writing-plans
The writing-plans skill generates structured, task-based implementation plans for software development projects. It enforces a specific markdown format that includes architecture, tech stack, global constraints, and granular, test-driven development steps for each task.
Is writing-plans safe to install?
Review before installing: our audit of writing-plans's source files found 3 shell commands, 0 external URLs, file reads and writes (medium risk). Every command and URL listed appears verbatim in the skill's source. The skill writes implementation plan files to the local filesystem and provides instructions for executing shell commands like git commits and test runners.
How we audit skills: our security review methodology.
Who is this skill for?
Software engineers and AI agents tasked with implementing complex features from specifications.
What can you do with it?
- Decomposing multi-step software requirements into bite-sized tasks.
- Creating implementation plans that follow TDD and DRY principles.
- Standardizing documentation for feature development.
- Preparing tasks for subagent-driven or inline execution.
How good is this skill?
Quality score: 5/10. The skill provides clear, actionable instructions for generating high-quality, test-driven implementation plans. It includes strict formatting rules and a self-review checklist to prevent common pitfalls like placeholders.
What does the skill file contain?
# 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. DRY. YAGNI. TDD. Frequent commits. 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 implemen...
Frequently asked questions
Where are the generated plans saved?
The skill saves plans to docs/superpowers/plans/YYYY-MM-DD-<feature-name>.md by default, unless the user specifies a different location.
What is the required header for a plan?
Every plan must start with a header containing the feature name, a requirement to use subagent-driven-development or executing-plans, the goal, architecture, tech stack, and global constraints.
How granular should tasks be?
Each task step should represent a single action taking 2-5 minutes, such as writing a test, running a test, implementing minimal code, or committing changes.
What happens after the plan is saved?
The skill prompts the user to choose between subagent-driven development or inline execution using the executing-plans skill.
Related skills
skill-creator
301.8KUsers who want to create, edit, or optimize AI agent skills, ranging from those new to coding to experienced developers
The skill-creator provides a structured workflow for developing, testing, and refining AI agent skills. It guides users through intent capture, skill drafting, iterative evaluation using subagents, and performance benchmarking.
github-actions-docs
264.6KDevelopers and DevOps engineers working with GitHub Actions workflows
The github-actions-docs skill provides grounded answers to GitHub Actions queries by retrieving information from official GitHub documentation. It assists with workflow syntax, security, migration, and runner configuration.
brainstorming
256.4KDevelopers and project managers who need to define requirements, architecture, and design for software projects before writing code
A structured brainstorming framework that guides users through project exploration, design proposal, and specification before implementation. It enforces a strict design-first workflow, requiring user approval for designs and documentation before transitioning to the writing-plans skill.
paper-context-resolver
140.4KDevelopers and researchers performing deep learning repository reproduction who encounter specific technical ambiguities in documentation
The paper-context-resolver skill provides targeted information from research papers to resolve specific gaps in deep learning repository reproduction. It focuses on technical details like dataset splits, preprocessing steps, evaluation protocols, checkpoint mappings, and runtime assumptions.