Planning And Task Breakdown
This is the skill you reach for when a spec feels too big to start or you're not sure what order to build things in. It pushes you into read-only planning mode first, then walks through dependency mapping, vertical slicing (build one complete user flow at a time instead of all database, then all API, then all UI), and writing tasks with acceptance criteria. The core insight is solid: horizontal slicing across layers leads to integration hell, while vertical slices give you working checkpoints. It's opinionated about task sizing (nothing over 5-8 files), includes a plan template, and has good guidance on what's safe to parallelize. Honestly, the discipline of writing acceptance criteria before touching code prevents most of the "I'll refactor this later" disasters.
- skills.sh installs
- 73.5K
- GitHub stars
- 114.6K
- last updated
- Aug 21, 2026
Install
$ npx -y skills add addyosmani/agent-skills --skill planning-and-task-breakdown --agent claude-codeInstalls into .claude/skills of the current project.
Files
Planning and Task Breakdown
Overview
Decompose work into small, verifiable tasks with explicit acceptance criteria. Good task breakdown is the difference between an agent that completes work reliably and one that produces a tangled mess. Every task should be small enough to implement, test, and verify in a single focused session.
When to Use
- You have a spec and need to break it into implementable units
- A task feels too large or vague to start
- Work needs to be parallelized across multiple agents or sessions
- You need to communicate scope to a human
- The implementation order isn't obvious
When NOT to use: Single-file changes with obvious scope, or when the spec already contains well-defined tasks.
The Planning Process
Step 1: Enter Plan Mode
Before writing any code, operate in read-only mode:
- Read the spec and relevant codebase sections
- Identify existing patterns and conventions
- Map dependencies between components
- Note risks and unknowns
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageDetails
- Repository
- github.com/addyosmani/agent-skills
- Categories
- AI & Agent Building, Productivity & Planning, Automation & Workflows
- First seen
- Apr 16, 2026
More from addyosmani/agent-skills
All 25- Documentation And Adrs73.5K
- Code Simplification72.6K
- Api And Interface Design72.4K
- Debugging And Error Recovery72.4K
- Test Driven Development71.3K
- Context Engineering71.1K
- Incremental Implementation71K
- Git Workflow And Versioning68.8K
- Idea Refine68.3K
- Using Agent Skills68K
- Browser Testing With Devtools67.7K
- Shipping And Launch67.4K
- Source Driven Development67.4K
- Ci Cd And Automation67.3K
- Interview Me66.4K
- Deprecation And Migration66.4K
- Doubt Driven Development65.8K
- Observability And Instrumentation63.8K
- Constraint Driven Development42.4K
- Code Review And Quality84.1K
- Security And Hardening81.4K
- Frontend Ui Engineering77.8K
- Performance Optimization75.2K
- Spec Driven Development74.7K
Recommended
More AI & Agent Building
documentation-and-adrsaddyosmani/agent-skillsRecords decisions and documentation. Use when making architectural decisions, changing public APIs, shipping features, or when you need to record context that f73.5Kskills.sh installscode-simplificationaddyosmani/agent-skillsSimplifies code for clarity. Use when refactoring code for clarity without changing behavior. Use when code works but is harder to read, maintain, or extend tha72.6Kskills.sh installsapi-and-interface-designaddyosmani/agent-skillsGuides stable API and interface design. Use when designing APIs, module boundaries, or any public interface. Use when creating REST or GraphQL endpoints, defini72.4Kskills.sh installsdebugging-and-error-recoveryaddyosmani/agent-skillsGuides systematic root-cause debugging. Use when tests fail, builds break, behavior doesn't match expectations, or you encounter any unexpected error. Use when 72.4Kskills.sh installstest-driven-developmentaddyosmani/agent-skillsDrives development with tests. Use when implementing any logic, fixing any bug, or changing any behavior. Use when you need to prove that code works, when a bug71.3Kskills.sh installscontext-engineeringaddyosmani/agent-skillsOptimizes agent context setup. Use when starting a new session, when agent output quality degrades, when switching between tasks, or when you need to configure 71.1Kskills.sh installs