Test Skill
Skill Verifiziert AktivUse when creating or editing skills, before deployment, to verify they work under pressure and resist rationalization - applies RED-GREEN-REFACTOR cycle to process documentation by running baseline without skill, writing to address failures, iterating to close loopholes
To enforce discipline and quality in AI skill development by applying TDD principles, ensuring skills are robust, compliant, and resist rationalization under pressure.
Funktionen
- Applies RED-GREEN-REFACTOR cycle to skill documentation
- Provides methodology for baseline testing and failure documentation
- Guides writing minimal skills to address observed failures
- Details pressure testing scenarios to verify compliance
- Offers guidance on refactoring to close loopholes and prevent rationalization
Anwendungsfälle
- When creating or editing skills before deployment to verify their robustness.
- When needing to enforce discipline and quality in AI skill development.
- When skills have compliance costs or could be rationalized away.
- To ensure skills prevent specific, documented failures.
Nicht-Ziele
- Testing pure reference skills (API docs, syntax guides).
- Testing skills without rules to violate.
- Testing skills where agents have no incentive to bypass rules.
- Replacing foundational TDD knowledge; assumes understanding of the RED-GREEN-REFACTOR cycle.
Workflow
- Create pressure scenarios for the skill.
- Run scenarios WITHOUT the skill (RED phase) to document failures.
- Write the skill to address specific documented failures (GREEN phase).
- Re-test scenarios WITH the skill to verify compliance.
- Identify new rationalizations or loopholes.
- Refactor the skill to close loopholes and add counters (REFACTOR phase).
- Re-verify compliance and meta-test clarity.
Praktiken
- Test-driven development
- Process documentation
- Quality assurance
Voraussetzungen
- Understanding of superpowers:test-driven-development skill.
- Access to context-engineering-kit in Claude Code.
Installation
Zuerst Marketplace hinzufügen
/plugin marketplace add NeoLabHQ/context-engineering-kit/plugin install customaize-agent@context-engineering-kitQualitätspunktzahl
VerifiziertVertrauenssignale
Ähnliche Erweiterungen
Teach Guidance
100Guide a person in becoming a better teacher and explainer. AI coaches content structuring, audience calibration, explanation clarity, Socratic questioning technique, feedback interpretation, and reflective practice for technical presentations, documentation, and mentoring. Use when a person needs to present technical content and wants preparation coaching, wants to write better documentation or tutorials, struggles to explain concepts across expertise levels, is mentoring a colleague, or is preparing for a talk or knowledge-sharing session.
Prepare Inspection Readiness
100Prepare an organisation for regulatory inspection by assessing readiness against agency-specific focus areas (FDA, EMA, MHRA). Covers warning letter and 483 theme analysis, mock inspection protocols, document bundle preparation, inspection logistics, and response template creation. Use when a regulatory inspection has been announced or is anticipated, when a periodic self-assessment is due, when new systems have been implemented since the last inspection, or after a significant audit finding that may attract regulatory attention.
External Context
100Invoke parallel document-specialist agents for external web searches and documentation lookup
Deepinit
100Deep codebase initialization with hierarchical AGENTS.md documentation
Readme I18n
100Nutzen Sie dies, wenn der Benutzer eine Repository-README übersetzen, ein Repository mehrsprachig machen, Dokumentationen lokalisieren, einen Sprachumschalter hinzufügen, die README internationalisieren oder lokalisierte README-Varianten in einem GitHub-ähnlichen Repository aktualisieren möchte.
Next Cache Components
100Next.js 16 Cache Components – PPR, use cache directive, cacheLife, cacheTag, updateTag