skills.rest
oleyna80
oleyna80COMMUNITY
Explore all skills by this author →
GitHub

task-decomposition

Decompose objectives into atomic tasks with verifiable acceptance criteria and dependencies.

Updated Jun 12, 2026
Search Tags:#planning#dependencies#acceptance criteria#task decomposition#opencode#work breakdown#tasklist
One-click install
npx skills add https://github.com/oleyna80/agentic-sdlc-framework --skill task-decomposition-oleyna80
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: task-decomposition
Source: https://github.com/oleyna80/agentic-sdlc-framework/tree/main/.opencode/skills/task-decomposition
Command: npx skills add https://github.com/oleyna80/agentic-sdlc-framework --skill task-decomposition-oleyna80

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Large objectives and approved Work Blocks are hard to execute and verify when they remain as monolithic goals. This Skill breaks them into atomic, staged tasks with measurable acceptance criteria so an Orchestrator can plan, assign, and verify work reliably. ## Core Features & Use Cases - Atomic Task Breakdown: Enforces one verifiable result per task with explicit dependencies between tasks. - Measurable Acceptance Criteria: Requires every task to carry checkable AC, plus an Expected Final Result for each Work Block. - Lifecycle Stage Mapping: Maps tasks to Define/Execute/Assure/Close stages and flags when independent assurance (Reviewer, Verifier, Critic) is needed. - Use Case: Given an approved feature Work Block, generate a docs/tasklist/<ticket>.tasklist.md file with Task IDs, objectives, scope, dependencies, AC, execution notes, and a Retrospective Plan. ## Quick Start Ask the agent to decompose the approved Work Block into a tasklist with verifiable acceptance criteria and stage mapping.

Frequently Asked Questions about task-decomposition

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

FAQPage Schema
How do I break down a large feature into actionable tasks?▼

Provide the approved Work Block or objective and the Skill generates a tasklist where each task has one verifiable result, explicit dependencies, and measurable acceptance criteria. Output is written to docs/tasklist/<ticket>.tasklist.md.

What makes a good acceptance criterion for a task?▼

Acceptance criteria must be measurable and checkable, not subjective. Each task defines exactly one verifiable result, and the Work Block starts with an Expected Final Result the Owner can verify.

Does this task decomposition work with OpenCode agents?▼

Yes, this version is adapted for OpenCode with compatible tool references, while the original framework skill remains authoritative. It integrates with the Orchestrator workflow for staged execution.

When should a Work Block use end-to-end autonomous execution?▼

Set Execution mode to End-to-end autonomous for large approved Work Blocks. Significant Work Blocks should also define a Retrospective Plan upfront and note when independent assurance roles are needed.

What is the difference between Must Resolve Before Start and Can Resolve During Work?▼

Must Resolve Before Start lists blockers that prevent work from beginning, while Can Resolve During Work covers open questions addressable during execution. Separating them prevents false blockers from delaying staged tasks.

Related Skills

Explore More Product & Management Skills→
azat-ioazat-io
14

discovering

Clarify vague project ideas into goals, scope, and a discovery brief.

Community
Basic
ConsiliencyConsiliency
2

execute-detailed

Executes one bounded implementation plan with verification, acceptance checks, and PR publication.

Official
Advanced
Brite-NitesBrite-Nites

verification-before-completion

Enforce multi-level build, test, acceptance, and integration verification before task completion.

Official
Advanced
mhdxbilalmhdxbilal
1

octopus-quick

Execute lightweight ad-hoc tasks with atomic commits and concise summaries.

Community
Basic