sdd-apply

Implements spec-driven development tasks from specs and design artifacts as an executor sub-agent.

Updated Aug 5, 2026
One-click install
npx skills add https://github.com/Alountk/Bloodbowl_Project --skill sdd-apply-alountk
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: sdd-apply
Source: https://github.com/Alountk/Bloodbowl_Project/tree/main/.opencode/skills/sdd-apply
Command: npx skills add https://github.com/Alountk/Bloodbowl_Project --skill sdd-apply-alountk

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? It turns approved SDD specs, designs, and task lists into actual code by executing assigned tasks with strict status gating, progress persistence, and optional strict TDD enforcement. ## Core Features & Use Cases - Task Execution from Specs: Reads proposal, spec, design, and tasks artifacts, then implements only the assigned tasks while marking them complete in tasks.md or Engram. - Strict TDD Mode: Conditionally loads a strict-tdd module enforcing RED-GREEN-REFACTOR cycles, triangulation, assertion quality rules, and a TDD evidence table. - Workload and PR Governance: Enforces review workload forecasts, chained/stacked PR strategies, size exceptions, and blocked-state guards before any code is written. - Use Case: An orchestrator assigns Phase 1 tasks 1.1-1.3 of a change; the executor reads the specs, writes the code with tests, persists apply-progress, and returns a structured summary ready for the verify phase. ## Quick Start Delegate the pending tasks for a change to the sdd-apply sub-agent so it implements them according to the specs and design.

Frequently Asked Questions about sdd-apply

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

FAQPage Schema
How do I implement SDD tasks from a tasks.md file?▼

Delegate the assigned tasks to the sdd-apply executor sub-agent with the change name and artifact store mode. It reads the specs and design, writes the code, marks tasks complete with [x], and persists apply-progress before returning a summary.

What is strict TDD mode in spec-driven development?▼

Strict TDD mode activates when strict_tdd is true and a test runner exists. It loads the strict-tdd module requiring a failing test before any production code, mandatory triangulation with multiple cases, and a TDD Cycle Evidence table verified by the verify phase.

Can the apply executor run without an orchestrator?▼

No. The skill is delegate-only and not user-invocable. If loaded via the skill tool, the orchestrator must stop and delegate to the dedicated sdd-apply sub-agent rather than executing instructions inline.

Why does apply stop with a blocked status before writing code?▼

Execution halts when applyState is blocked, the workload forecast lacks a resolved delivery decision, or required edits fall outside allowedEditRoots. The executor returns the missing artifacts or unsafe paths instead of editing.

How does apply-progress persistence work across batches?▼

Before starting, the executor reads any existing apply-progress artifact and merges prior completions with new ones into a single cumulative artifact. Overwriting without reading prior progress permanently loses completed work from earlier batches.