critical-thinking
Skill0 starsChanged 9 days agoMITView on GitHub
Challenge what you think is right — alternative hypotheses, missing data, evidence quality, bias detection, falsifiability, and adversarial review
22 other projects use a version of this.
Adopted by
Most recently taken up by
- coji/natural-japanesetheir own version, first seen Nov 8, 2026
- pradyumnasagar/open-research-skillstheir own version, first seen Nov 8, 2026
- tovrleaf/openkatatheir own version, first seen Nov 1, 2026
- GiangGiangTran/ba-skillstheir own version, first seen Oct 20, 2026
- tronghieu/agent-skillstheir own version, first seen Oct 18, 2026
- mia-cx/skillstheir own version, first seen Oct 16, 2026
Other versions22 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 22
- coji/natural-japanese★ 2ksame name
- TheGoat395/Codex-Skills★ 136same name
- tronghieu/agent-skills★ 94same name
- ysskrishna/ai-agent-skills★ 20same name
- mlevison/agent-thinking-skills★ 18same name
- deciqAI/knowledge-skills★ 13same name
- GiangGiangTran/ba-skills★ 8same name
- pradyumnasagar/open-research-skills★ 8same name
- Johna2an/critical-thinking★ 5same name
- Cogni-AI-OU/cogni-ai-agent-skills★ 4same name
12 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository66 other files it gives its agents.
- AGENTS.mdAGENTS.md
- skills/bootstrap-project/resources/AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- skills/bootstrap-project/resources/CLAUDE.mdCLAUDE.md
- act-tenetsSkill
- adversarial-reviewSkill
- annotate-screenshotSkill
- anti-hallucinationSkill
- ascii-chartSkill
- assess-brainSkill
- big-ideaSkill
- bootstrap-coreSkill
- bootstrap-projectSkill
- browser-toolsSkill
- chart-big-ideaSkill
- chart-interpretationSkill
- chart-vocabularySkill
- code-reviewSkill
- communication-craftSkill
- compile-brainSkill
- convertSkill
- corpus-qa-sweepSkill
- deep-reviewSkill
- doc-hygieneSkill
- docs-shellSkill
- docx-to-mdSkill
- ethical-reasoningSkill
- evaluate-before-adoptingSkill
- figure-generatorSkill
- flint-chartSkill
- flint-interactionsSkill
- flint-themeSkill
- git-workflowSkill
- html-to-mdSkill
- humanizerSkill
- install-visual-companionsSkill
- lint-clean-markdownSkill
- markdown-mermaidSkill
- markdown-sanitization-chainSkill
- md-to-emlSkill
- md-to-htmlSkill
- md-to-txtSkill
- md-to-wordSkill
- meditationSkill
- mutation-testingSkill
- planSkill
- platform-awarenessSkill
- print-svg-style-guideSkill
- proactive-awarenessSkill
- problem-framing-auditSkill
- project-capability-authoringSkill
- project-statusSkill
- render-chartSkill
- render-verifySkill
- rich-emailSkill
- risk-analysisSkill
- security-and-hardeningSkill
- setup-dependenciesSkill
- setup-enterprise-stackSkill
- spikeSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
1 rule. 0 are common, 1 is distinctive, and 0 are very specific to this project.
0
Common
Most of the 20 edited versions we read keep these.
1
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 30
Use act-pass mode. Produce grounded alternatives, explicit disconfirmers, and evidence-scoped commitment when stakes warrant them.
“Common” is measured: kept by at least 6 in 10 of the 20 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Critical Thinking
Materiality first: trivial mechanical work exits cheaply. For material work, audit the frame before solving. Preserve the ten-tenet canon; a procedure is not a new canon.
Modes
Load only the selected methods/reference, not the entire family:
| Mode | Canonical procedure |
| act-pass (default) | Seven-step pass: materiality, hypothesis, alternatives, disconfirmers, priors, severity, commit |
| reasoning | Evidence and reasoning methods plus resident reasoning contract |
| framing | Step-back method and frame/output boundary |
| instruction-preconditions | Instruction precondition audit within applicable authority and safety boundaries |
| adversarial | Adversarial methods; general decisions need no code diff |
| curation | Curation-specific risk reference, not a universal release authority |
For medium stakes, state grounded alternatives and an explicit disconfirmer; for high stakes use the full pass and evidence-scoped commitment. Do not manufacture disagreement or require a fixed number of agents. Native Plan/research and available critics provide mechanics, not the ACT contract. Use direct analysis for evidence that fits the current context.
If rules conflict, report the conflict and resolve the material decision with the user; do not silently choose the shorter or more permissive rule. Report missing references and do not claim the selected pass ran. This workflow does not authorize file edits, external actions, or publication.
Compatibility command constraints: critical-thinking
Use act-pass mode. Produce grounded alternatives, explicit disconfirmers, and evidence-scoped commitment when stakes warrant them; exit cheaply on trivia.
Runtime contract references
Load only the reference selected by the triggering instruction; do not replay all runtime contracts for unrelated work. These references add no authority and do not call the instruction again.
- act-pass: act-pass
- reasoning: critical-thinking
- framing: problem-framing-audit
- instruction-preconditions: system-prompt-skepticism
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.