farhanhidayatulhaq-max/GAMUKIS / .agents/skills/teamwork-handoff
teamwork-handoff
VerifiedUse when handing off work, reporting results, or resuming another agent's work, writing progress and handoffs with verification evidence and reconciling stale status before editing.
Teamwork Handoff
Before Resuming Another Agent's Work
Status in progress.md and PROJECT.md frequently lags behind the actual code. Reconcile first:
- Read
.agents/teamwork/INDEX.md, then the task'sDISPATCH.md,progress.md, andhandoff.md. - Inspect git status and diff. Treat existing modifications as belonging to another agent unless the dispatch explicitly states otherwise.
- Compare document claims against actual code. Run permitted quick smoke checks if needed.
- Record any discrepancies as a new entry. Never overwrite historical entries.
Writing Handoffs
Use .agents/templates/HANDOFF.md and append new entries to the bottom (append-only):
- Sign:
agent · model · date. Never write on behalf of another agent, even when relaying user requests. - List modified files along with justifications. For read-only findings, provide
path:linereferences. - Verification: specify exact commands executed and actual output (passed/failed counts). Note unperformed checks as "not executed" with rationale.
- Separate verified facts from hypotheses.
- Conclude with the first actionable step for the subsequent agent and files requiring priority reading.
Writing Progress
First line: Status: <draft|ready|in-progress|blocked|review|done|superseded>. Update the task row in teamwork/INDEX.md when the status changes.
Prohibitions
- Machine-specific absolute paths (starting with Windows drive letters or home directories): use relative paths from repository root.
- Credentials, tokens, or passwords, including in command examples. Use placeholders such as
<MYSQL_PASSWORD>. - Copying raw chat logs. Record only current status and active decisions.
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 |