skills.rest
samjhecht
samjhechtCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

implement

Implement tasks from specs, plans, or issues using subagents with TDD and code review.

4|1|Updated Oct 29, 2025
Search Tags:#automation#code review#AI automation#subagents#test-driven development#orchestration#audit trail
One-click install
npx skills add https://github.com/samjhecht/wrangler --skill implement-samjhecht
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: implement
Source: https://github.com/samjhecht/wrangler/tree/main/skills/implement
Command: npx skills add https://github.com/samjhecht/wrangler --skill implement-samjhecht

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill autonomously implement tasks from specs, plans, or issues using subagents with TDD and code review.

Core Features & Use Cases

  • Subagent orchestration: Dispatch subagents to break down tasks and implement them.
  • TDD-driven workflow: Write tests first, implement, and refactor based on test results.
  • Audit trail: Maintain an audit log of actions for traceability.

Quick Start

Run: /wrangler:implement spec-auth-system.md to start autonomous implementation with an audit trail.

Frequently Asked Questions about implement

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

FAQPage Schema
How do I autonomously implement tasks from specifications using test-driven development?▼

Autonomous implementation with TDD writes tests first, then implements code to satisfy them. This Skill orchestrates subagents to break down specs into testable units, run automated tests, and perform integrated code reviews, ensuring quality gates are met before completion.

Can I use subagents to implement multiple related issues or tasks in parallel?▼

Yes. This Skill dispatches subagents to handle ranges of related issues or complete specifications end-to-end. Each subagent receives task orchestration with dependency tracking, environment capture, and per-task audit trails for traceability across parallel workflows.

What audit trail and traceability does autonomous implementation provide?▼

Autonomous implementation maintains per-task audit logs capturing all actions, environment state (absolute working directory, git root, branch), and code review outcomes. This creates a complete trace of decisions and changes for compliance and debugging.

How does code review integrate into the automation workflow?▼

Integrated code reviews run after test-driven implementation completes. The Skill automatically detects issues, dispatches fixes through subagents, and re-runs tests until all quality gates pass—eliminating manual review bottlenecks.

Can autonomous implementation work in headless mode without manual intervention?▼

Yes. This Skill operates fully in headless mode, autonomously handling task dispatch, test execution, code generation, and review cycles. It requires only an input spec, plan, or issue—no manual steps between start and deployment-ready output.

What's the difference between this approach and traditional code review workflows?▼

Traditional review waits for manual inspection after coding. Autonomous implementation inverts this: write tests first, auto-generate code, auto-review, auto-fix, then re-test—all before human review, reducing iteration cycles and catching bugs earlier.

Related Skills

Explore More Software Engineering Skills→
kvnxiaokvnxiao

linear-fix

Create per-ticket git worktrees and generate GitHub PRs for Linear tickets.

Community
Advanced
HeldinhowHeldinhow
4

cicd-github-actions

Generate GitHub Actions CI/CD pipelines for automated builds, tests, and deployments.

Community
Intermediate
arbazkhan971arbazkhan971
26

lint

Configure linters, formatters, pre-commit hooks, and CI enforcement across repositories.

Community
Advanced
greyhaven-aigreyhaven-ai
29

grey-haven-tdd-orchestration

Coordinate multi-agent TDD workflows enforcing red-green-refactor discipline across Python and TypeScript.

Community
Advanced