07-epic — Claude Code skill: create and install
07-epic is a Claude Code skill that shapes and reviews product backlog Epics. It checks readiness, resumes saved work, and supports approval before saving.
MIT ★ 571 updated 2026-10-29
/plugin marketplace add ai-driven-dev/framework
/plugin install aidd-pm@aidd-frameworkWhat 07-epic does
The skill guides an Epic through shaping, review, and finalization. It can frame one outcome-based Epic, challenge its coherence and readiness, then help approve, persist, or transition it. An Epic that has already been persisted can go straight to finalization. Product and lifecycle choices remain with the user.
The workflow separates evidence, decisions, and assumptions, while preserving source links and existing edits. Any write needs explicit approval or bounded authority from the caller. This stays at outcome level: it does not propose child slices or implementation work. In Claude Code, add the marketplace and install the plugin with the commands below; npx skills add is another installation route.
What it helps with
- frame an Epic from a request or Product Brief
- check whether an Epic is coherent and ready
- resume work on a persisted Epic
- save an Epic after approval
Example prompts for the agent
- Turn this request into an outcome-focused Epic for the product backlog.
- Review this Epic for coherence and readiness.
- Resume the saved Epic and prepare it for approval.
How to install 07-epic
1Plugin marketplace
/plugin marketplace add ai-driven-dev/framework/plugin install aidd-pm@aidd-frameworkThis installs the whole aidd-pm plugin with all its skills
2Skills CLI (Vercel)
npx skills add ai-driven-dev/framework --skill 07-epic -a claude-code3Manually: put the files in place
~/.claude/skills/07-epic/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/07-epic/
1Skills CLI (Vercel)
npx skills add ai-driven-dev/framework --skill 07-epic -a codex2Manually: put the files in place
.agents/skills/07-epic/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add ai-driven-dev/framework --skill 07-epic -a cursor2Manually: put the files in place
.cursor/skills/07-epic/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install ai-driven-dev/framework plugins/aidd-pm/skills/07-epic2Manually: put the files in place
.github/skills/07-epic/SKILL.md1Skills CLI (Vercel)
npx skills add ai-driven-dev/framework --skill 07-epic -a gemini-cli2Platform CLI
gemini skills install https://github.com/ai-driven-dev/framework --path plugins/aidd-pm/skills/07-epicManually: put the files in place
.devin/skills/07-epic/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add ai-driven-dev/framework --skill 07-epic -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about 07-epic
How do I install 07-epic in Claude Code?
Add the marketplace with /plugin marketplace add ai-driven-dev/framework, then install the plugin with /plugin install aidd-pm@aidd-framework.
What does 07-epic do?
It helps shape an outcome-based Epic, review its coherence, and finalize it. It is not for Product Briefs, User Stories, or implementation.
Does 07-epic write an Epic without approval?
No. A write requires explicit approval or bounded authority supplied by the caller.
Source text
SKILL.md · MIT
--- name: 07-epic description: Produces or refines an outcome-based Epic for a product backlog. Use when the user wants to frame, review, resume, or persist an Epic. Not for Product Briefs, User Stories, or implementation. argument-hint: request | epic --- # Epic ```mermaid flowchart LR source([request, Product Brief, PRD, or Epic]) --> shape --> review --> finalize source -->|"already persisted"| finalize review -->|"revise"| shape finalize -->|"revise"| shape finalize -->|"authorized"| done([Epic]) ``` ## Actions Run the flow above. Read only the next action file. | Action | Does | | -------- | ------------------------------------- | | shape | frame one outcome-based Epic | | review | challenge its coherence and readiness | | finalize | approve, persist, or transition | ## Transversal rules - Keep product and lifecycle decisions with the user. - Separate evidence, decisions, and assumptions. - Preserve source links and existing edits. - Ask natural questions; never expose actions, references, or unchanged state. - Require explicit approval or caller-provided bounded authority before any write. - Stay at outcome level; do not propose child slices or implementation.
© AI-Driven Dev · MIT · ai-driven-dev/framework