From squad
Before signing off — whether you finished an item or stopped mid-flight — post a 3-bullet summary. Shipped, in flight / queued, surprised by. Three bullets, no ceremony.
How this skill is triggered — by the user, by Claude, or both
Slash command
/squad:squad-handoffThis skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
Every session ends with a 3-bullet brief. The point is to give the next session a one-paragraph cold-start, not a status report. Three bullets, no ceremony.
Every session ends with a 3-bullet brief. The point is to give the next session a one-paragraph cold-start, not a status report. Three bullets, no ceremony.
Invoke this skill at the end of every session: when you finish an item, when you pause mid-item for the day, when you hand off to a coworker, or when the user says "wrap up." Also invoke when you are about to run squad release or /handoff.
in_progress or review and where it stands. If clear, say "queue clear."If you are pausing on an in-progress item, also:
status: in_progress.## Session log section to the item file at the bottom (above ## Resolution):## Session log
### YYYY-MM-DD
- What I did
- What is left
- Any gotchas / dead-ends to avoid
- Next concrete step
STATUS.md under "In Progress" with (uncommitted on branch X).squad say "end of session, picking up <next step> tomorrow" so peers see the pause.If you are truly handing off (not pausing yourself): squad release <ID> --outcome released and name the next concrete step in the chat message. The releasing agent owes the next agent a clean starting point, not just a frozen state.
Sessions are not continuous; agents come and go; coworkers pick up where others left off. The handoff is the seam. A bad handoff costs the next session 30+ minutes of reconstruction; a good handoff costs them 30 seconds. The 3-bullet brief is the minimum content that produces a good handoff — less, and the next session re-discovers; more, and the bullets get skimmed.
squad say).## Session log entry in the item file.squad release <ID> --outcome released with the next-step message.## Session log entry. The next session has no breadcrumb.Provides behavioral guidelines to reduce common LLM coding mistakes, focusing on simplicity, surgical changes, assumption surfacing, and verifiable success criteria.
Searches, retrieves, and installs Agent Skills from prompts.chat registry using MCP tools like search_skills and get_skill. Activates for finding skills, browsing catalogs, or extending Claude.
Creates, edits, and optimizes skills for Claude Code, including drafting, evaluating with test prompts, iterating on performance, and improving skill descriptions for better triggering accuracy.
npx claudepluginhub zsiec/squad --plugin squad