Claude MarketplacesSubmit
vudovn avatar

Plan Writing

vudovn/antigravity-kit

This breaks down work into short, verifiable tasks with a strong opinion on keeping plans minimal. Each task should take 2-5 minutes and have clear verification criteria. The real value is in the constraints: plans go in your project root (not hidden folders), stay under one page, and skip generic templates for project-specific actions. It pushes you to write "Install next-auth, create /api/auth/[...nextauth].ts" instead of "Add authentication." The principle of only including relevant verification scripts based on what you're actually building (frontend, API, mobile) keeps things focused. Good for feature work and refactoring when you need structure without bureaucracy.

skills.sh installs
121
GitHub stars
7.6K
last updated
Jun 3, 2026
View on GitHub

Install

$ npx -y skills add vudovn/antigravity-kit --skill plan-writing --agent claude-code

Installs into .claude/skills of the current project.

Files

Plan Writing

Source: obra/superpowers

Overview

This skill provides a framework for breaking down work into clear, actionable tasks with verification criteria.

Task Breakdown Principles

1. Small, Focused Tasks

  • Each task should take 2-5 minutes
  • One clear outcome per task
  • Independently verifiable

2. Clear Verification

  • How do you know it's done?
  • What can you check/test?
  • What's the expected output?

3. Logical Ordering

  • Dependencies identified
  • Parallel work where possible
  • Critical path highlighted
  • Phase X: Verification is always LAST

4. Dynamic Naming in Project Root

  • Plan files are saved as {task-slug}.md in the PROJECT ROOT
  • Name derived from task (e.g., "add auth" → auth-feature.md)
  • NEVER inside .agents/, docs/, or temp folders

Planning Principles (NOT Templates!)

🔴 NO fixed templates. Each plan is UNIQUE to the task.

Principle 1: Keep It SHORT

❌ Wrong✅ Right
50 tasks with sub-sub-tasks5-10 clear tasks max
Every micro-step listedOnly actionable items
Verbose descriptionsOne-line per task
SKILL.md on GitHub

Sponsors

Promote your product hereReach 125k+ visitors monthlyPromote your product hereReach 125k+ visitors monthlyAgent CaffeineSponsoredClose your lid, come back to finished workSnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthlyWaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthlyknobsSponsoredSee your site on any phone, any day, in any language

Details

Repository
github.com/vudovn/antigravity-kit
Categories
Documentation, Productivity & Planning
First seen
Jun 3, 2026

More from vudovn/antigravity-kit

All 30

Recommended

More Documentation
1dougtrajano avatarpydanticai-docsdougtrajano/pydantic-ai-skillsThis gives Claude direct access to the Pydantic AI framework docs, covering agent setup, structured outputs, function tools, dependency...115skills.sh installs
2agentworkforce avatarwriting-agent-relay-workflowsagentworkforce/relayThis is the opinionated playbook for building multi-agent workflows with @relayflows/core.0skills.sh installs
3agnosticui avatarexplain-codeagnosticui/agnosticuiExplain what code does in plain English0skills.sh installs
4anthropics avatarWriting Hookify Rulesanthropics/claude-codeThis skill should be used when the user asks to "create a hookify rule", "write a hook rule", "configure hookify", "add a hookify rule", or needs guidance on ho0skills.sh installs
5ar9av avatarpaper-writing-benchar9av/paperorchestraReverse-engineer raw materials (Sparse idea, Dense idea, experimental log) from an existing AI research paper to build a benchmark case for evaluating paper-wri0skills.sh installs
6ar9av avatarsection-writing-agentar9av/paperorchestraStep 4 of the PaperOrchestra pipeline (arXiv:2604.05018). ONE single multimodal LLM call that drafts the remaining paper sections (Abstract, Methodology, Experi0skills.sh installs