Epic Designer
Turn a large feature or initiative into a well-scoped epic: clear boundaries, sequenced milestones, validation criteria.
Before & after
Same prompt, same agent — the only difference is the skill.
Here's how I'd break down a team workspaces epic: **Epic**: Team Workspaces **Stories**: 1. As a user, I can create a workspace 2. As a user, I can invite members to my workspace 3. As a user, I can switch between workspaces 4. As an admin, I can manage member permissions 5. As a user, I can see workspace-scoped content **Considerations**: - Data model changes to scope existing resources to a workspace - Permission system design - Migration path for existing users - UI updates for workspace context You'll want to size each story and identify dependencies before sprinting. Should I expand any of these?
EPIC — Team Workspaces
OUTCOME (not a feature list)
A user can put work in a shared space and control who sees it. Success:
40% of active accounts have ≥2 members within 60 days of ship.
THE DECISION THAT GATES EVERYTHING
Is a workspace a tenant or a container? Tenant means row-level isolation
and it touches every query you have. Container means a foreign key and a
filter. This decision cannot be deferred — every story below inherits it,
and reversing it later is a migration, not a refactor.
→ Recommend: container now, tenancy boundary designed but not built.
SLICES — each independently shippable
S1 Data model + backfill [gated by the decision above]
Every existing resource gets a workspace. Solo users get a
personal workspace silently. Ships dark.
S2 Create + switch First user-visible slice
S3 Invite + accept Email, token, expiry
S4 Roles: owner / member Two roles only. Not four.
S5 Workspace-scoped listing Every index endpoint gets the filter
S6 Billing per workspace ← often forgotten until it blocks launch
DEPENDENCIES
S1 → everything. S3 → S2. S6 → S4. S5 can run parallel to S3–S4.
EXPLICITLY OUT
Nested workspaces · cross-workspace sharing · custom roles · SSO
provisioning. Named here so they get deferred deliberately rather than
discovered mid-sprint.
RISK
S1's backfill is the only irreversible step. Rehearse against a
production-sized copy before running it, and make it resumable.
OPEN QUESTION FOR PRODUCT
What happens to a solo user's existing content on their first invite —
does it move into the shared space or stay personal? This changes S1.About this skill
name: epic-design description: Use when Structured Claude skill that gives Claude a repeatable workflow for epic design.
Epic Design
One of 337+ skills in the original author's multi-agent claude-skills mega-collection (~19k GitHub stars). Packages the Epic Design workflow with its own instructions and validation so outputs stay consistent.
What you get
- Public GitHub repo (alirezarezvani/claude-skills)
- the epic-design skill folder with SKILL.md. Part of a 337-skill / 30-agent / 70-command install.
Customize your output
- Fork the repo and adapt the skill's instructions and references to your workflow.
Example output
Activates automatically when your request matches Epic Design; chains with the other skills, agents, and commands in the collection.
Best for
Creators, builders, and teams using Claude Code.
SKILL.md preview
---
name: epic-design
description: Use when an engineering team needs a large feature or initiative broken down into a structured epic with scope, milestones, and validation criteria.
version: 1.0.0
category: Development / Engineering
author: AgentVolt
license: proprietary
tags:
- development
- engineering
---
# Epic Design
Turns a large feature or initiative into a well-scoped epic: clear boundaries, sequenced milestones, and validation criteria before implementation starts.
## When to use
… (sign up to view the full skill)More development skills
View all Development skills →Generate
Scaffold code, tests, and boilerplate from a short spec.
Performance Profiler
Systematic performance profiling for Node.js, Python, and Go applications.
Threat Detection
Use when hunting for threats in an environment, analyzing IOCs, or detecting behavioral anomalies in telemetry.
Agent Harness
Turns a domain folder of skills into a bounded agentic loop: compile a goal into a task plan, execute with the domain's tools, verify every task, retry within a budget.