orchestrate-epic
Coordinates a multi-ticket epic (a Jira/GitLab epic, or a GitHub issue whose child issues are the tickets). Builds the dependency graph and parallel wave schedule, routes each workable ticket to a background agent or its own session, re-verifies what unblocked as tickets finish, and runs the repo's PR merge gate when its CLAUDE.md defines one. Use when the user wants to parallelize an epic without breaking dependencies, asks what is unblocked now, or wants a resident coordinator for the epic. Not for a single ticket (fast-feature) or for picking one best task (best-roi-task).
89%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Low
Low-risk findings worth noting
The canonical home for this skill is orchestrate-epic in AndreJorgeLopes/devflow
W011: Third-party content exposure detected (indirect prompt injection risk).
What this means
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
Why it was flagged
The workflow reads child issues and text from Jira and GitHub repositories containing outsider-authored free text.
- Repository
AndreJorgeLopes/devflow
- Revision
a9e5962
- Audited
- Security analysis
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.