resume-handoff — Claude Code skill: pick up work from a handoff doc
Reads a handoff document, checks it against the actual repo state, and suggests a way forward. Useful when a session got cut off and the context needs to come back fast.
npx skills add parcadei/Continuous-Claude-v3 --skill resume-handoff -a claude-code
npx skills add parcadei/Continuous-Claude-v3 --skill resume_handoff -a claude-codeWhat resume-handoff does
This skill picks up work where the previous session stopped. It reads the handoff document in full, then pulls in linked files from thoughts/shared/plans and thoughts/shared/research directly — not through subagents, so nothing gets lost in the handover.
The next step is analysis: tasks, changes and learnings from the handoff are compared with what the codebase actually looks like now. The skill then proposes a course of action and waits for confirmation. Once confirmed, it builds a todo list with TodoWrite and routes the work to specialist agents — kraken for big features, spark for quick fixes, sleuth for debugging, oracle for external docs. Direct implementation is off the table; everything goes through the Task tool.
You can start it with a file path, a ticket number like ENG-2124, or no arguments at all — in that case it lists the available handoffs. Files live in thoughts/shared/handoffs/ENG-XXXX, and names include a YYYY-MM-DD_HH-MM-SS timestamp, so the newest one is easy to spot. Without the thoughts/shared folder structure there is nothing to search, so that layout is a prerequisite.
What it helps with
- restore context after a session break
- locate the latest handoff for a ticket number
- verify handoff claims against the current code
- turn action items into a todo list
- hand tasks to a matching specialist agent
Example prompts for the agent
- Resume work from
thoughts/shared/handoffs/ENG-2124/2025-03-14_10-30-00_ENG-2124_description.md - Continue from ticket
ENG-2124 - Show available handoffs and help me pick one to resume
How to install resume-handoff
1Skills CLI (Vercel)
npx skills add parcadei/Continuous-Claude-v3 --skill resume-handoff -a claude-codenpx skills add parcadei/Continuous-Claude-v3 --skill resume_handoff -a claude-code2Manually: put the files in place
~/.claude/skills/resume_handoff/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/resume_handoff/
1Skills CLI (Vercel)
npx skills add parcadei/Continuous-Claude-v3 --skill resume_handoff -a codex2Manually: put the files in place
.agents/skills/resume_handoff/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add parcadei/Continuous-Claude-v3 --skill resume_handoff -a cursor2Manually: put the files in place
.cursor/skills/resume_handoff/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install parcadei/Continuous-Claude-v3 resume_handoff2Manually: put the files in place
.github/skills/resume_handoff/SKILL.md1Skills CLI (Vercel)
npx skills add parcadei/Continuous-Claude-v3 --skill resume_handoff -a gemini-cli2Platform CLI
gemini skills install https://github.com/parcadei/Continuous-Claude-v3 --path .claude/skills/resume_handoffManually: put the files in place
.devin/skills/resume_handoff/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add parcadei/Continuous-Claude-v3 --skill resume_handoff -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about resume-handoff
How do I install resume-handoff in Claude Code?
Run npx skills add parcadei/Continuous-Claude-v3 --skill resume-handoff -a claude-code or npx skills add parcadei/Continuous-Claude-v3 --skill resume_handoff -a claude-code. The skill lands in ~/.claude/skills/resume_handoff/SKILL.md.
What does resume-handoff do?
It reads a handoff document plus the files it references, compares the write-up with the current repo state, and proposes next steps. After your confirmation it creates a todo list and routes tasks to specialist agents.
What does the skill expect from the repo?
Handoffs must sit in thoughts/shared/handoffs/, with plans and research in thoughts/shared/plans or thoughts/shared/research. The skill relies on filenames with timestamps to pick the most recent handoff.
Source text
SKILL.md · MIT
---
name: resume-handoff
description: Resume work from handoff document with context analysis and validation
---
# Resume work from a handoff document
You are tasked with resuming work from a handoff document through an interactive process. These handoffs contain critical context, learnings, and next steps from previous work sessions that need to be understood and continued.
## Initial Response
When this command is invoked:
1. **If the path to a handoff document was provided**:
- If a handoff document path was provided as a parameter, skip the default message
- Immediately read the handoff document FULLY
- Immediately read any research or plan documents that it links to under `thoughts/shared/plans` or `thoughts/shared/research`. do NOT use a sub-agent to read these critical files.
- Begin the analysis process by ingesting relevant context from the handoff document, reading additional files it mentions
- Then propose a course of action to the user and confirm, or ask for clarification on direction.
2. **If a ticket number (like ENG-XXXX) was provided**:
- locate the most recent handoff document for the ticket. Tickets will be located in `thoughts/shared/handoffs/ENG-XXXX` where `ENG-XXXX` is the ticket number. e.g. for `ENG-2124` the handoffs would be in `thoughts/shared/handoffs/ENG-2124/`. **List this directory's contents.**
- There may be zero, one or multiple files in the directory.
- **If there are zero files in the directory, or the directory does not exist**: tell the user: "I'm sorry, I can't seem to find that handoff document. Can you please provide me with a path to it?"
- **If there is only one file in the directory**: proceed with that handoff
- **If there are multiple files in the directory**: using the date and time specified in the file name (it will be in the format `YYYY-MM-DD_HH-MM-SS` in 24-hour time format), proceed with the _most recent_ handoff document.
- Immediately read the handoff document FULLY
- Immediately read any research or plan documents that it links to under `thoughts/shared/plans` or `thoughts/shared/research`; do NOT use a sub-agent to read these critical files.
- Begin the analysis process by ingesting relevant context from the handoff document, reading additional files it mentions
- Then propose a course of action to the user and confirm, or ask for clarification on direction.
3. **If no parameters provided**, respond with:
```
I'll help you resume work from a handoff document. Let me find the available handoffs.
Which handoff would you like to resume from?
Tip: You can invoke this command directly with a handoff path: `/resume_handoff `thoughts/shared/handoffs/ENG-XXXX/YYYY-MM-DD_HH-MM-SS_ENG-XXXX_description.md`
or using a ticket number to resume from the most recent handoff for that ticket: `/resume_handoff ENG-XXXX`
```
Then wait for the user's input.
## Process Steps
### Step 1: Read and Analyze Handoff
1. **Read handoff document completely**:
- Use the Read tool WITHOUT limit/offset parameters
- Extract all sections:
- Task(s) and their statuses
- Recent changes
- Learnings
- Artifacts
- Action items and next steps
- Other notes
2. **Spawn focused research tasks**:
Based on the handoff content, spawn parallel research tasks to verify current state:
```
Task 1 - Gather artifact context:
Read all artifacts mentioned in the handoff.
1. Read feature documents listed in "Artifacts"
2. Read implementation plans referenced
3. Read any research documents mentioned
4. Extract key requirements and decisions
Use tools: Read
Return: Summary of artifact contents and key decisions
```
3. **Wait for ALL sub-tasks to complete** before proceeding
4. **Read critical files identified**:
- Read files from "Learnings" section completely
- Read files from "Recent changes" to understand modifications
- Read any new related files discovered during research
### Step 2: Synthesize and Present Analysis
1. **Present comprehensive analysis**:
```
I've analyzed the handoff from [date] by [researcher]. Here's the current situation:
**Original Tasks:**
- [Task 1]: [Status from handoff] → [Current verification]
- [Task 2]: [Status from handoff] → [Current verification]
**Key Learnings Validated:**
- [Learning with file:line reference] - [Still valid/Changed]
- [Pattern discovered] - [Still applicable/Modified]
**Recent Changes Status:**
- [Change 1] - [Verified present/Missing/Modified]
- [Change 2] - [Verified present/Missing/Modified]
**Artifacts Reviewed:**
- [Document 1]: [Key takeaway]
- [Document 2]: [Key takeaway]
**Recommended Next Actions:**
Based on the handoff's action items and current state:
1. [Most logical next step based on handoff]
2. [Second priority action]
3. [Additional tasks discovered]
**Potential Issues Identified:**
- [Any conflicts or regressions found]
- [Missing dependencies or broken code]
Shall I proceed with [recommended action 1], or would you like to adjust the approach?
```
2. **Get confirmation** before proceeding
### Step 3: Create Action Plan
1. **Use TodoWrite to create task list**:
- Convert action items from handoff into todos
- Add any new tasks discovered during analysis
- Prioritize based on dependencies and handoff guidance
2. **Present the plan**:
```
I've created a task list based on the handoff and current analysis:
[Show todo list]
Ready to begin with the first task: [task description]?
```
### Step 4: Route to Specialist Agent
**CRITICAL: Do NOT implement directly. Always spawn via Task tool.**
1. **Analyze task type and select specialist agent**:
**Leads (can spawn workers):**
| Agent | Domain | Use For |
|-------|--------|---------|
| `kraken` | implement | Large features, new systems, major components |
| `architect` | plan | Feature design, system architecture, implementation planning |
| `phoenix` | plan | Refactoring plans, migrations, codebase restructuring |
| `herald` | deploy | Releases, deployments, publishing |
| `maestro` | orchestrate | Complex multi-agent workflows |
**Workers (focused specialists):**
| Agent | Domain | Use For |
|-------|--------|---------|
| `spark` | implement | Quick fixes, patches, minor tweaks |
| `scribe` | document | Documentation, guides, explanations |
| `sleuth` | debug | Bug investigation, tracing, root cause analysis |
| `aegis` | debug | Security audits, vulnerability scanning |
| `profiler` | debug | Performance optimization, bottleneck analysis |
| `arbiter` | validate | Unit tests |
| `atlas` | validate | E2E/integration tests |
| `oracle` | research | External docs, best practices, how-to |
| `scout` | research | Codebase exploration, finding existing code |
| `pathfinder` | research | Repository structure analysis |
| `plan-reviewer` | review | Feature plan review, design validation |
| `plan-reviewer` | review | Migration review, refactoring validation |
| `chronicler` | session | Session analysis, history summaries |
2. **Spawn the specialist via Task tool**:
```
Use Task tool with:
- subagent_type: [selected agent from above]
- prompt: [task description + relevant handoff context + learnings]
```
3. **Include handoff context in the prompt**:
- Key learnings from the handoff
- File references with line numbers
- Patterns to follow
- Pitfalls to avoid
4. **Wait for agent completion**, then proceed to next task
## Guidelines
1. **Be Thorough in Analysis**:
- Read the entire handoff document first
- Verify ALL mentioned changes still exist
- Check for any regressions or conflicts
- Read all referenced artifacts
2. **Be Interactive**:
- Present findings before starting work
- Get buy-in on the approach
- Allow for course corrections
- Adapt based on current state vs handoff state
3. **Leverage Handoff Wisdom**:
- Pay special attention to "Learnings" section
- Apply documented patterns and approaches
- Avoid repeating mistakes mentioned
- Build on discovered solutions
4. **Track Continuity**:
- Use TodoWrite to maintain task continuity
- Reference the handoff document in commits
- Document any deviations from original plan
- Consider creating a new handoff when done
5. **Validate Before Acting**:
- Never assume handoff state matches current state
- Verify all file references still exist
- Check for breaking changes since handoff
- Confirm patterns are still valid
## Common Scenarios
### Scenario 1: Clean Continuation
- All changes from handoff are present
- No conflicts or regressions
- Clear next steps in action items
- Proceed with recommended actions
### Scenario 2: Diverged Codebase
- Some changes missing or modified
- New related code added since handoff
- Need to reconcile differences
- Adapt plan based on current state
### Scenario 3: Incomplete Handoff Work
- Tasks marked as "in_progress" in handoff
- Need to complete unfinished work first
- May need to re-understand partial implementations
- Focus on completing before new work
### Scenario 4: Stale Handoff
- Significant time has passed
- Major refactoring has occurred
- Original approach may no longer apply
- Need to re-evaluate strategy
## Example Interaction Flow
```
User: /resume_handoff specification/feature/handoffs/handoff-0.md
Assistant: Let me read and analyze that handoff document...
[Reads handoff completely]
[Spawns research tasks]
[Waits for completion]
[Reads identified files]
I've analyzed the handoff from [date]. Here's the current situation...
[Presents analysis]
Shall I proceed with implementing the webhook validation fix, or would you like to adjust the approach?
User: Yes, proceed with the webhook validation
Assistant: This is a bugfix task, so I'll route to the `spark` agent.
[Uses Task tool with subagent_type="spark" and prompt containing:
- The webhook validation fix task
- Key learnings from handoff
- Relevant file:line references
- Patterns to follow]
[Waits for spark agent to complete]
The spark agent has completed the webhook validation fix. Moving to the next task...
```
© parcadei · MIT · parcadei/Continuous-Claude-v3