-method
description
When a symptom has several plausible causes, rank falsifiable hypotheses and run the cheapest discriminating observation first; prefer least-assumptive survivors only after evidence fit.
disable-model-invocation
true

Scientific Method (Hypothesis Differential)

When a symptom could come from several places, enumerate competing falsifiable hypotheses and spend the cheapest observation on the one that best discriminates among them. After each observation, keep only hypotheses that still fit, then prefer the survivor with the fewest unsupported assumptions as the working explanation.

When to Use

  • A bug, incident, or anomaly has more than one plausible cause.
  • You can observe code, logs, diffs, traces, tests, configs, or data now.
  • You must localize the faulty file, function, branch, config, or invariant before fixing.
  • Competing explanations fit the same surface facts and you need a discriminating check.

When NOT to Use

  • Cause is already obvious from a single stack, failing test, or recent diff — fix directly.
  • Only one plausible hypothesis exists — test it; do not invent rivals for ritual.
  • No observation is possible yet — obtain access first; do not speculate a localization.
  • Multi-week experiments, product A/B tests, or policy trials — this skill is for agent-now checks.
  • Fault is already localized and you need systemic root/prevention depth — use five-whys-plus.
  • Selective "only these objects/times" defects better suited to IS/IS-NOT comparison — use Kepner-Tregoe.
  • Representation (doc/dashboard) may be stale versus reality — verify territory with map-territory first, then resume hypotheses.

Procedure

  1. State the symptom precisely. Capture failing behavior, scope, timing, environment, and constraints. Separate observation from interpretation.
  2. Enumerate 2–5 competing hypotheses. Name specific files, functions, configs, input conditions, or invariants. Reject vague buckets ("backend issue"). If no serious alternative remains after a deliberate check, exit this differential and test or fix the sole evidenced cause directly; never fabricate a rival to continue the procedure.
  3. Name falsifiers and cheap observations before looking. For each hypothesis: what result drops it, and what read/grep/diff/log/test check can you run now. Prefer observations available immediately over deploys, canaries, or long waits.
  4. Rank observations by discrimination × cheapness. Run the cheapest check that best separates the top contenders. Do not deep-dive the favorite first if a cheap cross-check would kill alternatives.
  5. Update after each observation. Drop falsified hypotheses. Among survivors that still fit all evidence, prefer the one with the fewest independent unsupported assumptions (extra components, rare timing, external dependencies). Parsimony ranks survivors after fit; it never rescues a leaner hypothesis that evidence already contradicts. Escalate complexity only when simpler survivors are ruled out.
  6. Localize and stop. When one hypothesis has direct supporting evidence and key alternatives are ruled out, name the file/function/config to change and the evidence that localizes it. Stop analyzing once localization is direct.
Show full SKILL.md (85 more words)Show less

Output

text
Symptom: <specific failing behavior, scope, timing>
Hypotheses:
  H1: <specific cause> | Why plausible | Observation | Falsified if
  H2: ...
  H3: ...
Test order: <cheapest discriminating checks>
Results: <what each observation showed>
Survivors: <remaining Hs; least-assumptive working pick among fit>
Localized fault: <file/function/config + supporting evidence>
Ruled out: <Hs dropped and why>

Verification

  • Falsify the differential conclusion if you continued with fewer than two serious hypotheses, if no pre-stated falsifier existed, if a cheaper discriminating check was skipped, or if a "simpler" story was kept after evidence contradicted it.
  • Stop when the fault is directly localized and alternatives that matter are ruled out; do not continue theorizing.
  • Over-application guard: do not narrate observe→question without competing causes; do not treat fewest assumptions as proof; do not run this skill when a single obvious cause is already evidenced.

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

Files

Just SKILL.md in skills/thinking-scientific-method of tjboudreaux/cc-thinking-skills.

Open the folder on GitHubat commit 7b8fece

Compare with similar skills

Thinking Scientific Method 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.

Thinking Scientific Method compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Thinking Scientific Method this skilltjboudreaux/cc-thinking-skills1.6k—~1.1kAutomated safety check: PassMIT
Scientific Thinking Literature Reviewaffaan-m/ECC276k1 repos~1.3kAutomated safety check: PassMIT
Scientific Critical ThinkingK-Dense-AI/scientific-agent-skills48k1 repos~3.3kAutomated safety check: PassMIT
Scientific Thinking Scholar Evaluationaffaan-m/ECC276k1 repos~1.2kAutomated safety check: PassMIT
Scientific Thinking Literature Reviewaffaan-m/ECC276k—~734Automated safety check: PassMIT
Scientific Thinking Scholar Evaluationaffaan-m/ECC276k—~610Automated safety check: PassMIT

Similar skills

  • Scientific Thinking Literature Review

    affaan-m/ECC

    Systematic literature-review workflow for academic, biomedical, technical, and scientific topics, including search planning, source screening, synthesis, citation checks, and evidence logging.

    276k GitHub starsUsed in 1 repo~1.3k tokens
    Research & ScienceAuto-check passed

  • Scientific Critical Thinking

    K-Dense-AI/scientific-agent-skills

    Evaluates scientific claims and evidence quality. An agent skill from K-Dense-AI/scientific-agent-skills.

    48k GitHub starsUsed in 1 repo~3.3k tokens
    Research & ScienceAuto-check passed

  • Scientific Thinking Scholar Evaluation

    affaan-m/ECC

    Structured scholarly-work evaluation for papers, proposals, literature reviews, methods sections, evidence quality, citation support, and research-writing feedback.

    276k GitHub starsUsed in 1 repo~1.2k tokens
    Research & ScienceAuto-check passed

  • Scientific Thinking Literature Review

    affaan-m/ECC

    学術、生物医学、技術、科学的なトピックに対するシステマティックな文献レビューワークフロー。検索計画、ソースのスクリーニング、統合、引用確認、証拠ログを含む。

    276k GitHub stars~734 tokensUpdated 4 days ago
    Research & ScienceAuto-check passed

  • Scientific Thinking Scholar Evaluation

    affaan-m/ECC

    論文、提案書、文献レビュー、方法論セクション、証拠の質、引用サポート、研究論文フィードバックのための構造化された学術的作業評価。

    276k GitHub stars~610 tokensUpdated 4 days ago
    Research & ScienceAuto-check passed

  • Falsify

    sickn33/agentic-awesome-skills

    The scientific thinking protocol for AI agents. An agent skill from sickn33/agentic-awesome-skills.

    47k GitHub starsUsed in 1 repo~7.7k tokens
    Auto-check passed

More from tjboudreaux/cc-thinking-skills

All 26 skills in this repo

  • Thinking Bounded Rationality

    tjboudreaux/cc-thinking-skills

    A skill your agent uses when search or investigation could run forever.

    1.6k GitHub stars~703 tokensUpdated 2 mo ago
    Auto-check passed

  • Thinking Circle Of Competence

    tjboudreaux/cc-thinking-skills

    A skill your agent uses when a specific claim may lack grounding.

    1.6k GitHub stars~733 tokensUpdated 2 mo ago
    Auto-check passed

  • Thinking Lindy Effect

    tjboudreaux/cc-thinking-skills

    A skill your agent uses when longevity of a non-perishable option matters.

    1.6k GitHub stars~650 tokensUpdated 2 mo ago
    Auto-check passed

  • Thinking Via Negativa

    tjboudreaux/cc-thinking-skills

    A skill your agent uses when the reflex is to add a feature, layer, or process.

    1.6k GitHub stars~735 tokensUpdated 2 mo ago
    Auto-check passed

  • Thinking Cynefin

    tjboudreaux/cc-thinking-skills

    When the right response mode is unclear, classify the cause-effect domain first; decompose disorder.

    1.6k GitHub stars~651 tokensUpdated 2 mo ago
    Auto-check passed

  • Thinking Five Whys Plus

    tjboudreaux/cc-thinking-skills

    When a fault is localized and the proximate cause is known but the systemic root is not, chain evidence-linked whys with a counterfactual stop and a countermeasure.

    1.6k GitHub stars~881 tokensUpdated 2 mo ago
    Auto-check passed

Questions about Thinking Scientific Method

What does Thinking Scientific Method do?

When a symptom has several plausible causes, rank falsifiable hypotheses and run the cheapest discriminating observation first; prefer least-assumptive survivors only after evidence fit. Thinking Scientific Method is an agent skill from tjboudreaux/cc-thinking-skills. When a symptom has several plausible causes, rank falsifiable hypotheses and run the cheapest discriminating observation first; prefer least-assumptive survivors only after evidence fit.

How do I install Thinking Scientific Method in Claude Code?

Run `npx skills add tjboudreaux/cc-thinking-skills --skill thinking-scientific-method -a claude-code`. Or copy the skill folder (skills/thinking-scientific-method in tjboudreaux/cc-thinking-skills) into .claude/skills/thinking-scientific-method in your project. Claude Code loads it when a task matches its description.

How do I install Thinking Scientific Method in Codex?

Run `npx skills add tjboudreaux/cc-thinking-skills --skill thinking-scientific-method -a codex`. Or copy the skill folder (skills/thinking-scientific-method in tjboudreaux/cc-thinking-skills) into .agents/skills/thinking-scientific-method in your project. Codex loads it when a task matches its description.

Can I use Thinking Scientific Method 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 tjboudreaux/cc-thinking-skills --skill thinking-scientific-method -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/thinking-scientific-method, .gemini/skills/thinking-scientific-method, .github/skills/thinking-scientific-method and .opencode/skills/thinking-scientific-method in your project.

What does Thinking Scientific Method need to run?

SKILL.md names no scripts, command-line tools or credentials: Thinking Scientific Method is instructions for the agent only.

Does Thinking Scientific Method 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 Thinking Scientific Method 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 Thinking Scientific Method use?

Thinking Scientific Method 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 Thinking Scientific Method use?

About 1.1k tokens (SKILL.md is roughly 4.3k 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 Thinking Scientific Method?

Skills that share tags, products or a category with Thinking Scientific Method: Scientific Thinking Literature Review (affaan-m/ECC, 276k stars), Scientific Critical Thinking (K-Dense-AI/scientific-agent-skills, 48k stars), Scientific Thinking Scholar Evaluation (affaan-m/ECC, 276k stars) and Scientific Thinking Literature Review (affaan-m/ECC, 276k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Thinking Scientific Method?

tjboudreaux (a GitHub user) maintains it in tjboudreaux/cc-thinking-skills, which has 1,612 GitHub stars. The repository holds 26 skills in this directory. The repository was last updated on August 7, 2026.

Source: tjboudreaux/cc-thinking-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.