parcadei

resume-handoff

3,433
266
# Install this skill:
npx skills add parcadei/Continuous-Claude-v3 --skill "resume-handoff"

Install specific skill from multi-skill repository

# Description

Resume work from handoff document with context analysis and validation

# SKILL.md


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:
  2. If a handoff document path was provided as a parameter, skip the default message
  3. Immediately read the handoff document FULLY
  4. 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.
  5. Begin the analysis process by ingesting relevant context from the handoff document, reading additional files it mentions
  6. Then propose a course of action to the user and confirm, or ask for clarification on direction.

  7. If a ticket number (like ENG-XXXX) was provided:

  8. 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.
  9. There may be zero, one or multiple files in the directory.
  10. 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?"
  11. If there is only one file in the directory: proceed with that handoff
  12. 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.
  13. Immediately read the handoff document FULLY
  14. 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.
  15. Begin the analysis process by ingesting relevant context from the handoff document, reading additional files it mentions
  16. Then propose a course of action to the user and confirm, or ask for clarification on direction.

  17. 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:
  2. Use the Read tool WITHOUT limit/offset parameters
  3. Extract all sections:

    • Task(s) and their statuses
    • Recent changes
    • Learnings
    • Artifacts
    • Action items and next steps
    • Other notes
  4. 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

  1. Wait for ALL sub-tasks to complete before proceeding

  2. Read critical files identified:

  3. Read files from "Learnings" section completely
  4. Read files from "Recent changes" to understand modifications
  5. 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] โ†’ [Current verification]
- [Task 2]: [Status from handoff] โ†’ [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?
```

  1. Get confirmation before proceeding

Step 3: Create Action Plan

  1. Use TodoWrite to create task list:
  2. Convert action items from handoff into todos
  3. Add any new tasks discovered during analysis
  4. Prioritize based on dependencies and handoff guidance

  5. 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 |

  1. Spawn the specialist via Task tool:
    ```
    Use Task tool with:
  2. subagent_type: [selected agent from above]
  3. prompt: [task description + relevant handoff context + learnings]
    ```

  4. Include handoff context in the prompt:

  5. Key learnings from the handoff
  6. File references with line numbers
  7. Patterns to follow
  8. Pitfalls to avoid

  9. Wait for agent completion, then proceed to next task

Guidelines

  1. Be Thorough in Analysis:
  2. Read the entire handoff document first
  3. Verify ALL mentioned changes still exist
  4. Check for any regressions or conflicts
  5. Read all referenced artifacts

  6. Be Interactive:

  7. Present findings before starting work
  8. Get buy-in on the approach
  9. Allow for course corrections
  10. Adapt based on current state vs handoff state

  11. Leverage Handoff Wisdom:

  12. Pay special attention to "Learnings" section
  13. Apply documented patterns and approaches
  14. Avoid repeating mistakes mentioned
  15. Build on discovered solutions

  16. Track Continuity:

  17. Use TodoWrite to maintain task continuity
  18. Reference the handoff document in commits
  19. Document any deviations from original plan
  20. Consider creating a new handoff when done

  21. Validate Before Acting:

  22. Never assume handoff state matches current state
  23. Verify all file references still exist
  24. Check for breaking changes since handoff
  25. 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...

# Supported AI Coding Agents

This skill is compatible with the SKILL.md standard and works with all major AI coding agents:

Learn more about the SKILL.md standard and how to use these skills with your preferred AI coding agent.