resume-handoff

name	resume-handoff
description	Resume work from a handoff document produced by create-handoff. Reads the handoff, verifies current repo, branch, and state, and continues from where the previous session left off. Use at the start of a new session when the user references a handoff file, says "resume from handoff", "continue from where we left off", or invokes /resume-handoff.
argument-hint	["handoff-path"]
shell-timeout	10
contract	{"produces":{"kind":"side-effect","meta":{"effect":"work-continuation"}},"consumes":{"meta":{"artifactKind":"handoff"}}}

Resume Handoff

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.

Input

$ARGUMENTS — path to a handoff document under .rpiv/artifacts/handoffs/. If omitted, the skill lists available handoffs and asks which to resume from.

Metadata

echo "### recent (read only in case of empty user input)"
echo "recent handoffs:"
node "${SKILL_DIR}/../_shared/list-recent.mjs" .rpiv/artifacts/handoffs 10

Flow

1. Input → 2. Read & analyze handoff → 3. Synthesize & present → 4. Create action plan → 5. Begin implementation

Steps

Step 1: Input Handling

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 using the Read tool
   • Immediately read any research or plan documents that it links to under .rpiv/artifacts/plans or .rpiv/artifacts/research or .rpiv/artifacts/solutions. Read these critical files DIRECTLY using the Read tool - do NOT invoke skills for this initial reading phase.
   • 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 no parameters provided, branch on the recent handoffs: listing in the Metadata block:

   • Empty — no handoffs exist; tell the user and ask for a path in prose.
   • Exactly one entry — confirm with ask_user_question: "Resume this handoff?" with options "Resume <filename> (Recommended)" and "Pick a different path". Do NOT call ask_user_question with a single option (the tool requires ≥2).
   • Two or more entries — present the top 4 filenames as ask_user_question options. The tool automatically appends a Type something. free-text row; do not list it manually.

   Direct invocation alternative: /skill:resume-handoff .rpiv/artifacts/handoffs/<filename>

Step 2: 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 agents: After reading all critical handoff/plan/research documents directly, spawn the agents below in parallel using the Agent tool. Wait for ALL agents to complete before proceeding.

   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 agents to complete before proceeding

4. Verify current state:

   • Read files from "Learnings" section completely to validate patterns still apply
   • Read files from "Recent changes" to verify modifications are still present
   • Use git log or git diff if needed to check commit history since handoff
   • Re-read implementation files mentioned to confirm current state matches handoff expectations
   • Read any new related files discovered during research

Step 3: Synthesize and Present Analysis

1. Present comprehensive analysis:

   I've analyzed the handoff from {date} by {author}. 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}
   
   

   Header is capped at ≤16 characters (MAX_HEADER_LENGTH = 16 — longer values are rejected). Use the ask_user_question tool to confirm the approach. Question: "{Summary of recommended next action}. Proceed?". Header: "Resume". Options: "Proceed (Recommended)" (Begin with {recommended action 1}); "Adjust approach" (Change the order or scope of next steps); "Re-analyze" (The codebase has changed — re-verify state first).

Step 4: Create Action Plan

1. Create a 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 5: Begin Implementation

1. Start with the first approved task
2. Reference learnings from handoff throughout implementation
3. Apply patterns and approaches documented in the handoff
4. Update progress as tasks are completed

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:

   • Keep the task list updated 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 by reading them
   • Check for breaking changes since handoff using git log/diff or by reading modified files
   • Confirm patterns mentioned in "Learnings" are still valid by examining current code
   • Compare handoff timestamps with current git commits to assess how much has changed

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: /skill:resume-handoff .rpiv/artifacts/handoffs/2025-01-08_14-30-15_webhook-validation.md
Assistant: Let me read and analyze that handoff document...

{Reads handoff completely}
{Spawns research agents}
{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: {Creates todo list and begins implementation}