Paca Epic Builder
Convert product requirements into structured epics with user stories and spec documents.
Installation
- Make sure Claude is on your device and in your terminal.
Skills load from
~/.claude/skills/when Claude Code starts up — so you need it on your machine first. If you don't have it yet, install it once with the command below, then runclaudein any terminal to verify.One-time setupnpm i -g @anthropic-ai/claude-codeAlready have it? Skip ahead.
- Paste into Claude Code or into your terminal.
This copies the whole skill folder into
~/.claude/skills/paca-epic-paca-ai/— the SKILL.md plus any scripts, reference docs, or templates the skill ships with. Safe default: works for every skill.Faster alternative (instruction-only skills)
Skips the clone and grabs only the SKILL.md file. Don't use this if the skill ships Python scripts, reference markdowns, or asset templates — they won't be downloaded and the skill will fail when it tries to load them.
Quick install (SKILL.md only)Sign up to copy - Restart Claude Code.
Quit and reopen Claude Code (or any other agent that loads from
~/.claude/skills/). New skills are picked up on startup. - Just ask Claude.
Skills auto-activate when your request matches the skill's description — no slash command needed. Trigger phrases live in the skill's own frontmatter; you can read them in the “What this skill does” section above.
Prefer to read the source first? Open on GitHub.
When Claude uses it
Turn a product requirement or feature description into a structured epic in Paca, with child user stories and a spec document. Use when asked to plan a new feature, break down a high-level requirement into stories, create an epic, or go from "we need X" to a fully structured backlog ready for sprint planning.
What this skill does
You are turning requirements into a structured epic in Paca. Use Paca MCP tools throughout — never create local files.
If no requirement is specified, ask: "What requirement or feature do you want to turn into an epic? Describe it in a sentence or two."
Step 1 — Load project context
- Call
list_projectsto identify the relevant project (infer from the user's message, or ask if ambiguous). - Call
list_documentsand search for documents whose titles or descriptions suggest requirements, roadmap, architecture, or BDD scenarios. Read the most relevant ones withget_document. Understand the domain and existing feature landscape before writing anything. - Call
list_task_typesto check whether an "Epic" type exists. - Call
list_task_statusesto know available statuses. - Call
list_tasksto scan for existing epics so you avoid duplicating scope.
Step 2 — Parse the requirements
Extract from the user's message:
- Goal — what user or business outcome this achieves
- Scope — what is in / out of scope
- Stakeholders — who benefits, who owns
- Constraints — tech, time, dependencies
If requirements are vague, ask at most 3 targeted questions before proceeding. Focus on what you genuinely cannot infer. Good question templates:
- "Who is the primary user of this feature, and what problem does it solve for them?"
- "Is X (name a reasonable assumption) in scope, or should I treat it as out of scope for now?"
- "Are there existing systems or services this needs to integrate with?"
Don't ask about things you can reasonably infer from the project docs you just read.
Step 3 — Create the epic task
Call create_task:
- Type: "Epic" if available from
list_task_types; otherwise a standard task clearly titled as an epic - Title: concise, outcome-oriented (e.g.
Epic: User Authentication) - Description (Markdown):
## Goal <one paragraph> ## Scope **In:** ... **Out:** ... ## Acceptance Criteria - [ ] ... ## Open Questions - ...
Step 4 — Break into stories
Derive child tasks from the requirements. Aim for 3–8 stories for a typical epic; go higher if the scope is large, but confirm with the user before creating more than 10. For each story:
- Call
create_taskwith a clear title, brief description, and 2–3 acceptance criteria - Reference the parent epic in the description:
Part of #<epic-number> - Prefer vertical slices (end-to-end thin features) over horizontal layers (all-backend, all-frontend)
Step 5 — Create a spec document
Call create_document:
- Title:
Epic: <name> — Specification - Content: Goal · Background · User Stories (linked by
#number) · Acceptance Criteria · Out of Scope · Open Questions
What's next: After this, consider running /paca-estimate #<epic-number> to add story point estimates to the new tasks, and /paca-sprint to plan them into a sprint.
Report back: epic task number, list of child task numbers and titles, and the spec document title.
If Paca MCP is not connected
Paca MCP tools are not available. Run
/paca-setupto configure the connection.
Tool reference
Tasks: create_task · update_task · list_tasks · get_task_by_number · list_task_types · list_task_statuses
Documents: create_document · list_documents · get_document
Projects: list_projects · get_project
Related skills
Documentation Co-Authoring
anthropics
Guide structured workflows for writing docs, proposals, and technical specs collaboratively.
MCP Server Builder
anthropics
Build protocol servers that connect language models to external APIs and services.
Ask Questions If Underspecified
trailofbits
Ask clarifying questions before starting work on ambiguous requests.
Claude Plugin Marketplace Builder
daymade
Convert a Claude skills repository into an installable marketplace with auto-updates.