Generate counter-arguments to challenge analysis before finalizing conclusions.
npx skills add https://github.com/cris-m/flopsy --skill self-critique-cris-m
Please help me install this Agent Skill. Skill: self-critique Source: https://github.com/cris-m/flopsy/tree/main/src/team/templates/skills/self-critique Command: npx skills add https://github.com/cris-m/flopsy --skill self-critique-cris-m
This Skill helps you identify and challenge your own reasoning before presenting conclusions, reducing overconfidence and blind spots.
Provide your current conclusion and prompt for a self-critique to uncover at least two substantial counter-arguments.
High-intent search queries and answers about installing and using this skill.
Self-critique challenges your analysis by generating counter-arguments before finalizing a stance. You provide a drafted interpretation or recommendation, and the workflow pauses to surface underlying assumptions, counter-evidence, and potential biases.
Confidence calibration adjusts your certainty level by actively checking for biases and counter-evidence. It is needed during high-stakes decisions, research reporting, and policy discussions to reduce overconfidence and blind spots in your conclusions.
To generate counter-arguments, input your current conclusion into the self-critique workflow. The process forces an evaluation pause to uncover at least two substantial counter-arguments, surfacing hidden assumptions and checking biases before you commit.
Yes, self-critique is designed for analysis-heavy tasks including research reporting and policy discussions. It provides a structured workflow to draft interpretations, pause for evaluation, and generate counter-arguments to strengthen your final recommendations.
The best way to surface hidden assumptions is applying a structured self-critique workflow after drafting an interpretation. By forcing counter-argument generation before finalizing a stance, you expose underlying biases and counter-evidence.
No external dependencies are required. The self-critique workflow operates through a frontmatter-defined entry point, though it can optionally reference scripts, references, and assets to support the structured evaluation process.
yin52133Analyze structured inputs to produce evidence-based conclusions with risk and confidence.
human-avatarCalibrates stated confidence percentages by auditing evidence and counter-evidence for falsifiable claims.
bykoleksii-hardoApply advanced scoring, bias mitigation, and confidence calibration to LLM outputs.
toilahuonggAnalyze arguments, detect fallacies, and evaluate claims using structured reasoning frameworks.
