gds-quick-dev

Implements code changes through a spec-driven plan, implement, review, and present workflow.

1|Updated Sep 18, 2026
One-click install
npx skills add https://github.com/PastaSus/egg-defender --skill gds-quick-dev-pastasus
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: gds-quick-dev
Source: https://github.com/PastaSus/egg-defender/tree/main/.agents/skills/gds-quick-dev
Command: npx skills add https://github.com/PastaSus/egg-defender --skill gds-quick-dev-pastasus

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Turning a user intent, bug report, or story into reviewed, working code often skips planning discipline and adversarial review, producing unreviewable or misaligned changes. This Skill enforces a structured workflow that converts intent into an approved specification, implements it, runs multi-perspective code review, and presents a navigable change summary. ## Core Features & Use Cases - Spec-driven development: Clarifies intent, investigates the codebase, and writes a token-bounded specification with tasks, acceptance criteria, and a code map before any code changes. - Dual routing: Routes zero-blast-radius changes to a fast one-shot path and everything else through the full plan-implement-review cycle. - Adversarial review loop: Runs blind, edge-case, and acceptance-auditor reviews, classifies findings (intent gap, bad spec, patch, defer, reject), and loops back to re-derive code when needed. - Epic context compilation: Distills planning artifacts (PRD, architecture, UX) into a focused per-epic context file and syncs sprint-status.yaml for epic stories. - Use Case: A developer asks to add a new API endpoint with validation. The Skill drafts a spec, gets human approval, implements via sub-agent, runs three review passes, fixes findings, commits, and opens a clickable Suggested Review Order in VS Code. ## Quick Start Ask the agent to implement a feature or fix a bug, for example: implement password reset email flow following the project conventions.

Frequently Asked Questions about gds-quick-dev

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

FAQPage Schema
How do I implement a feature with a spec-driven AI workflow?

Invoke the skill with your intent; it clarifies requirements, investigates the codebase, writes a specification with tasks and acceptance criteria, waits for your approval, then implements, reviews, and commits the change.

How does the plan-code-review route differ from the one-shot route?

One-shot handles zero-blast-radius changes by implementing directly with a single adversarial review. Plan-code-review runs the full cycle: spec drafting, human approval checkpoint, implementation, and three review subagents with loopback handling.

Can this workflow handle epic stories from sprint planning?

Yes. It detects epic stories, compiles a focused epic context file from PRD and architecture artifacts, loads continuity from prior completed stories, and syncs story status in sprint-status.yaml.

What happens when the review subagents find problems?

Findings are deduplicated and classified as intent_gap, bad_spec, patch, defer, or reject. Serious findings trigger a loopback that reverts code and re-derives it from an amended spec; trivial patches are auto-fixed.

Does the skill work without sub-agent support?

Yes. Runtimes without sub-agents fall back to inline execution: the skill writes review prompt files and halts so the human can run each review in a separate session and paste back findings.

When should I not use the one-shot route?

Avoid one-shot when the change has any plausible blast radius, involves architectural decisions, or unclear intent. When uncertain, the skill routes to the full plan-code-review path by default.