collectiveai-team/botica / skills/productivity/handoff
handoff
VerifiedCompact the current conversation and workspace state into a handoff document for a fresh agent session.
Write a handoff document summarising the current conversation and workspace state so a fresh agent can continue the work. Save it under the workspace's .tmp/handoff/ directory and name it with the current timestamp and a slugified topic (for example, 2024-01-01T12-00-00-fix-login-bug.md).
Include only what the next agent needs to resume confidently:
- The objective and intended outcome.
- Decisions made, constraints, and important discoveries.
- Current workspace path, worktree path when applicable, branch, and relevant git state.
- Work completed and files changed.
- Verification already run and its results.
- Remaining work, blockers, risks, and the immediate next action.
- A "Suggested skills" section naming only skills relevant to the next action.
Do not duplicate content already captured in other artifacts such as specs, plans, ADRs, issues, commits, research notes, or diffs. Reference them by path or URL and summarize only why they matter. Prefer durable source artifacts over restating conversation history.
Redact any sensitive information, such as API keys, passwords, or personally identifiable information.
When $ARGUMENTS is non-empty, treat it as the next session's focus and tailor the document accordingly.
After writing the file, respond with a short restart prompt that references the handoff path, states the immediate objective, and tells the next agent to inspect the referenced artifacts and current git state before editing. Do not reproduce the full handoff in chat.
Credits and sources: references/CREDITS.md.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 471k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |