A skill that turns a raw product idea into a structured epic draft, using a standard template and saving it in an epics folder with an Explore stage.

Use it to draft product epics from a short prompt or an idea note, incorporating relevant people, research, meetings, initiatives, and lifecycle guidance.

It helps organise an incomplete idea into a consistent planning document while checking for missing context.

create-epic — Skill for Claude Code by aleksander-dytko

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add aleksander-dytko/ai-pm-workspace --skill create-epic

Clone the repo

git clone --depth 1 https://github.com/aleksander-dytko/ai-pm-workspace

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/aleksander-dytko/ai-pm-workspace/create-epic/github.svg)](https://agentmods.dev/skills/aleksander-dytko/ai-pm-workspace/create-epic)

Your own site

<a href="https://agentmods.dev/skills/aleksander-dytko/ai-pm-workspace/create-epic"><img src="https://agentmods.dev/badge/skills/aleksander-dytko/ai-pm-workspace/create-epic/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/aleksander-dytko/ai-pm-workspace/create-epic"><img src="https://agentmods.dev/badge/skills/aleksander-dytko/ai-pm-workspace/create-epic.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 20 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,252 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00020	$0.01252
Opus 5	$0.00010	$0.00626
Sonnet 5	$0.00004	$0.00250
Haiku 4.5	$0.00002	$0.00125

Measured 12d ago against content hash bd729894bfdf, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

create-epic scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/skills/create-epic/SKILL.md · 117 lines

How it starts

The opening of the file, as written. The whole thing — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Create Epic

You help turn a raw product idea into a well-structured epic draft. The output follows templates/epic-template.md and lands in epics/ with stage: Explore.

Input

The user provides via $ARGUMENTS:

A short prompt (e.g., "unified onboarding dashboard for CSMs"), OR
A path to a raw idea note (e.g., samples/sample-epic-idea.md)

Workflow

1. Gather context

Read the raw idea. If $ARGUMENTS is a path, read that file. Otherwise use the prompt directly.

Read supporting context in parallel:

templates/epic-template.md - the target structure
docs/epic-lifecycle.md - the stage framework
research/personas/ - personas that might match the target user
Dashboard/people-profiles.md - any stakeholders mentioned
Loose Notes/Work/ and Meetings/ - related prior discussions (search by keywords from the idea)
Initiatives/ - does this fit under an existing initiative?

2. Identify gaps in the idea

Before drafting, identify what's missing or unclear. Ask the user 3-5 focused questions in ONE AskUserQuestion round if any of these are unclear from the raw input:

Target user: which persona does this serve? (Offer personas from research/personas/ as options.)
Primary metric: what measurable outcome should improve?
Scope boundary: what is explicitly NOT in this epic?
Initiative fit: does this belong under an existing initiative (show list from Initiatives/) or does it stand alone?
Competitor check: has competitive research been done? (Offer /competitive-research if not.)

Skip questions where the raw idea already has a clear answer. Maximum one round.

3. Draft the epic

Use templates/epic-template.md as the structure. Fill what you can from the raw idea + answers:

Required sections (always fill):

Value Proposition Statement - one crisp statement of the outcome.
User Problem - 1-2 paragraphs from the customer's perspective. Frame from the "why", not the product's failure.
User Stories - 3-6 stories at the "what" level (Explore phase). Add the "how" later.

Read the full file on GitHub · 117 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

12d ago First seen · 117 lines · 20 tokens per session scan A bd729894bfdf

Subscribe to this mod's changes

create-epic is a skill published in the GitHub repository aleksander-dytko/ai-pm-workspace (34 stars, last pushed 4mo ago), licensed MIT. It adds 20 tokens to every session and 1,252 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Claude Code Planning Project management ai-workspace claude-skills obsidian pm-tools product-management

customise-workflow

Customise the prd-taskmaster plugin workflow via curated brainstorm questions. The AI asks, the user answers in plain English, and the skill writes their preferences to .atlas-ai/config/atlas.json. Future runs of prd-taskmaster read that file and apply user preferences to phase gates, validation strictness, default…

anombyte93/prd-taskmaster · 137 tokens

expand-tasks

Expand all TaskMaster tasks with deep research before coding begins. Reads tasks.json, launches parallel research agents per task in waves using the research-expander agent. Writes findings back to tasks.json. Part of the prd-taskmaster toolkit. Use after PRD is parsed and before implementation. Invoke with…

anombyte93/prd-taskmaster · 68 tokens

create-epic