Session Handoff Agent Skill
Creates structured context summaries for continuing work across AI sessions. Use when ending a session to enable seamless continuation in a new session without losing context.
Install
one command, takes just this skill from the repositorynpx skills add https://github.com/ArabelaTso/Skills-4-SE --skill session-handoffThe instruction itself
10 sections, as written by the authorSession Handoff
Generates a detailed handoff document capturing the current state of work, enabling seamless continuation in a fresh AI session.
When to Use This Skill
- Ending a long coding session that will continue later
- Switching between AI tools or models mid-task
- Context window approaching limits, need a fresh session
- Handing off work to a teammate (human or AI)
What This Skill Does
Generate a structured handoff document with:
1. Current State Summary
## Session Summary
**Task**: [What was being worked on]
**Branch**: [Current git branch]
**Status**: [In progress / Blocked / Ready for review]
**Started**: [When work began]
2. What Was Done
## Completed Work
1. [Task 1] — [files changed, what was done]
2. [Task 2] — [files changed, what was done]
### Key Decisions Made
- Chose X over Y because [reason]
- Used pattern Z from [existing file] for consistency
3. What Remains
## Remaining Work
1. [ ] [Next task] — [specific files, what to do]
2. [ ] [Following task] — [dependencies, approach]
### Blockers
- [Any blocking issues with context]
4. Relevant Context
## Key Files
- `src/auth/oauth.ts` — Main implementation file (modified)
- `src/auth/types.ts` — Type definitions (new)
- `tests/auth/oauth.test.ts` — Tests (partially written)
## Patterns to Follow
- Auth middleware pattern from `src/middleware/jwt.ts`
- Error handling style from `src/errors/`
## Gotchas Discovered
- The `UserService` caches aggressively — clear cache after auth changes
- Test DB needs `--runInBand` flag to avoid connection pool exhaustion
## Commands
- Build: `npm run build`
- Test: `npm test -- --runInBand`
- Verify: `npm run typecheck`
5. Continuation Instructions
## How to Continue
1. Read this handoff document
2. Check `git status` and `git log -5 --oneline` for current state
3. Start with [specific next task]
4. Reference [specific file] for the pattern to follow
Tips
- Write the handoff BEFORE you lose context, not after
- Include specific file paths, not vague descriptions
- Document gotchas — things that surprised you during the session
- Include the exact commands needed to verify work
- Keep it under 200 lines — the next session needs room in its context window
Example
User: "Create a handoff for this session"
Output: Generates a structured markdown document covering: 3 completed tasks with file paths, 2 remaining tasks with specific instructions, 4 key files with their roles, 2 gotchas discovered during the session, and exact build/test commands.
Inspired by: oh-my-opencode /handoff command
Other skills for the same job
different authors, same section of the catalogue
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
Replace with description of the skill and when Claude should use it.
Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies
This skill should be used when the user wants to "create a skill", "add a skill to plugin", "write a new skill", "improve skill description", "organize skill content", or needs guidance on skill structure, progressive disclosure, or skill development best practices for Claude Code plugins.
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
Use when creating new skills, editing existing skills, or verifying skills work before deployment
How to use it
Take arabelatso/session-handoff from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.