handoff
Compact the current conversation into a handoff document for another agent to pick up.
Skill by dwin
Chalk Labs
Need help deploying handoff?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/dwin-handoff
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: documents, agent-building
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/handoff
What's inside
- Skill name
handoff- Description
- Compact the current conversation into a handoff document for another agent to pick up.
- License
- MIT
- Instructions
- 27 lines in SKILL.md · view on GitHub
Files (2)
- SKILL.md
- openai.yaml · agents/
SKILL.md (first lines)
Write a handoff document summarising the current conversation so a fresh agent can continue the work. Save to the temporary directory of the user's OS (`$TMPDIR`, else `/tmp`; `%TEMP%` on Windows) - not the current workspace. Include a "suggested skills" section in the document, which suggests skills that the agent should invoke. Capture the state needed to resume without repeating decisions: - The active objective, acceptance criteria, and next executable step. - Repository and worktree paths, branch, head SHA, PR links, and local changes. - Decisions and permissions already given, their scope, and explicit holds or actions still awaiting approval. - Completed validation with its revision and environment; distinguish local checks, remote CI, deployment, and runtime evidence. - Outstanding findings, dependencies, owners, and any running monitor or review that the next session must reattach to or replace. Label observations with their time or revision. Tell the receiving agent which mutable state to refresh before acting, especially the PR head, remote checks, worktree changes, and coordinator ownership. A handoff preserves the task and its authorization; it does not make old observations current. Do not duplicate content already captured in other artifacts (specs, plans, ADRs, issues, commits, diffs). Reference them by path or URL instead. Redact any sensitive information, such as API keys, passwords, or personally identifiable information. If the user passed arguments, treat them as a description of what the next session will focus on and tailor the doc accordingly.
From dwin/skills, MIT.
More from dwin/skills
- 0.570score
file-pr
dwin
Create, open, file, or submit a pull request with an outcome-focused title and description.
SkillAFreshness: AClaude Code +9 - 0.570score
autopilot
dwin
Drive a branch to a ready pull request.
SkillAFreshness: AClaude Code +9 - 0.570score
managing-workspaces
dwin
Manage the lifecycle of isolated task checkouts and their build storage.
SkillAFreshness: AClaude Code +9 - 0.567score
engineering-principles
dwin
Apply simple, type-safe engineering practices while implementing, refactoring, testing, or reviewing TypeScript, Go, or C#.
SkillAFreshness: AClaude Code +9 - 0.565score
babysit-pr
dwin
Monitor or babysit an open pull request through CI, mergeability changes, and review feedback.
SkillAFreshness: AClaude Code +9 - 0.565score
grilling
dwin
Interview the user rigorously about a plan, design, decision, or idea until consequential assumptions and branches are resolved.
SkillAFreshness: AClaude Code +9 - 0.563score
sprites
dwin
Run builds, tests, data jobs, development services, or agent tasks on Fly.io Sprites when local CPU, memory, disk, or Linux compatibility is a constraint.
SkillAFreshness: AClaude Code +9 - 0.544score
diagnosing-bugs
dwin
Diagnosis loop for hard bugs and performance regressions.
SkillAFreshness: AClaude Code +9 - 0.539score
code-review
dwin
Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes — Standards (does the code follow this repo's documented coding…
SkillAFreshness: AClaude Code +9 - 0.533score
implement
dwin
Implement a piece of work based on a spec or set of tickets.
SkillAFreshness: AClaude Code +9 - 0.530score
retro
dwin
Conduct a retrospective on a coding session.
SkillAFreshness: AClaude Code +9 - 0.524score
focus-output
dwin
Keep responses action-first, low-distraction, and easy to resume for the rest of the session.
SkillBFreshness: BClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Oct 20, 2026 (10 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/dwin/skills
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from dwin
- 0.570score
file-pr
dwin
Create, open, file, or submit a pull request with an outcome-focused title and description.
SkillAFreshness: AClaude Code +9 - 0.570score
managing-workspaces
dwin
Manage the lifecycle of isolated task checkouts and their build storage.
SkillAFreshness: AClaude Code +9 - 0.570score
autopilot
dwin
Drive a branch to a ready pull request.
SkillAFreshness: AClaude Code +9 - 0.567score
engineering-principles
dwin
Apply simple, type-safe engineering practices while implementing, refactoring, testing, or reviewing TypeScript, Go, or C#.
SkillAFreshness: AClaude Code +9 - 0.565score
babysit-pr
dwin
Monitor or babysit an open pull request through CI, mergeability changes, and review feedback.
SkillAFreshness: AClaude Code +9 - 0.565score
grilling
dwin
Interview the user rigorously about a plan, design, decision, or idea until consequential assumptions and branches are resolved.
SkillAFreshness: AClaude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get handoff running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
handoff skill. Agent Mart. https://agentmart.dev/skills/dwin-handoff (last updated 2026-10-24)