writing-plans

Write comprehensive implementation plans assuming the engineer has zero context for our codebase and questionable taste. Document everything they need to know: which files to touch for each task, code, testing, docs they might need to check, how to test it. Give them the whole plan as bite-sized tasks.

Safety Notice

This listing is imported from skills.sh public index metadata. Review upstream SKILL.md and repository scripts before running.

Copy this and send it to your AI assistant to learn

Install skill "writing-plans" with this command: npx skills add tstelzer/skills/tstelzer-skills-writing-plans

Writing Plans

Overview

Write comprehensive implementation plans assuming the engineer has zero context for our codebase and questionable taste. Document everything they need to know: which files to touch for each task, code, testing, docs they might need to check, how to test it. Give them the whole plan as bite-sized tasks.

Assume they are a skilled developer, but know almost nothing about our toolset or problem domain. Assume they don't know good test design very well.

Announce at start: "I'm using the writing-plans skill to create the implementation plan."

Save plans to: <repository-root>/plans/YYYY-MM-DD_<plan-name>.md

Plan Structure

Plan: <Feature Name>

Summary

<One paragraph describing what this builds>

Prerequisites

<Setup steps, deps to install, docs to read — skip if none>

Open Questions

<Unknowns or decisions to resolve before/during implementation — skip if none>

Out of Scope

<What this plan explicitly does NOT cover>

Overview

<A couple of paragraphs about approach>

Task <n>: <name>

Files: path/to/file.ts:42, ... Depends on: Task <m> (if any)

<What to do and why. Verbose — include code when useful.>

Verify: <How to confirm this task is done — command, test, manual check>

Remember

  • Exact file paths always, with line-numbers if relevant

  • Verbose description of implementation, or even complete code in plan (not "add validation")

  • Exact commands with expected output

  • Reference relevant skills

  • Order tasks by dependency; call out blocking relationships

  • Each task should be independently verifiable

Source Transparency

This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.

Related Skills

Related by shared tags or category signals.

Coding

effect-cli

No summary provided by upstream source.

Repository SourceNeeds Review
General

skill-creator

No summary provided by upstream source.

Repository SourceNeeds Review
General

effect-vitest

No summary provided by upstream source.

Repository SourceNeeds Review
General

effect

No summary provided by upstream source.

Repository SourceNeeds Review