How do I install the Epic Run skill?

Run npx skillmds@latest add drmoisan/epic-run-2 in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Epic Run safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Epic Run?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Epic Run free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Epic Run?

drmoisan (@drmoisan) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Epic Run by drmoisan — Agent Skill

Name: Epic Run
Author: drmoisan

Epic Run

Execute a previously planned epic by replaying the committed epic-kickoff artifact through the epic-orchestrator agent. Use after /epic-plan has prepared the epic (issues, folders, research, specs, atomic plans, preflight clearance) and the user is ready to execute end-to-end.

drmoisan 34162dc 3.4 KB Updated Sep 17, 2026

File contents

Epic Run Skill

A user invocation (/epic-run <epic-slug>) forks the epic-orchestrator agent to execute an epic that epic-planner has already prepared. The epic slug (or a path under docs/features/epics/) for this run is:

$ARGUMENTS

Procedure

Resolve the epic home. A bare slug resolves to docs/features/epics/<epic-slug>/; a path argument resolves to its containing epic folder.
Resolve the committed kickoff artifact docs/features/epics/<epic-slug>/epic-kickoff.md. It may exist only on the epic integration branch: epic-plan commits it to epic/<epic-slug>-integration (worked in a separate integration worktree), so the worktree that invokes /epic-run is not guaranteed to have it checked out. Discover it across both locations before concluding it is missing:
- Attempt git fetch origin epic/<epic-slug>-integration. A failure because the remote branch does not exist is the genuine "epic not planned" case; tolerate it and continue to the local check rather than treating the fetch failure as fatal.
- Treat the artifact as present when EITHER the plain local path exists in the invoking worktree, OR it exists on the fetched integration ref, tested with git cat-file -e epic/<epic-slug>-integration:docs/features/epics/<epic-slug>/epic-kickoff.md (equivalently origin/epic/<epic-slug>-integration:<path>).
- When the artifact is present only on the integration ref, read its content with git show <ref>:<path>. That is sufficient to extract the ## Invocation Prompt text needed to proceed; do NOT check the integration branch out into the invoking worktree — the session worktree must never be checked out onto the integration branch (worktree-isolation convention).
- STOP without delegating anything only when the artifact is absent BOTH locally and on the fetched integration branch (the branch does not exist, or exists but lacks the file). In that case report that the epic has no committed kickoff artifact: the user must run /epic-plan first (or, for an epic that was authored manually, invoke /epic-orchestrate <epic-manifest-path> directly).
Execute the kickoff artifact's ## Invocation Prompt section as the epic objective, applying the epic-orchestrate skill procedure and the ## Prepared-Epic Execution (epic-planner Handoff) section of .claude/agents/epic-orchestrator.md: reuse the existing integration branch, and have each child Agent(orchestrator) delegation resume at atomic execution from its committed plan-path rather than re-running promotion, research, or planning.
Honor existing checkpoint state: if artifacts/orchestration/epic-orchestrator-state.json already tracks this epic, resume per the epic-orchestrate skill's resume procedure instead of restarting.

Scope

This skill adds no procedure of its own beyond kickoff-artifact resolution; wave scheduling, the wave barrier, merge-on-green fan-in, worktree cleanup, epic-status.md maintenance, and the final integration-to-main PR are governed entirely by the epic-orchestrate skill.

---name: epic-run-2description: Execute a previously planned epic by replaying the committed epic-kickoff artifact through the epic-orchestrator agent. Use after /epic-plan has prepared the epic (issues, folders, research, specs, atomic plans, preflight clearance) and the user is ready to execute end-to-end.---# Epic Run SkillA user invocation (`/epic-run <epic-slug>`) forks the `epic-orchestrator` agent to execute anepic that `epic-planner` has already prepared. The epic slug (or a path under`docs/features/epics/`) for this run is:$ARGUMENTS## Procedure1. Resolve the epic home. A bare slug resolves to `docs/features/epics/<epic-slug>/`; a path argument resolves to its containing epic folder.2. Resolve the committed kickoff artifact `docs/features/epics/<epic-slug>/epic-kickoff.md`. It may exist only on the epic integration branch: `epic-plan` commits it to `epic/<epic-slug>-integration` (worked in a separate integration worktree), so the worktree that invokes `/epic-run` is not guaranteed to have it checked out. Discover it across both locations before concluding it is missing: - Attempt `git fetch origin epic/<epic-slug>-integration`. A failure because the remote branch does not exist is the genuine "epic not planned" case; tolerate it and continue to the local check rather than treating the fetch failure as fatal. - Treat the artifact as present when EITHER the plain local path exists in the invoking worktree, OR it exists on the fetched integration ref, tested with `git cat-file -e epic/<epic-slug>-integration:docs/features/epics/<epic-slug>/epic-kickoff.md` (equivalently `origin/epic/<epic-slug>-integration:<path>`). - When the artifact is present only on the integration ref, read its content with `git show <ref>:<path>`. That is sufficient to extract the `## Invocation Prompt` text needed to proceed; do NOT check the integration branch out into the invoking worktree — the session worktree must never be checked out onto the integration branch (worktree-isolation convention). - STOP without delegating anything only when the artifact is absent BOTH locally and on the fetched integration branch (the branch does not exist, or exists but lacks the file). In that case report that the epic has no committed kickoff artifact: the user must run `/epic-plan` first (or, for an epic that was authored manually, invoke `/epic-orchestrate <epic-manifest-path>` directly).3. Execute the kickoff artifact's `## Invocation Prompt` section as the epic objective, applying the `epic-orchestrate` skill procedure and the `## Prepared-Epic Execution (epic-planner Handoff)` section of `.claude/agents/epic-orchestrator.md`: reuse the existing integration branch, and have each child `Agent(orchestrator)` delegation resume at atomic execution from its committed `plan-path` rather than re-running promotion, research, or planning.4. Honor existing checkpoint state: if `artifacts/orchestration/epic-orchestrator-state.json` already tracks this epic, resume per the `epic-orchestrate` skill's resume procedure instead of restarting.## ScopeThis skill adds no procedure of its own beyond kickoff-artifact resolution; wave scheduling,the wave barrier, merge-on-green fan-in, worktree cleanup, `epic-status.md` maintenance, andthe final integration-to-`main` PR are governed entirely by the `epic-orchestrate` skill.

Frequently asked questions