Claude Skills by uppifyagency

This skill should be used when the user asks to "/harness-eval", "evaluate the build", "run QA on the app", "grade the application", "test against the spec", or wants to run the evaluator agent standalone without a full harness loop. Dispatches the harness-evaluator agent to test a running application against a specification.

This skill should be used when the user asks to "/harness-simplify", "simplify the harness", "remove harness component", "stress test the harness", "do we need the evaluator", "is the planner necessary", "optimize harness cost", or wants to test whether a harness component is still needed. Implements progressive simplification — removing one component at a time and comparing quality.

This skill should be used when the user asks to "/harness-status", "harness status", "where is the harness", "what round are we on", "harness progress", or wants to inspect the current state of a harness run. Reads .harness/state.json and presents a human-readable progress report.

This skill should be used when the user asks to "/harness", "build an application with harness", "run the harness", "start a harness build", "multi-agent build", "planner evaluator build", "long-running application build", or wants to build a complete application using the planner-generator-evaluator architecture. Orchestrates a multi-agent loop inspired by Anthropic's harness design pattern for long-running AI application development.