From aidd-dev
Validates correctness of implementations through iterative assertion loops, architecture conformance checks, and browser-based frontend UI verification.
How this skill is triggered — by the user, by Claude, or both
Slash command
/aidd-dev:03-assertsonnetThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Validates correctness of implementations through iterative assertion loops, architecture checks, and browser-based frontend verification.
Validates correctness of implementations through iterative assertion loops, architecture checks, and browser-based frontend verification.
| # | Action | When to use |
|---|---|---|
| 01 | assert | Iterate until a feature works by running the project's coding assertions |
| 02 | assert-architecture | Verify the codebase conforms to documented architecture (C4, ADRs, tree) |
| 03 | assert-frontend | Iterate until a frontend feature works by inspecting the running UI |
These actions are complementary facets, not mutually exclusive. This skill is run-one-OR-run-all:
When running all applicable: 01-assert is the baseline (project coding assertions); add 03-assert-frontend when the feature has a UI and a running frontend URL; add 02-assert-architecture when architecture conformance is in scope. A facet whose precondition is absent (e.g. no running URL) is skipped with a noted reason, never forced. Run the selected actions in order (01, then 03, then 02). Read and follow each selected action file.
@actions/01-assert.md@actions/02-assert-architecture.md@actions/03-assert-frontend.mdnpx claudepluginhub ai-driven-dev/frameworkRuns parallel specialized agents to verify implementations, run tests (unit/e2e/integration/perf/LLM), grade quality (0-10 scale), and suggest improvements. Use before merging.
Enables autonomous testing and verification mode where Claude thoroughly tests, iterates, and validates its own work across frontend, backend, CLI, and build tools.
Detects project type (web/backend/mobile) and enforces verification via Playwright screenshots, test suite runs (jest/vitest/pytest), or mobile E2E—no assumptions or manual checks.