writing-plans

Generates detailed multi-task implementation plans from specs with TDD steps and exact file paths.

Updated Aug 28, 2026
One-click install
npx skills add https://github.com/epicodic/drift --skill writing-plans-epicodic
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: writing-plans
Source: https://github.com/epicodic/drift/tree/main/.agents/skills/writing-plans
Command: npx skills add https://github.com/epicodic/drift --skill writing-plans-epicodic

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Turning a spec or requirements document into an actionable implementation plan is error-prone: tasks end up vague, files are unspecified, and engineers without codebase context get stuck. This Skill produces complete, bite-sized implementation plans that an engineer with zero project context can execute task by task. ## Core Features & Use Cases - Structured Plan Generation: Creates plan documents with a mandatory header, file structure mapping, and tasks broken into 2-5 minute steps following TDD (failing test, verify failure, minimal implementation, verify pass). - Placeholder Enforcement: Forbids vague steps like "add error handling" — every step must contain exact file paths, complete code, and exact commands with expected output. - Self-Review and Handoff: Includes a self-review checklist for spec coverage, placeholder scans, and type consistency, plus an execution handoff offering subagent-driven or inline execution. - Use Case: After brainstorming a feature spec for a KWin script, invoke this Skill to produce a dated plan in docs/agents/plans/ with per-task checkboxes, test code, and coding-convention checklists ready for an implementing agent. ## Quick Start Use the writing-plans skill to turn my spec into a step-by-step implementation plan saved under docs/agents/plans.

Frequently Asked Questions about writing-plans

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

FAQPage Schema
How do I write an implementation plan from a feature spec?▼

Invoke the writing-plans skill with your spec before touching code. It maps the file structure, decomposes work into bite-sized TDD tasks with exact paths and complete code, and saves the plan to docs/agents/plans with a dated filename.

What makes a good task breakdown for AI coding agents?▼

Each step should be one 2-5 minute action: write the failing test, run it to confirm failure, implement minimal code, run tests to confirm passing, then complete a coding-guideline checklist. Every step needs exact file paths and full code, never placeholders.

Does this planning approach support multiple programming languages?▼

Yes. The plan template covers TypeScript, JavaScript, and QML via npm, Python via uv and pytest, and includes C++ GoogleTest examples. Naming conventions for each language are specified in the plan header and checklist.

When should a spec be split into multiple implementation plans?▼

Split when the spec covers multiple independent subsystems. Each plan should produce working, testable software on its own, so one plan per subsystem keeps tasks self-contained and independently executable.

What happens after the implementation plan is written?▼

The skill offers two execution options: subagent-driven development, which dispatches a fresh subagent per task with review between tasks, or inline execution with batch processing and checkpoints using the executing-plans skill.