$ loading_
Create a path-free handoff prompt another agent can immediately use.
Copy the install command and let the AI configure it · recommended for beginners
Please install the "handoff" skill from askskill: 1. Download https://raw.githubusercontent.com/openclaw/agent-skills/main/skills/handoff/SKILL.md 2. Save it as ~/.claude/skills/handoff/SKILL.md 3. Reload skills and tell me it's ready
Write a handoff prompt to delegate investigation of an intermittent 500 error in the login API to another agent. Avoid file paths, include repo clues, known symptoms, constraints, validation expectations, and ask them to independently review before deciding on a fix.
A copy-ready handoff prompt that lets another agent independently review and continue the investigation.
Help me write a handoff prompt that passes the discussion of whether to add filters to report export to another agent. Emphasize that this is not a command-only task; they should first assess whether the request is valid, over-scoped, or already has a better alternative.
A discussion-oriented handoff prompt that asks the receiving agent to make an independent judgment before proceeding.
Write a handoff prompt for another agent to follow up on a PR. Include the PR name or link, current state, non-goals, output format, and remind them to re-check the latest repo, GitHub, and CI status.
A PR-focused handoff prompt with context, boundaries, and instructions to re-verify live state.
When you already know part of the problem context but want another agent to continue independently, this skill can generate a complete handoff prompt. It emphasizes known clues, constraints, and review-before-action expectations.
When a task is still in discussion and not yet clearly worth implementing, this skill writes a discussion-oriented handoff. The receiving agent is prompted to judge whether the task is stale, over-scoped, or better solved another way.
When you need to pass issue-, PR-, or branch-related work to another agent, it organizes context using portable anchors such as repo names, links, and exact error text. This reduces dependence on local paths and makes pickup easier across different working directories.
The README describes a skill for creating clipboard-ready handoff prompts that let another agent investigate, discuss, or continue a task. It outlines a workflow of identifying the task, gathering enough context, writing a standalone prompt, and copying it to the clipboard. The main guidance is to avoid file paths, use portable anchors, require an independent review by the receiving agent, re-check live repo and CI state, and clearly state constraints, non-goals, and expected output.
Write a clipboard-ready prompt for another agent to investigate, discuss, or work on a specific task.
Use when the user asks for handoff <task>, "write a handoff", "delegate this",
or wants a prompt for another agent.
The prompt must:
Use this shape by default:
I want to discuss and possibly work on: <short task title>
Context:
- <portable repo/product context>
- <what triggered this task>
- <known current state, branch/issue/PR names or URLs if relevant>
- <important constraints and ownership boundaries>
Before doing any implementation:
- Find the right repository from the current directory, a parent directory, or the usual workspace.
- Read the local agent/repo instructions.
- Inspect the relevant code, docs, tests, recent commits, and linked issue/PR state.
- Decide whether this task is still real, whether the proposed direction is a good idea, and whether a smaller/better fix exists.
- Call out stale assumptions, hidden risks, and anything that should stop the work.
Task:
- <what to investigate or implement if the review supports it>
- <expected behavior or decision criteria>
- <non-goals>
Validation:
- <focused tests/checks/live proof expected>
- <what evidence should be included>
- <what is explicitly not required>
Output:
- Start with your review findings and recommendation.
- Then give the proposed plan or patch summary.
- If you edit code, keep changes scoped and report exact proof run.
- Do not push, merge, close issues/PRs, label, or post public comments unless explicitly told.
On macOS:
pbcopy < /tmp/handoff-prompt.txt
Use a temp file or pipe. Avoid inline shell quoting for prompts containing
backticks, $, quotes, or user text.
If pbcopy is unavailable, use the obvious platform clipboard tool (wl-copy,
xclip, clip.exe) or print the prompt and say clipboard copy was unavailable.
…
It creates a copy-ready handoff prompt for another agent to investigate, discuss, or take over a task. The docs emphasize that the prompt provides starting context, while the receiving agent is responsible for independent review and judgment.
The docs require path-free handoffs because the receiving agent may start from the repo, a parent directory, a workspace, or a home directory. They recommend portable anchors such as repo names, branch names, PR links, public symbols, exact error text, and search terms.
No. The docs explicitly say not to perform the receiving agent’s full independent review or pre-decide the final technical direction. Instead, the receiving agent should inspect code, docs, tests, and current state before deciding whether the task still makes sense.
Render AI session JSONL logs into searchable, shareable single-file HTML viewers.
Run cross-platform OpenClaw remote validation with provider and lease reporting.
Run a structured code review before commit or release on local or PR branches.
Attach redacted agent transcripts to GitHub PRs or issues for local provenance.
Generate concept, architecture, flow, and whiteboard diagrams in multiple formats.
Helps maintainers triage, clean up, and resolve OpenClaw secret scanning alerts.
Enable verifiable agent task handoffs with signed, auditable provenance chains.
Delegate subtasks to DeepSeek within Claude Code or Codex sessions.
Delegate long-running task decisions to an OpenAI reviewer for structured next steps.
Turn finalized designs into clear developer handoff specs for implementation.
Helps coding agents delegate investigations and compress subagent findings into usable context.
Enable verifiable agent handoffs with signed provenance for trusted multi-agent workflows.