ss-sdd-testing-implementation

Coordinate feature-level SDD testing with a tester subagent and bounded fix loop.

Updated May 19, 2026
One-click install
npx skills add https://github.com/Emrebener/Sublime-Skills --skill ss-sdd-testing-implementation
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: ss-sdd-testing-implementation
Source: https://github.com/Emrebener/Sublime-Skills/tree/main/skills/spec-driven-development/ss-sdd-testing-implementation
Command: npx skills add https://github.com/Emrebener/Sublime-Skills --skill ss-sdd-testing-implementation

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It prevents SDD pipeline runs from finishing with unverified feature behavior by running a dedicated feature-level testing stage after implementation, with safe guardrails and clear escalation paths.

Core Features & Use Cases

  • Depth-gated feature testing: Prompts the user for quick vs standard testing depth, then reuses that depth consistently across fix-loop iterations.
  • Tool-aware tester strategy: Delegates execution to a tester subagent that selects UI/DB/Mixed approaches based on plan type and available tools, and falls back to code review when MCP tools are unavailable.
  • Bounded fix loop: Runs a coordinator-driven PASS/FAIL/MCP_UNAVAILABLE workflow with a maximum of 3 fix iterations, escalating to the user if the loop can’t resolve issues.
  • Safety and policy enforcement: Includes explicit prohibitions around state handling (never committing state.json) and forbids the coordinator from self-testing when MCP tools are missing.

Quick Start

Load this skill to test the just-implemented feature by first answering the requested testing depth (quick or standard) when prompted.

Frequently Asked Questions about ss-sdd-testing-implementation

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

FAQPage Schema
How do I verify implemented features end-to-end before finishing an SDD pipeline run?

Feature-level testing verifies implemented SDD features by dispatching a tester subagent for UI, backend, library, or mixed verification, ensuring pipeline runs do not finish with unverified behavior.

What happens when MCP tools are unavailable during feature testing?

When MCP tools are unavailable, the tester subagent applies an MCP fallback strategy by executing code review instead of direct UI or backend verification, while the coordinator is prohibited from self-testing.

How does the fix loop handle failing feature tests?

The bounded fix loop runs a coordinator-driven PASS, FAIL, and MCP_UNAVAILABLE workflow with a maximum of 3 fix iterations, escalating to the user if issues remain unresolved.

Can I choose between quick and standard testing depth for feature verification?

Yes, depth-gated feature testing prompts the user to select either quick or standard testing depth, then consistently reuses that chosen depth across all subsequent fix-loop iterations.

Why must state.json not be committed during feature test orchestration?

Committing state.json is explicitly prohibited as a safety guardrail to prevent prohibited state manipulation and ensure safe escalation paths during the coordinator-driven test workflow.

Does feature testing require sub-skill orchestration for UI and backend verification?

Yes, feature testing requires sub-skill orchestration via ss-sdd-testing-feature and ss-sdd-fixing-test-failures to execute tool-aware tester strategies and handle bounded fix loops.