Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
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
  • Authors
  • 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
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Handoff

ASecurity

Compress the current session into a concise handoff document for another agent

10 stars
0 votes
0 copies
1 views
Added 9/19/2026
ai-agentsgogit

Works with

cursor

Security Analysis

A100/100

Scanned 9/19/2026

$npx -y skills add initxy/noeta --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/initxy-handoff/badge)](https://www.skillsdirectory.com/skills/initxy-handoff)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: handoff
description: Compress the current session into a concise handoff document for another agent
argument-hint: [focus, e.g. "emphasize the open bug" or a target file path]
---

# Hand off the session

Distill everything that matters about the current task into a self-contained handoff
document, so a fresh agent with none of this conversation's context can pick up exactly
where you left off.

Take any focus or output target from the conversation; with none given, cover
the whole task so far.

## Steps

1. Recover the ground truth. Don't rely on memory alone — run `git_status` and
   `git_diff` to capture the actual in-progress changes, and `read` the key files
   you've been editing so the handoff reflects the real current state.
2. Write the handoff with these sections, in this order:
   - **Goal** — the task in one or two sentences: what we're trying to achieve and why.
   - **State** — what is already done and working, with the concrete files / functions
     touched (cite paths).
   - **In progress** — what is half-done right now, and where exactly the cursor is.
   - **Next steps** — the ordered, specific actions the next agent should take.
   - **Open questions / risks** — unresolved decisions, blockers, and known gotchas.
   - **How to verify** — the exact commands to build / test / run this work.
3. Be specific and load-bearing. Prefer file paths, command lines, function names, and
   exact error messages over vague summaries. Cut anything the next agent could
   rediscover trivially.
4. Emit the result. By default print the handoff as your final message. If the user
   asked for a file (or named a path above), write it there with `write_file`.

Capture only what you actually know from this session and the files you read — do not
speculate about parts of the codebase you never looked at.

(fork agent: main)

Attribution

initxyinitxy
View sourceSee grades on GitHubMore from initxy →
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

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 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', ...

698621 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 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.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, 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.

741 votes
View all in ai-agents →