sdd-apply

Executes approved SDD task batches as controlled code changes with checkpoints.

Updated Apr 2, 2026
One-click install
npx skills add https://github.com/nico0695/ai-tools --skill sdd-apply-nico0695
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: sdd-apply
Source: https://github.com/nico0695/ai-tools/tree/main/sdd/sdd-v2/skills/sdd-apply
Command: npx skills add https://github.com/nico0695/ai-tools --skill sdd-apply-nico0695

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Turning an approved implementation plan into actual code changes often loses scope control, approval discipline, and traceability. This Skill executes a formalized SDD task plan one approved batch at a time, keeping tasks.md, apply-progress.md, and state.yaml consistent so work stays resumable and auditable. ## Core Features & Use Cases - Batch-scoped execution: Runs exactly one approved batch per invocation, requiring explicit user approval before any code-touching batch. - Safety triggers and dirty-tree policy: Blocks on dirty working trees, code-plan desync, out-of-scope blast radius, or ambiguous instructions, and records blockers in state.yaml. - Traceable progress logging: Appends per-batch evidence, changed files, and decisions to apply-progress.md while keeping state.yaml operational. - Use Case: After planning a feature change with SDD v2, invoke this Skill to implement batch 1, have it stop when a referenced function was renamed, and resume later from the recorded checkpoint. ## Quick Start Ask the assistant to execute the next approved batch of the current SDD change using sdd-apply and update the progress files.

Frequently Asked Questions about sdd-apply

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

FAQPage Schema
How do I execute an SDD task plan one batch at a time?▼

Invoke sdd-apply after the plan is approved; it reads the Suggested Batches in tasks.md, opens a pre_apply checkpoint, and executes only the approved batch. Each subsequent batch requires separate explicit user approval.

What happens if my working tree is dirty before applying a batch?▼

The Skill blocks execution by default when the working tree is dirty and opens a checkpoint recommending you review or clean the tree first. The blocker is persisted through the orchestrator checkpoint and state.yaml.

Does sdd-apply run tests or QA automatically after code changes?▼

No, it never auto-runs stage-qa. For code-touching batches reaching an end-of-feature or critical-point checkpoint, it recommends stage-qa and waits for your confirmation before any handoff.

What happens when the code no longer matches the planned tasks?▼

The code-plan desync trigger stops the batch, documents the mismatch in apply-progress.md, and recommends pausing or replanning. It returns a blocked or partial status instead of guessing.

Can sdd-apply modify files outside the approved batch scope?▼

No, the collateral blast radius trigger stops execution before touching out-of-scope files and surfaces the affected modules explicitly. Continuing requires an explicit user decision through a checkpoint.