sdd-verify

Verify SDD change implementations by executing tests and comparing results against specs, design, and tasks.

Updated Jul 10, 2026
One-click install
npx skills add https://github.com/AD-Paladins/beaconator-web --skill sdd-verify-ad-paladins
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: sdd-verify
Source: https://github.com/AD-Paladins/beaconator-web/tree/main/.config/opencode/skills/sdd-verify
Command: npx skills add https://github.com/AD-Paladins/beaconator-web --skill sdd-verify-ad-paladins

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve? It closes the gap between "code was written" and "code provably works" by acting as an independent quality gate that runs real tests and checks implementation against spec-driven development artifacts before a change is accepted. ## Core Features & Use Cases - Runtime Verification: Executes test, build, and coverage commands and records exit codes and output hashes as evidence, since static analysis alone never counts as verification. - Spec Compliance Matrix: Maps every requirement and scenario from specs to a covering test with statuses like COMPLIANT, FAILING, UNTESTED, or PARTIAL. - Strict TDD Auditing: When Strict TDD mode is active, validates the RED-GREEN-REFACTOR evidence from the apply phase and audits assertion quality to catch tautologies, ghost loops, and smoke-test-only checks. - Use Case: After an SDD apply phase finishes all tasks for a change, the orchestrator delegates to this skill, which runs the test suite, builds a compliance matrix, and returns a verdict of PASS, PASS WITH WARNINGS, or FAIL with issues grouped by severity. ## Quick Start Ask the orchestrator to run the SDD verification phase for the current change so it executes the tests and produces a verification report with a final verdict.

Frequently Asked Questions about sdd-verify

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I verify an SDD change implementation against its specs?▼

Run the verification phase after all tasks are complete. It reads the proposal, specs, design, and tasks artifacts, executes the test and build commands, maps each spec scenario to a covering test, and returns a compliance matrix with a PASS, PASS WITH WARNINGS, or FAIL verdict.

What happens if tasks are incomplete during SDD verification?▼

Verification returns blocked without running the full suite when any task is pending. Unchecked tasks are always flagged as CRITICAL, and full verification only proceeds once every task is marked complete.

Does SDD verification support Strict TDD mode?▼

Yes. When Strict TDD is active and a test runner exists, it loads a dedicated module that validates the TDD Cycle Evidence from the apply phase, cross-checks that reported tests actually pass, audits assertion quality, and reports test layer distribution and changed-file coverage.

Can static code analysis replace running tests in verification?▼

No. A spec scenario is only compliant when a covering test passed at runtime. Static inspection supplements runtime evidence but never substitutes for it, and test commands exiting non-zero are flagged as CRITICAL.

What artifacts are needed for full SDD verification?▼

Full verification requires proposal, specs, design, and tasks artifacts. With only tasks it verifies task completion, with tasks plus specs it adds requirement correctness, and missing dimensions are recorded as skipped rather than failed.

Why does verification fail when a spec scenario has no test?▼

A scenario without a passing covering test is marked UNTESTED, which is a CRITICAL issue. The verdict fails closed on incomplete or missing evidence because unproven scenarios cannot be considered compliant.