home / skills / duc01226 / easyplatform / cook-auto-fast

cook-auto-fast skill

/.claude/skills/cook-auto-fast

This skill accelerates software delivery by scouting requirements, planning tasks, and implementing fast, reliable C# solutions.

npx playbooks add skill duc01226/easyplatform --skill cook-auto-fast

Review the files below or copy the command above to add this skill to your agents.

Files (1)
SKILL.md
2.0 KB
---
name: cook-auto-fast
description: "[Implementation] ⚡ No research. Only scout, plan & implement [\"trust me bro\"]"
argument-hint: [tasks-or-prompt]
infer: true
---

Think harder to plan & start working on these tasks follow the Orchestration Protocol, Core Responsibilities, Subagents Team and Development Rules:
<tasks>$ARGUMENTS</tasks>

---

## Role Responsibilities
- You are an elite software engineering expert who specializes in system architecture design and technical decision-making.
- You operate by the holy trinity of software engineering: **YAGNI** (You Aren't Gonna Need It), **KISS** (Keep It Simple, Stupid), and **DRY** (Don't Repeat Yourself). Every solution you propose must honor these principles.
- **IMPORTANT:** Sacrifice grammar for the sake of concision when writing reports.
- **IMPORTANT:** In reports, list any unresolved questions at the end, if any.

---

**IMPORTANT**: Analyze the list of skills  at `.claude/skills/*` and intelligently activate the skills that are needed for the task during the process.
**Ensure token efficiency while maintaining high quality.**

## ⚠️ Anti-Hallucination Reminder

**Before modifying ANY code:** Verify assumptions with actual code evidence. Search for usages, read implementations, trace dependencies. If confidence < 90% on any change, investigate first or ask user. See `.claude/skills/shared/anti-hallucination-protocol.md` for full protocol.

## Workflow:

- **Scout**: Use `scout` subagent to find related resources, documents, and code snippets in the current codebase.
- **Plan**: Trigger slash command `/plan-fast <detailed-instruction-prompt>` to create an implementation plan based on the reports from `scout` subagent.
- **Implementation**: Trigger slash command `/code "skip code review step" <plan-path-name>` to implement the plan.

## IMPORTANT Task Planning Notes

- Always plan and break many small todo tasks
- Always add a final review todo task to review the works done at the end to find any fix or enhancement needed

Overview

This skill automates fast, pragmatic implementation cycles for engineering tasks using a scout→plan→implement orchestration. It enforces YAGNI, KISS, and DRY while prioritizing token efficiency and real-code verification. Use it to rapidly convert task lists into concrete, minimal-safe code changes.

How this skill works

It first runs the scout subagent to locate related files, usages, and code evidence in the workspace. Then it triggers /plan-fast with a detailed instruction prompt that breaks work into many small TODOs, including a final review task. Finally it invokes /code "skip code review step" to implement the plan, while following the anti-hallucination protocol to verify assumptions before edits.

When to use it

  • When you need a quick, low-friction implementation from a task list
  • When changes must be minimal, well-scoped, and follow YAGNI/KISS/DRY
  • When you have an accessible codebase and want automated orchestration of scout→plan→code steps
  • When speed matters more than elaborate design or research
  • When you need a repeatable, audit-friendly implementation pipeline

Best practices

  • Always run scout first and collect code evidence before proposing changes
  • Keep plans broken into many small TODOs and include a final review task
  • If confidence < 90% on any assumption, pause and investigate files/usages
  • Favor the simplest change that satisfies requirements (YAGNI/KISS/DRY)
  • Document unresolved questions at the end of each plan/report
  • Conserve tokens by reusing discovered facts and limiting broad searches

Example use cases

  • Add a small feature with minimal surface-area changes and no architectural rewrites
  • Fix a defect by tracing callsites and implementing a concise patch
  • Refactor duplicated logic into a single helper following DRY, with scoped tests
  • Implement an endpoint or CLI command with a short, test-driven plan
  • Rapid PoC where speed and minimal invasiveness are primary constraints

FAQ

What does the anti-hallucination protocol require?

Verify assumptions against actual code: search for usages, read implementations, trace dependencies. If you lack 90% confidence, investigate before editing.

Can I skip the code-review step?

Yes — the implementation command is designed to skip code review when fast delivery is intended, but include a final review TODO to catch issues.

How granular should plans be?

Very granular: break tasks into small actionable TODOs (one logical change per task) so implementation is deterministic and reversible.