critical-thinking-bias-check
Skill28 starsChanged 8 months agoMITView on GitHub
In this repository105 other files it gives its agents.
- acceptance-criteria-writerSkill
- ambiguity-hunterSkill
- as-is-process-investigatorSkill
- assumption-extractorSkill
- assumptions-constraints-logSkill
- benefit-hypothesis-writerSkill
- breakout-structure-designerSkill
- business-problem-framingSkill
- business-rule-extractorSkill
- catwoe-root-definitionSkill
- constraint-detectorSkill
- definition-of-done-drafterSkill
- deliverable-consistency-checkSkill
- edge-case-elicitorSkill
- evidence-gap-reviewSkill
- functional-vs-nonfunctional-splitterSkill
- interview-designSkill
- moscow-prioritisationSkill
- observation-study-planSkill
- pestle-analysisSkill
- porters-five-forcesSkill
- power-interest-gridSkill
- probe-question-generatorSkill
- problem-statement-refinerSkill
- process-modelling-and-improvementSkill
- process-model-specSkill
- proto-requirements-normalizerSkill
- prototype-elicitationSkill
- pyramid-funnel-diamond-interviewerSkill
- questionnaire-designSkill
- questionnaire-pilot-checkerSkill
- raci-matrixSkill
- raci-rasci-builderSkill
- requirements-conflict-checkerSkill
- requirements-elicitationSkill
- requirements-gap-auditorSkill
- requirements-interrogatorSkill
- requirements-packagerSkill
- requirements-prioritizerSkill
- requirements-quality-checkSkill
- requirements-traceability-starterSkill
- see-i-clarifierSkill
- ssm-analysisSkill
- stakeholder-analysisSkill
- stakeholder-communication-plannerSkill
- stakeholder-registerSkill
- strategy-analysisSkill
- swot-prioritisationSkill
- to-be-process-designerSkill
- use-case-specificationSkill
- value-proposition-analysisSkill
- workshop-designSkill
- acceptance-criteria-writerSkill
- ambiguity-hunterSkill
- as-is-process-investigatorSkill
- assumption-extractorSkill
- assumptions-constraints-logSkill
- benefit-hypothesis-writerSkill
- breakout-structure-designerSkill
- business-problem-framingSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
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 16
Look for omissions, contradictions, weak assumptions, and vague language.
- Distinctive: line 30
Do not rewrite the whole artifact unless necessary.
- Distinctive: line 32
Prefer explainable quality gates.
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Purpose
Detect biased reasoning, oversimplification, hidden assumptions, and weak logic.
Use when
- the analysis feels too neat
- a preferred solution may be biasing the work
- critical review is required before decisions
Inputs
- artifact or analysis output under review
- source material and assumptions
- project context and quality bar
Procedure
- Inspect the artifact systematically.
- Look for omissions, contradictions, weak assumptions, and vague language.
- Distinguish evidence-backed claims from inference.
- Record issues by severity.
- Recommend targeted fixes, not generic criticism.
- Re-state what would make the artifact review-ready.
Outputs
- bias and assumption log
- rival interpretations
- logic weaknesses
- revised decision notes
Guardrails
- Be concrete.
- Do not rewrite the whole artifact unless necessary.
- Focus on the highest-leverage defects first.
- Prefer explainable quality gates.
Completion criteria
- key defects identified
- fixes proposed
- pass/fail or ready/not-ready decision given
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.

