Audit course objectives against five adversarial dimensions and output a confidence score.
npx skills add https://github.com/savvides/idstack --skill red-team-savvides
Please help me install this Agent Skill. Skill: red-team Source: https://github.com/savvides/idstack/tree/main/red-team Command: npx skills add https://github.com/savvides/idstack --skill red-team-savvides
Adversarial course design audit across five dimensions—alignment stress test, evidence verification, cognitive load analysis, learner persona simulation, and prerequisite chain integrity—produces a confidence score that helps identify structural weaknesses early and guide remediation.
Run /red-team to start the adversarial audit against your course manifest and export results to .idstack/project.json.
High-intent search queries and answers about installing and using this skill.
An adversarial course design audit challenges every objective-assessment pair across five dimensions: alignment, evidence, cognitive load, learner personas, and prerequisite chain integrity, producing a consolidated confidence score to identify structural weaknesses.
Cognitive load analysis in course quality assurance evaluates whether the instructional design overwhelms the learner by simulating learner personas and stress-testing the prerequisite chain integrity within the course manifest.
Evidence verification in a course manifest involves adversarially challenging objective-assessment pairs to ensure the assessments actually produce valid evidence of learning, which is then compiled into a structured red-team audit report.
Yes, the adversarial audit works standalone or reads directly from the idstack project manifest to simulate learner personas and validate prerequisite chains without requiring external dependencies.
The best way to calculate a quality assurance confidence score is applying an adversarial red-team evaluation across alignment, evidence, cognitive load, personas, and prerequisites to expose hidden flaws and guide remediation.
You export red-team audit findings by writing the structured audit report, including the consolidated confidence score and actionable findings, directly to the .idstack/project.json manifest for stakeholder traceability.
92Bilal26Generate YAML-ready learning objectives aligned with Bloom's taxonomy and CEFR levels.
savvidesAudit online course quality against QM standards and the Community of Inquiry framework.
savvidesMap LMS course data into idstack manifests with Bloom's taxonomy classification.
lhohanEvaluate Claude Code skills across eight dimensions and generate improvement reports.
