Test Cases and Acceptance Validation
Design test cases based on confirmed requirements and real failure mechanisms, clearly distinguishing between case design, red test handoff, validation, and authorized fix closed loops.
MIT | v1.1.0Start with the task you need to finish. Compare instructions, compatibility, and licenses before downloading; recommended skills open the original project instead.
Design test cases based on confirmed requirements and real failure mechanisms, clearly distinguishing between case design, red test handoff, validation, and authorized fix closed loops.
MIT | v1.1.0Coordinate development, testing, defect fixes, regression, and review based on confirmed requirements and implementable designs. Assess delivery status using complete user tasks and evidence.
MIT | v1.1.0Reproduce the failure, trace the first broken rule along the real execution path, and then validate the minimal fix within the authorized scope.
MIT | v1.0.0Perform a read-only review of PR, commits, branches, or workspace differences, trace callers, verify requirements, and provide evidence-based findings. The default is an in-depth Solo review.
MIT | v1.0.0A design language for AI programming agents: 24 design commands, real-time browser iteration, and 61 deterministic detection rules for identifying cookie-cutter, AI-generated front-end designs.
Apache-2.0Investigate the current behavior and, before design begins, organize the goals into confirmed product requirements, clear decisions, and acceptance criteria.
MIT | v1.1.0Write or review actionable development, database, and interface designs. First verify key mechanisms, affected entry points, cross-layer contracts, and failure recovery, then determine whether the handoff is ready.
MIT | v1.1.0Agent Skills that provide artistic direction, reference images, and browser inspection for programming agents, aiming to create distinctive front-end designs rather than generic AI-styled pages.
MITA locally pre-indexed code knowledge graph for programming agents, automatically synchronized after code changes, aiming to reduce token usage and tool calls, covering agents such as Claude Code, Codex, Cursor, etc.
MITEngineering Agent Skills shared by Matt Pocock from his personal .agents directory: small, composable, easy to modify, and not bound to specific models.
MITAn agent skill that makes programming agents prioritize minimal viable changes: fewer lines of code, less speculative code, simpler diffs. Think like the laziest seasoned developer in the room.
MITA composable engineering Skill framework for clarifying work, planning, testing and reviewing coding-agent changes. Read the workflow and its costs before adopting it.
MIT | v7.0.0Read the instructions, inspect the files, and check compatibility.