Loading...
Loading...
Found 24 Skills
Write the minimal production code needed to make all existing failing tests pass. No extra features, no test modifications, no refactoring. Use after tests are written and confirmed failing.
Test-driven development with strict RED-GREEN-REFACTOR enforcement. Enforces: write failing test first, minimal implementation, then refactor. Use when adding new features or fixing bugs.
Use when implementing any feature or bugfix, before writing implementation code
QA validation and fix loop workflow — validates implementation completeness then iterates fix cycles until all acceptance criteria pass and quality gates clear
Write test files driven by acceptance criteria in strict TDD mode. No production code is generated. Use after the low-level design is approved.
Use when writing any code - enforces test-driven development discipline with RED-GREEN-REFACTOR cycle, fires during any coding task
Red-green-refactor discipline. Use when writing new functionality.
Methodology for effective AI-assisted software development. Use when helping users build software with AI coding assistants, debugging AI-generated code, planning features for AI implementation, managing version control in AI workflows, or when users mention "vibe coding," Cursor, Windsurf, or similar AI coding tools. Provides strategies for planning, testing, debugging, and iterating on code written with LLM assistance.
TDD London School workflow -- mock-first, outside-in test development
Use when finishing a ticket or pull request and the user asks to validate, demo, or sign off on delivered behavior, including non-user-facing changes. Triggers include "UAT", "verify", "walk me through", "show what changed", "can we merge?", "sign off", "acceptance test", "demo this", "ready to merge", "validate the changes", "show me it works", and similar phrases indicating a need for an acceptance walkthrough or demonstration before merge.
Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always
Reproduce a bug from a Linear ticket with a failing test. Expects the full ticket context (title, description, comments) to be provided as input.