AI Agent Testing and Evaluation Bundle
Six skills to compare agent runs, turn failures into regression tests, build eval datasets, gate provenance, inspect untrusted content, and write audit reports whose proof a stranger can re-check.
THE AGENSI STORE
677 skills found
Diagnoses why a project won't install, build, start or test: runtime and package-manager versions, missing .env keys, port conflicts, lockfile and native build issues, Docker, databases, certificates, PATH. Read-only scan first, minimal explained fixes, then proves it runs.
Your agent builds features and fixes bugs test-first: a planned test list, one failing test at a time (failing for the right reason), minimal code to pass, refactor with the suite green. Works in your own framework: Jest, Vitest, pytest, Go, Rust, JUnit, RSpec.
Test-driven development (TDD) workflow - a strict red-green-refactor loop with a test list, forcing tests, minimal-code-to-pass guidance and an edge-case catalogue. Use when the user says help me stick to test-driven development, write tests first for this, what tests should I write, improve test coverage, or red green refactor this function.
Page 1 of 29