Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

Back to skills

Handoff

ASecurity

Generate a concise session handoff for resuming work later, including current state, decisions, open issues, and next steps.

2 stars
0 votes
0 copies
0 views
Added 9/22/2026
ai-agentsgogit

Works with

cli

Security Analysis

A100/100

Scanned 9/22/2026

Install to Claude Code

$npx -y skills add jckeen/dotfiles --skill handoff --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Handoff?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Handoff
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/jckeen-handoff/badge)](https://www.skillsdirectory.com/skills/jckeen-handoff)

More formats (shields.io, HTML) on the badges page.

Download Zip
Files
SKILL.md
---
name: handoff
description: Generate a concise session handoff for resuming work later, including current state, decisions, open issues, and next steps.
---

# Handoff

Use when the user asks for a handoff, context note, session summary, or resume
brief.

## Workflow

1. Inspect the current repo state with `git status --short`.
2. Review relevant recent commits or diffs if needed.
3. Summarize only durable context that would help the next session.
4. Queue USER ACTION items to `~/.claude/operator-queue.md` — see
   "Operator-action queue" below for the block format and rules.
5. Session-end hygiene (before saving the note):
   - `git worktree list` — record every task worktree as removed, or retained
     with its owner, reason, PR, and concrete follow-up command. Follow the
     shared lifecycle procedure in `claude/scripts/README.md`. Stop owned
     processes first and archive recovery/review evidence. Remove explicitly
     released worktrees only after verified integration and applicable user or
     standing cleanup authorization. Preserve active/locked worktrees, unique
     work, dirty/untracked/ignored content, stashes and unknown ownership.
     Pending PRs retain their worktrees; release the exact completed artifact
     when appropriate so a later session can assess it after merge.
   - Inventory local branches fully merged into the default branch
     (`git branch --merged "$(git rev-parse --abbrev-ref origin/HEAD)"` —
     don't assume it's named `main`). Delete them only when the user or an
     applicable standing order explicitly authorizes branch deletion.
   - Push or PR every branch that has work on it — never leave work
     stranded local-only.
   - `gh pr list` — note each open PR's review + CI state in the
     handoff's "Open issues" section.
6. Save the note to `~/.claude/handoffs/YYYY-MM-DD-<project>-handoff.md` —
   the same directory the Claude `/handoff` skill uses, so either tool can
   resume the other's session. Create the directory if needed. Never save it
   inside the public repo.

## Output

Use the same section names as the Claude `/handoff` skill so notes are
interchangeable across tools:

```markdown
## Handoff — YYYY-MM-DD

### What we did
- ...

### Where we left off
- ...

### Key decisions made
- ...

### Open issues
- ...

### Next steps
- ...

### Context for next session
- ...

### Session continuity
- (optional) Resumable agent sessions: my Codex session id (`codex resume <id>`),
  or an agy conversation id (`agy --conversation <id>`). Omit if none.
```

Keep it concise. Do not include secrets, private project details, tokens, or
machine-specific paths unless the user explicitly asks and the destination is
private.

### Operator-action queue

Anything only the operator can do (rotate a token, click an approval, decide
on a purchase) goes to the durable queue at `~/.claude/operator-queue.md` —
handoff prose gets buried by the next handoff; the queue does not. One item
per block:

```markdown
## <stable-slug>
- added: YYYY-MM-DD
- project: <source project>
- deadline: YYYY-MM-DD
- verified: YYYY-MM-DD
- action: <one line: what the operator must do>
```

The slug is stable (same action = same slug across sessions); `deadline` and
`verified` are optional — omit the line if none. **Append only if absent** —
match on the slug, never re-add or duplicate an existing item. **Remove an
item's block only when the action is actually done**, not when it's merely
mentioned again.

`verified` records the last time the item was checked against live state
(the PR, the env var, the dashboard — not the previous handoff). **When a
session touches an item's subject, re-check it against live state and
set/bump `verified`; remove the block only when done.** The SessionStart
reminder treats the newest of `verified`/`added` as the item's freshness and
marks anything older than 30 days `[stale — re-verify]`, so an unbumped item
announces its own rot instead of being repeated as fact.

Attribution

jckeenjckeen
View sourceMore from jckeen →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".

1066601 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

686011 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3351 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

651 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →