Loading...
Loading...
Found 2,348 Skills
Debug Streamlit frontend and backend changes using make debug with hot-reload. Use when testing code changes, investigating bugs, checking UI behavior, or needing screenshots of the running app.
Use when coordinating software development projects requiring multiple specialists (architect, developers, mathematician, statistician, notebook-writer) with quality gates for archival setup, requirements, architecture, pre-mortem, code review, testing, and version control integration.
Create or update repository README.md files with concise, human-skimmable structure and verified metadata. Use when writing or refreshing README content, adding or correcting badges, documenting stack and deployment/services, and explicitly reporting testing coverage (unit, integration, e2e api, e2e web) plus CI execution status.
Autonomous build-phase orchestrator. Manages slice queue, TDD pair dispatch, full-team code review, mutation testing, CI integration, and auto-merge with quality gates. Replaces manual coordinator overhead during build phase. Activate when running factory mode with ensemble-team.
Three-layer Vitest-BDD Skill for DashPlayer. Use this when developers want business-readable BDD scenarios without coupling scenario writing to code implementation details. Trigger keywords: "Three-layer BDD", "Behavioral Testing Layering", "Given-When-Then", "Vitest BDD", "Avoid writing implementations in scenarios".
PHPUnit testing conventions and best practices for any PHP project
First-principles thinking; identify what everything else builds on. Use when a learner feels like they're memorizing rather than understanding, wants to distinguish foundational from derived concepts, or needs to reconstruct knowledge from basics. This skill guides through dependency testing (elimination, reconstruction, abstraction descent) while enforcing human-only reasoning about what's core vs. derived. Triggers on phrases like "I'm memorizing not understanding", "what's really foundational", "I can use it but don't understand why", "distinguish core from derived", or when a learner wants deeper understanding of first principles.
Guides users through structured three-stage collaborative documentation workflow including context gathering, iterative refinement, and reader testing. Use when asked to "write a doc", "draft a proposal", "create a spec", "write technical documentation", "create a PRD", or "draft an RFC". Implements systematic approach for PRDs, design docs, decision docs, technical specs, and proposals through clarifying questions, section-by-section iteration, and fresh-eye validation. Works with markdown documentation, technical specifications, and structured writing projects.
Provides reflective questioning framework to challenge assumptions about work completeness, catching incomplete implementations before they're marked "done". Use before claiming features complete, before moving ADRs to completed status, during self-review, or when declaring work finished. Triggers on "is this really done", "self-review my work", "challenge my assumptions", "verify completeness", or proactively before marking tasks complete. Works with any type of implementation work. Enforces critical thinking about integration, testing, and execution proof.
Configures comprehensive testing in Gradle including JUnit 5, TestContainers, test separation (unit vs integration), and code coverage with JaCoCo. Use when asked to "set up JUnit 5", "configure TestContainers", "separate integration tests", or "add code coverage". Works with build.gradle.kts, test source sets, and CI/CD configurations.
Create comprehensive unit tests, integration tests, and end-to-end tests using pytest for Python projects. Specializes in FastAPI testing with TestClient, async testing with pytest-asyncio, SQLModel/SQLAlchemy database testing, fixture generation, and test configuration setup. Use when you need test coverage, want to implement TDD/BDD, create test suites for functions or API endpoints, add edge case testing, or improve code quality with automated testing. Triggers include requests like "write tests for this module", "create pytest fixtures", "test this FastAPI endpoint", "setup pytest configuration", or "generate test file".
Implement comprehensive evaluation strategies for LLM applications using automated metrics, human feedback, and benchmarking. Use when testing LLM performance, measuring AI application quality, or establishing evaluation frameworks.