handoff-protocols
The handoff-protocols skill generates structured handoff documents that capture project status, key decisions, blockers, and technical context when work transitions between team members or agents. Use it for planned transitions like shift changes or vacation coverage, unplanned emergencies, or partial work transfers where clear context and continuity are essential for the receiving person to resume work effectively.
git clone --depth 1 https://github.com/rohitg00/skillkit /tmp/handoff-protocols && cp -r /tmp/handoff-protocols/packages/core/src/methodology/packs/collaboration/handoff-protocols ~/.claude/skills/handoff-protocolsSKILL.md
# Handoff Protocols You are executing a work handoff between team members or agents. ## Handoff Types | Type | When | Key Characteristics | |------|------|---------------------| | **Planned** | End of shift, vacation, role change | Time to prepare docs; opportunity for sync meeting; gradual transition possible | | **Unplanned** | Illness, emergency, priority change | Limited prep time; rely on existing docs; may need to reconstruct context | | **Partial** | Transfer one piece while retaining other work | Requires clear boundary definition; shared ownership and integration points | ## Handoff Document ### Essential Sections ```markdown # Handoff: [Task/Project Name] ## Quick Summary [One paragraph: What is this and current state] ## Current Status - [ ] Phase: [Design/Implementation/Testing/etc] - [ ] Progress: [X% complete / Y of Z tasks done] - [ ] Blockers: [Current blockers, if any] - [ ] Next Action: [Very next thing to do] ## Context ### What We're Building [Brief description of the goal/feature] ### Why [Business/technical justification] ### Key Decisions Made | Decision | Options Considered | Choice | Rationale | |----------|-------------------|--------|-----------| | [D1] | A, B, C | B | [Why B was chosen] | ### Open Questions - [Question 1] - [Question 2] ## Technical Details ### Architecture/Design [Relevant diagrams or links] ### Key Files - `path/to/file1.ts` - [Purpose] - `path/to/file2.ts` - [Purpose] ### Dependencies - [Dependency 1]: [How it's used] - [Dependency 2]: [How it's used] ## Current State of Code ### What's Complete - [x] [Completed item 1] - [x] [Completed item 2] ### In Progress - [ ] [In progress item] - [Current state] ### Not Started - [ ] [Pending item 1] - [ ] [Pending item 2] ## Known Issues ### Active Issues - [Issue 1]: [Description and current understanding] ### Workarounds in Place - [Workaround 1]: [Why it exists, how to remove it] ## How to Continue ### Immediate Next Steps 1. [Step 1] 2. [Step 2] 3. [Step 3] ### Things to Watch Out For - [Gotcha 1] - [Gotcha 2] ### Who to Contact - [Name/Team] for [Topic] - [Name/Team] for [Topic] ## Resources - [Link to design doc] - [Link to requirements] - [Link to related PRs] ``` ## Handoff Meeting Checklist If doing a live handoff: **Before Meeting:** - [ ] Prepare handoff document - [ ] Ensure code is in clean state - [ ] List questions you anticipate **During Meeting:** 1. Walk through handoff document 2. Show current state of code 3. Demo any working functionality 4. Explain key decisions and trade-offs 5. Highlight risks and unknowns 6. Answer questions 7. Verify recipient understands **After Meeting:** - [ ] Share access to all resources - [ ] Offer availability for follow-up questions - [ ] Confirm handoff complete ## Code State Preparation Before handing off, ensure: ```bash # Clean working directory git status # Should be clean # Latest changes committed git log -1 # Recent meaningful commit # Branch is up to date git pull origin main # Tests pass npm test # All green # Build works npm run build # No errors ``` Leave the code in a state where: - It compiles/runs - Tests pass - No work-in-progress changes uncommitted - Clear commit messages explain recent changes ## Communication Templates ### Async Handoff Message ``` Hi [Name], I'm handing off [Task/Project] to you. Here's what you need to know: **Status:** [Current state in one sentence] **What I've Done:** - [Accomplishment 1] - [Accomplishment 2] **Next Steps:** 1. [Immediate next action] 2. [Following action] **Watch Out For:** - [Important gotcha] **Resources:** - Handoff doc: [link] - Code: [branch name] - Related PR: [link] Let me know if you have questions! ``` ### Requesting Additional Context ``` Hi [Name], I'm picking up [Task] from your handoff. A few clarifications: 1. [Specific question 1] 2. [Specific question 2] Also, I noticed [observation]. Was that intentional? Thanks! ``` ## Handoff Anti-Patterns Avoid: brain dumps of unstructured info, disappearing after handoff, omitting critical context, and handing off code in a broken state. ## Receiving a Handoff When you receive work: 1. **Read documentation** before asking questions 2. **Acknowledge receipt** to confirm handoff 3. **Identify gaps** in your understanding 4. **Ask focused questions** about specific unclear points 5. **Verify you can build/run** the current state 6. **Document** any additional context you discover ## Handoff Quality Checklist For the giver: - [ ] Documentation is complete and current - [ ] Code is in clean, working state - [ ] All access/permissions transferred - [ ] Key contacts introduced - [ ] Questions answered or noted - [ ] Availability for follow-up communicated For the receiver: - [ ] Documentation reviewed - [ ] Can build and run the code - [ ] Understand current state - [ ] Know next steps - [ ] Know who to contact - [ ] No blocking questions ## Integration with Other Skills - **structured-review**: Get review before handoff if work is complete - **parallel-investigation**: Handoff individual threads - **planning/task-decomposition**: Reference task breakdown in handoff
Coordinates parallel investigation threads to simultaneously explore multiple hypotheses or root causes across different system areas. Use when debugging production incidents, slow API performance, multi-system integration failures, or complex bugs where the root cause is unclear and multiple plausible theories exist; when serial troubleshooting is too slow; or when multiple investigators can divide root-cause analysis work. Provides structured phases for problem decomposition, thread assignment, sync points with Continue/Pivot/Converge decisions, and final report synthesis.
Performs a structured five-stage code review covering requirements compliance, correctness, code quality, testing, and security/performance. Each stage uses targeted checklists and categorized feedback (Blocker/Major/Minor/Nit) with actionable suggestions and rationale. Use when the user asks for code review, PR feedback, pull request review, or wants their code checked for bugs, style issues, or vulnerabilities — triggered by phrases like "review my code", "check this PR", "review my changes", "pull request review", or "code feedback".
Applies the scientific method to debugging by helping users form specific, testable hypotheses, design targeted experiments, and systematically confirm or reject theories to find root causes. Use when a user says their code isn't working, they're getting an error, something broke, they want to troubleshoot a bug, or they're trying to figure out what's causing an issue. Concrete actions include isolating failing components, forming and testing hypotheses, analyzing error messages, tracing execution paths, and interpreting test results to narrow down root causes.
Performs systematic root cause analysis to identify the true source of bugs, errors, and unexpected behavior through structured investigation phases — not just treating symptoms. Use when a user reports a bug, crash, error, or broken behavior and needs to debug, troubleshoot, or investigate why something is not working; especially for complex or intermittent issues across multiple components. Applies the Five Whys method, hypothesis-driven testing, stack trace analysis, git blame/log evidence gathering, and causal chain documentation to isolate and confirm root causes before applying any fix.
Applies systematic tracing and isolation techniques to pinpoint exactly where a bug originates in code. Use when a bug is hard to locate, code is not working as expected, an error or crash appears with unclear cause, a regression was introduced between recent commits, or you need to narrow down which component, function, or line is faulty. Covers binary search debugging, git bisect for regressions, strategic logging with [TRACE] patterns, data and control flow tracing, component isolation, minimal reproduction cases, conditional breakpoints, and watch expressions across TypeScript, SQL, and bash.
Creates and structures SKILL.md files for AI coding agents, including YAML frontmatter, trigger phrases, directive instructions, decision trees, code examples, and verification checklists. Use when the user asks to write a new skill, create a skill file, author agent capabilities, generate skill documentation, or define a skill template for Claude Code agents.
Guides the creation of technical design documents before writing code, producing architecture diagrams, data models, API interface definitions, implementation plans, and multi-option trade-off analyses. Use when the user asks to plan a feature, architect a system, design an API, explore implementation approaches, or requests a technical design or spec before coding — especially for complex features involving multiple components, ambiguous requirements, or significant architectural changes.
Breaks down complex software, writing, or research tasks into small, atomic, independently completable units with dependency graphs and milestone breakdowns. Use when the user asks to plan a project, decompose a feature, create subtasks, split up work, or needs help organizing a large piece of work into a step-by-step plan. Triggered by phrases like "break down", "decompose", "where do I start", "too big", "split into tasks", "work breakdown", or "task list".