Agent skill

Handoff

Capture session decisions, conventions, and lessons into plan files, auto-memory, and CLAUDE.md so a fresh session resumes cleanly.

MITAuto-check passedAgent Workflows

Install Handoff

skills CLI

$ npx skills add TyrealQ/q-skills --skill handoff -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI

$ gh skill install TyrealQ/q-skills handoff --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy

$ git clone --depth 1 https://github.com/TyrealQ/q-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/handoff .claude/skills/handoff && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Paste into Claude Code

Install the "handoff" agent skill from https://github.com/TyrealQ/q-skills/tree/main/skills/handoff into .claude/skills/handoff/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "handoff", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/TyrealQ/q-skills/tree/main/skills/handoff

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add TyrealQ/q-skills --skill handoff -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install TyrealQ/q-skills handoff --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/TyrealQ/q-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/handoff .agents/skills/handoff && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "handoff" agent skill from https://github.com/TyrealQ/q-skills/tree/main/skills/handoff into .agents/skills/handoff/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "handoff", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add TyrealQ/q-skills --skill handoff -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install TyrealQ/q-skills handoff --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/TyrealQ/q-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/handoff .cursor/skills/handoff && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "handoff" agent skill from https://github.com/TyrealQ/q-skills/tree/main/skills/handoff into .cursor/skills/handoff/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "handoff", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/TyrealQ/q-skills.git --path skills/handoff

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add TyrealQ/q-skills --skill handoff -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install TyrealQ/q-skills handoff --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/TyrealQ/q-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/handoff .gemini/skills/handoff && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "handoff" agent skill from https://github.com/TyrealQ/q-skills/tree/main/skills/handoff into .gemini/skills/handoff/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "handoff", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install TyrealQ/q-skills handoff

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add TyrealQ/q-skills --skill handoff -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/TyrealQ/q-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/handoff .github/skills/handoff && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "handoff" agent skill from https://github.com/TyrealQ/q-skills/tree/main/skills/handoff into .github/skills/handoff/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "handoff", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add TyrealQ/q-skills --skill handoff -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install TyrealQ/q-skills handoff --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/TyrealQ/q-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/handoff .opencode/skills/handoff && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "handoff" agent skill from https://github.com/TyrealQ/q-skills/tree/main/skills/handoff into .opencode/skills/handoff/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "handoff", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: handoff
GitHub stars: 108
Token cost: ~1.6k tokens
SKILL.md length: 808 words
Files: 1
Skills in repo: 16
Repo updated: Sep 23, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

Capture session decisions, conventions, and lessons into plan files, auto-memory, and CLAUDE.md so a fresh session resumes cleanly.

Works in 4 steps: Survey the session → Locate destinations → Apply updates → …
Update docs for next session
SKILL.md covers Workflow and Anti-patterns
Calls git

What it does

Handoff is an agent skill from TyrealQ/q-skills. Capture session decisions, conventions, and lessons into plan files, auto-memory, and CLAUDE.md so a fresh session resumes cleanly. Use for "hand off," "wrap up," "update docs for next session," or before /compact.

Its SKILL.md is about 1.6k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Agent Workflows, covering Agent instruction files. The repository describes itself as: End-to-end skills for academic writing, data analysis, teaching, and research communication. The licence is MIT.

When your agent uses it

Update docs for next session
Before /compact

Example prompts

“hand off,”
“wrap up,”
“update docs for next session,”
“/handoff”

Workflow steps

4 steps, taken from the step headings in SKILL.md.

Survey the session
Locate destinations
Apply updates
Produce a resume prompt

What it can do on your machine

Read from SKILL.md and the folder at commit d8aaee7. It shows what the files ask for, not the result of running them.

Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
- git
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Handoff loads about 1.6k tokens when it runs. Until then it costs about 56 tokens; SKILL.md has 808 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~56
When it runs · the whole SKILL.md, loaded when a task matches: ~1.6k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from TyrealQ/q-skills at commit d8aaee7, republished under its MIT licence (© TyrealQ). 808 words, ~1,571 tokens.

Download SKILL.mdSave it as .claude/skills/handoff/SKILL.md (or your agent's skills folder).

name: handoff
description: Capture session decisions, conventions, and lessons into plan files, auto-memory, and CLAUDE.md so a fresh session resumes cleanly. Use for "hand off," "wrap up," "update docs for next session," or before /compact.

handoff

Captures the load-bearing outcomes of a session and writes them to the right durable location. Goal: a future session can pick up without re-deriving context from the transcript.

Workflow

Step 1 — Survey the session

Identify what changed beyond the literal edits.

bash

git log --oneline <session-start>..HEAD
git diff <session-start>..HEAD --stat

If session-start is unclear, infer from the first commit timestamp after a context reset, or ask the user.

For each commit, note:

Decisions: terminology choices, structural conventions, methodological positions taken
Conventions reinforced or established: subtitle patterns, voice rules, argument structures, naming schemes
Controversies resolved: where the user pushed back and a final position landed
Lessons that emerged: when an early draft failed, what symptom triggered the fix, what rule the fix expressed (latent rules > literal pushbacks)

Skip routine work: typo fixes, formatting-only changes, mechanical refactors. Only capture outcomes a future session would otherwise have to re-derive.

Step 2 — Locate destinations

Discover what already exists; do not create new doc locations without asking.

bash

# Plan files (task tracking, current state, open items)
ls ~/.claude/plans/ 2>/dev/null | grep -i <project-keyword>

# Auto-memory (cross-session learnings keyed to project)
ls ~/.claude/projects/<project-id>/memory/ 2>/dev/null

# Project CLAUDE.md (project conventions, structure, banned terms)
ls <project-root>/CLAUDE.md 2>/dev/null

# User CLAUDE.md (cross-project preferences)
ls ~/CLAUDE.md 2>/dev/null

Match each session outcome to the right destination:

Outcome type	Destination
Task progress, completed items, residual open items	Plan file
Verified-state anchors (specific phrasings that mark current correct state)	Plan file
Writing/coding lessons, symptom → rule patterns	Auto-memory `*_lessons.md`
Banned terms, terminology decisions	Auto-memory `*_terms.md` (or project CLAUDE.md if it already lists them)
Project-level conventions (file layout, naming, structure)	Project CLAUDE.md
Cross-project user preferences	User CLAUDE.md

Do not duplicate. If a rule lives in CLAUDE.md, do not also add it to memory; if a lesson lives in memory, do not restate it in the plan.

Step 3 — Apply updates

Read every target file before editing. Match the existing style, depth, and section conventions.

Plan files: mark resolved items with strikethrough or RESOLVED YYYY-MM-DD tag; append new open items; refresh "verified state" anchors with the line content as it stands now (not as drafted earlier in the session).
Auto-memory *_lessons.md: append numbered lessons (L7, L8, ...) with trigger + corrective move + brief rationale. Update the file's frontmatter description if the scope expanded.
MEMORY.md index: add a pointer line only if a new memory file was created. Update the existing entry's hook only if its underlying content shifted materially. Keep each line under ~150 chars.
Project CLAUDE.md: insert into the appropriate existing section (style rules, structure, etc.). Do not create a session log section. If a new convention does not fit any section, ask before adding.
User CLAUDE.md: only for preferences that generalize beyond the current project. Be conservative.

Show full SKILL.md (410 more words)Show less

Step 4 — Produce a resume prompt

Output a single message the user can copy-paste verbatim into a fresh session as the opening prompt. The next Claude reads this message and a fresh, cold-started auto-memory load — nothing else from the prior transcript carries over. The resume prompt must be self-contained.

Wrap the resume prompt in a clearly delimited block (e.g., ```text ... ```) so the user can copy it cleanly.

Required sections, in order:

Context — one sentence on what project this is and what stage the work is at.
Read first — explicit absolute paths to the files the next Claude should load before acting (plan file, key memory files if not auto-loaded, the canonical source document, the active downstream document). Annotate each with one phrase on why.
Where we left off — last 2–4 commits relevant to the resumed thread (hash + one-line summary). Do not list every commit; only the load-bearing ones.
Conventions to honor — only conventions established or reinforced THIS session that have not yet propagated into memory or CLAUDE.md. If everything is durable, write "All conventions are captured in memory and the plan file."
Next task — the single most actionable next item with a file:line pointer and a one-sentence statement of the change to make. If multiple, list up to 3 in priority order.
Known gotchas — only if relevant: discrepancies, blockers, or non-obvious traps the next session should be aware of. Omit the section if none.

After the wrapped resume prompt, add a 2-line operator note for the user (outside the block):

where the new commits and doc updates landed (commit-hash range, files touched)
whether anything is uncommitted

Keep the resume prompt itself under ~250 words. The user pastes it; the next Claude executes from there.

Anti-patterns

Don't write session logs into project files. Permanent docs capture conventions, not session narratives.
Don't update CLAUDE.md with rules already in memory (and vice versa). Each rule has one durable home.
Don't create new doc locations without asking. Use what exists.
Don't restate edits as "decisions." A typo fix is not a decision. A terminology choice the user pushed back on twice is.
Don't bloat memory. Each memory file should have a clear scope. If a new lesson does not fit any existing file, ask before creating a new one.
Don't extract lessons the user has not validated. A first-draft pattern from one session is a hypothesis, not a rule. Wait for repeated correction or explicit confirmation before persisting.

Files

Just SKILL.md in skills/handoff of TyrealQ/q-skills.

Open the folder on GitHubat commit d8aaee7

Compare with similar skills

Handoff next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Handoff compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Handoff this skillTyrealQ/q-skills	108	—	~1.6k	Automated safety check: Pass	MIT	15 days ago
Using Agent Skillsaddyosmani/agent-skills	103k	4 repos	~2.4k	Automated safety check: Pass	MIT	5 days ago
Claude ReflectBayramAnnakov/claude-reflect	1.7k	2 repos	~627	Automated safety check: Pass	MIT	5 days ago
Writing For Agentsbestofjs/bestofjs	3.1k	19 repos	~2.7k	Automated safety check: Pass	MIT	4 days ago
Neat-Freak Knowledge CloseoutKKKKhazix/khazix-skills	21k	—	~1.9k	Automated safety check: Pass	MIT	7 days ago
Task Observerrebelytics/one-skill-to-rule-them-all	3.2k	1 repos	~12k	Automated safety check: Pass	CC-BY-4.0	6 days ago

Similar skills

Using Agent Skills
addyosmani/agent-skills
Meta-skill for choosing which workflow skill fits the task at hand, plus always-on habits: surface assumptions, stop on confusion, push back, keep it simple and stay in scope.
103k GitHub starsUsed in 4 repos~2.4k tokens
Agent WorkflowsAuto-check passed
Claude Reflect
BayramAnnakov/claude-reflect
Self-learning system that captures corrections during sessions and reminds users to run /reflect to update CLAUDE.md.
1.7k GitHub starsUsed in 2 repos~627 tokens
Agent WorkflowsAuto-check passed
Writing For Agents
bestofjs/bestofjs
Writing documents for agents. An agent skill from bestofjs/bestofjs.
3.1k GitHub starsUsed in 19 repos~2.7k tokens
Agent WorkflowsAuto-check passed
Neat-Freak Knowledge Closeout
KKKKhazix/khazix-skills
Brings project docs, agent rule files, authorized memory and leftover workspace files back in line with what the code and runtime actually do at the end of a work session.
21k GitHub stars~1.9k tokensUpdated 7 days ago
Agent WorkflowsAuto-check passed
Task Observer
rebelytics/one-skill-to-rule-them-all
Monitors task execution for skill improvement opportunities.
3.2k GitHub starsUsed in 1 repo~12k tokens
Agent WorkflowsAuto-check passed
SkillOpt Sleep Cycle
microsoft/SkillOpt
Official
Runs an on-demand or nightly sleep cycle that reviews past Claude Code sessions and proposes validated updates to CLAUDE.md and skills.
18k GitHub stars~2.3k tokensUpdated 2 days ago
Agent WorkflowsAuto-check passed

More from TyrealQ/q-skills

All 16 skills in this repo

Q-Infographics
TyrealQ/q-skills
Converts a report or other document into a business story and then an infographic image, pausing for your review after each step.
108 GitHub stars~814 tokensUpdated 15 days ago
Auto-check: notes
Q-EDA Exploratory Analysis
TyrealQ/q-skills
Runs exploratory data analysis on tabular data after you confirm each column's measurement level, then writes CSV tables and a narrative summary.
108 GitHub stars~1.1k tokensUpdated 15 days ago
Auto-check passed
Multimodal Media Feature Extraction
TyrealQ/q-skills
Extracts pixel, video-frame, speech, music and visual-semantic features from image, video and audio files for research datasets, using local tools or the Gemini API.
108 GitHub stars~2k tokensUpdated 15 days ago
Auto-check: notes
Topic Model Consolidation
TyrealQ/q-skills
Consolidates BERTopic, LDA or NMF topic output into a theory-driven classification framework and writes the final labels back to an Excel file.
108 GitHub stars~1k tokensUpdated 15 days ago
Auto-check passed
Q-Presentations Slide Deck Generator
TyrealQ/q-skills
Generates branded slide deck images from written content, with a content analysis step, a layout catalog and scripts that merge the slides into PowerPoint or PDF.
108 GitHub stars~1.1k tokensUpdated 15 days ago
Auto-check passed
Repository Layout and Docs Auditor
TyrealQ/q-skills
Audits a repository's file layout and project documentation against a written convention file, then proposes moves, deletions and doc fixes as an approved plan before touching anything.
108 GitHub stars~4.4k tokensUpdated 15 days ago
Auto-check: notes

Questions about Handoff

What does Handoff do?

Capture session decisions, conventions, and lessons into plan files, auto-memory, and CLAUDE.md so a fresh session resumes cleanly. Handoff is an agent skill from TyrealQ/q-skills.md so a fresh session resumes cleanly.

When should I use Handoff?

Handoff fits situations like: update docs for next session; before /compact.

How do I install Handoff in Claude Code?

Run `npx skills add TyrealQ/q-skills --skill handoff -a claude-code`. Or copy the skill folder (skills/handoff in TyrealQ/q-skills) into .claude/skills/handoff in your project. Claude Code loads it when a task matches its description.

How do I install Handoff in Codex?

Run `npx skills add TyrealQ/q-skills --skill handoff -a codex`. Or copy the skill folder (skills/handoff in TyrealQ/q-skills) into .agents/skills/handoff in your project. Codex loads it when a task matches its description.

Can I use Handoff in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add TyrealQ/q-skills --skill handoff -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/handoff, .gemini/skills/handoff, .github/skills/handoff and .opencode/skills/handoff in your project.

What does Handoff need to run?

Going by SKILL.md and its folder, Handoff needs the command-line tools its instructions call (git).

Does Handoff access the network?

SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Handoff safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Handoff use?

Handoff is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Handoff use?

About 1.6k tokens (SKILL.md is roughly 6.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Handoff?

Skills that share tags, products or a category with Handoff: Using Agent Skills (addyosmani/agent-skills, 103k stars), Claude Reflect (BayramAnnakov/claude-reflect, 1.7k stars), Writing For Agents (bestofjs/bestofjs, 3.1k stars) and Neat-Freak Knowledge Closeout (KKKKhazix/khazix-skills, 21k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Handoff?

TyrealQ (a GitHub user) maintains it in TyrealQ/q-skills, which has 108 GitHub stars. The repository holds 16 skills in this directory. The repository was last updated on September 23, 2026.

Source: TyrealQ/q-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install Handoff

Facts

At a glance

What it does

When your agent uses it

Example prompts

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

handoff

Workflow

Step 1 — Survey the session

Step 2 — Locate destinations

Step 3 — Apply updates

Step 4 — Produce a resume prompt

Anti-patterns

Files

Compare with similar skills

Similar skills

More from TyrealQ/q-skills

Related

Questions about Handoff