fmilioni
User"Jira for Claude Code": sprint/card/doc project management exposed over MCP, so AI agents plan, execute and track their own development.
Categories
Indexed Skills (2)
autopilot
Use to run the board autonomously — let the AI advance through SEVERAL ready cards on its own, each as an independent PR off main, guided by the blocker graph, without stacked PRs. Trigger when the user says "run the board", "execute the board", "advance on your own", "knock out the ready tasks", "autopilot", or asks the AI to work multiple cards in one go. It maps the dependency graph, settles every ready card's open decisions with the user UP FRONT (so execution never guesses), asks sequential-vs-parallel, then runs each ready card through the `implement` lifecycle + `review` gate on its own branch, opens a PR, and STOPS when only PR-dependent or blocked work remains — never merging to main itself. To execute ONE specific card interactively, use `implement`; to plan a new demand, use `plan`.
plan
Use to turn a NEW fuzzy demand — a feature, a change, a fix — into structured work in claude-organizer (sprints, histories/stories, tasks). Trigger whenever the user describes something new to build (a feature, a change, a fix) before it's broken down, asks to plan/organize the work, or asks to CREATE A CARD (or several) — card creation always runs through this skill, never a direct create_card call. Even a single obvious card goes through here. Understands the demand, organizes it, gets the design approved, then creates the cards. This is PLANNING, not execution — do NOT write code here.
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.