Run any Skill in Manus with one click

handoff

Stars4

Forks0

UpdatedFebruary 12, 2026 at 14:37

Create HANDOFF.md files for session continuity between conversations. Use when ending a session, switching context, or before /compact.

Installation

Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.

Run Skill in Manus

Source

pfangueiro

pfangueiro/claude-code-agents

View GitHub Repository View Creator Repositories

Download

Run Skill in Manus

Related occupationsSOC

Based on SOC occupation classification

Software DevelopersComputer and Mathematical Occupations·SOC 15-1252

SKILL.md

readonly

name	handoff
description	Create HANDOFF.md files for session continuity between conversations. Use when ending a session, switching context, or before /compact.

Handoff

Preserve context across Claude Code sessions by writing a structured HANDOFF.md file at the project root.

When to Use

Before ending a long session
Before running /compact to free context
When switching to a different task and planning to return
When handing work to another developer or agent

How It Works

Check if a HANDOFF.md already exists in the project root
If it does, read it first to build on previous context
Write/update HANDOFF.md with the five sections below

HANDOFF.md Format

# Handoff — [Project Name]

**Date**: YYYY-MM-DD HH:MM
**Branch**: current git branch

## Goal
What we're trying to accomplish overall.

## Current Progress
- What's been completed this session
- Files created or modified (with paths)
- Decisions made and rationale

## What Worked
- Approaches or patterns that succeeded
- Key insights discovered

## What Didn't Work
- Approaches tried and abandoned (with reasons)
- Pitfalls to avoid next time

## Next Steps
1. Specific actionable items for the next session
2. Ordered by priority
3. Include file paths and context needed

Rules

Always include the current git branch and date
Be specific about file paths — the next session has zero context
List what didn't work so the next session doesn't repeat failed approaches
Keep it under 100 lines — enough to resume, not a novel
If a HANDOFF.md exists, update it rather than overwriting blindly

Example

# Handoff — checkout-service

**Date**: 2026-02-12 14:30
**Branch**: feat/stripe-checkout

## Goal
Implement Stripe checkout flow with webhook verification.

## Current Progress
- Created `src/api/checkout.ts` with createSession endpoint
- Added `src/api/webhooks/stripe.ts` for webhook handler
- Database migration `migrations/005_orders.sql` applied
- Unit tests passing for checkout session creation

## What Worked
- Using Stripe's PaymentIntent API instead of Charges (simpler flow)
- Zod schema validation on webhook payload before processing

## What Didn't Work
- Tried using Stripe Checkout Sessions redirect — didn't work with SPA routing
- webhook signature verification failed when using raw body parser from express (need raw buffer)

## Next Steps
1. Fix webhook body parsing — use `express.raw()` middleware for `/api/webhooks/stripe`
2. Add idempotency key to prevent duplicate order creation
3. Write integration tests for the full checkout -> webhook -> order flow
4. Add error handling for failed payments (update order status)

More from this repository

same repository

diverge

pfangueiro/claude-code-agents

Structured divergence engine. Generates a wide, deliberately non-anchored set of approaches to a consequential, open-ended problem by spawning isolated parallel sub-agents under different cognitive frames, then a separate critic pass scores, declusters, and deepens the best. The divergent complement to /deep-analysis. Use for high-stakes architecture, strategy, design-space, and "what are our options" decisions. Auto-activates on diverge, brainstorm options, explore alternatives, what are our options, de-anchor, divergent thinking, option space, consider alternatives, multiple approaches.

2026-07-074

execute

pfangueiro/claude-code-agents

Orchestrated task execution engine. Decomposes any goal into small atomic tasks, plans dependencies, selects the right agent/tool/MCP server for each, executes in optimally parallel batches, and tracks everything. Use when given a complex, multi-step goal that benefits from structured decomposition and full tool utilization.

2026-07-074

multi-agent-orchestration

pfangueiro/claude-code-agents

Advanced multi-agent patterns using Claude Code's built-in orchestration. Teams, background agents, coordinator pattern, worker restrictions, SendMessage protocol, fork subagents. Auto-activates on multi-agent, orchestrate, team, coordinator, parallel agents, worker agents, background agent, agent swarm.

2026-07-074

deep-analysis

pfangueiro/claude-code-agents

Structured multi-step reasoning for complex problems using the sequential-thinking MCP server. Use when facing architectural decisions, performance bottlenecks, complex debugging, design trade-offs, technology selection, or any problem requiring rigorous step-by-step analysis with hypothesis testing.

2026-05-294

investigate

pfangueiro/claude-code-agents

Deep root cause analysis engine. Systematically investigates bugs, crashes, unexpected behavior, and performance issues through an 8-phase diagnostic protocol. Uses structured reasoning (sequential-thinking MCP), multi-pass codebase analysis, git forensics, evidence-based hypothesis testing, and the 5 Whys method. Never jumps to a fix — always proves the root cause first.

2026-05-294

deep-read

pfangueiro/claude-code-agents

Comprehensive codebase reading engine. Systematically reads actual source code line by line through a 6-phase protocol — scoping, structural mapping, execution tracing, deep reading, pattern synthesis, and structured reporting. Source code is the source of truth. Use when needing to truly understand how code works, not just what documentation claims.

2026-05-294

Handoff

Preserve context across Claude Code sessions by writing a structured HANDOFF.md file at the project root.

When to Use

Before ending a long session

Before running /compact to free context

When switching to a different task and planning to return

When handing work to another developer or agent

How It Works

Check if a HANDOFF.md already exists in the project root

If it does, read it first to build on previous context

Write/update HANDOFF.md with the five sections below

HANDOFF.md Format

# Handoff — [Project Name] **Date**: YYYY-MM-DD HH:MM **Branch**: current git branch ## Goal What we're trying to accomplish overall. ## Current Progress - What's been completed this session - Files created or modified (with paths) - Decisions made and rationale ## What Worked - Approaches or patterns that succeeded - Key insights discovered ## What Didn't Work - Approaches tried and abandoned (with reasons) - Pitfalls to avoid next time ## Next Steps 1. Specific actionable items for the next session 2. Ordered by priority 3. Include file paths and context needed

Rules

Always include the current git branch and date

Be specific about file paths — the next session has zero context

List what didn't work so the next session doesn't repeat failed approaches

Keep it under 100 lines — enough to resume, not a novel

If a HANDOFF.md exists, update it rather than overwriting blindly

Example

# Handoff — checkout-service **Date**: 2026-02-12 14:30 **Branch**: feat/stripe-checkout ## Goal Implement Stripe checkout flow with webhook verification. ## Current Progress - Created `src/api/checkout.ts` with createSession endpoint - Added `src/api/webhooks/stripe.ts` for webhook handler - Database migration `migrations/005_orders.sql` applied - Unit tests passing for checkout session creation ## What Worked - Using Stripe's PaymentIntent API instead of Charges (simpler flow) - Zod schema validation on webhook payload before processing ## What Didn't Work - Tried using Stripe Checkout Sessions redirect — didn't work with SPA routing - webhook signature verification failed when using raw body parser from express (need raw buffer) ## Next Steps 1. Fix webhook body parsing — use `express.raw()` middleware for `/api/webhooks/stripe` 2. Add idempotency key to prevent duplicate order creation 3. Write integration tests for the full checkout -> webhook -> order flow 4. Add error handling for failed payments (update order status)