Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Resume work from handoff document with context analysis and validation
.claude/skills/resume-handoff/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-12 | ✗→✓ | ▲ Improved | — | — |
| case-10 | ✗→✓ | ▲ Improved | — | — |
| case-08 | ✗→✓ | ▲ Improved | — | — |
| case-22 | ✗→✓ | ▲ Improved | — | — |
| case-03 | ✗→✓ | ▲ Improved | — | — |
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.
When this command is invoked:
thoughts/shared/plans or thoughts/shared/research. do NOT use a sub-agent to read these critical files.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.YYYY-MM-DD_HH-MM-SS in 24-hour time format), proceed with the _most recent_ handoff document.thoughts/shared/plans or thoughts/shared/research; do NOT use a sub-agent to read these critical files.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.
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.
Use tools: Read Return: Summary of artifact contents and key decisions
I've analyzed the handoff from date] by researcher]. Here's the current situation:
Original Tasks:
Key Learnings Validated:
Recent Changes Status:
Artifacts Reviewed:
Recommended Next Actions: Based on the handoff's action items and current state:
Potential Issues Identified:
Shall I proceed with recommended action 1], or would you like to adjust the approach?
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]?
CRITICAL: Do NOT implement directly. Always spawn via Task tool.
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 |
Use Task tool with:
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...| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-06 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-12 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-15 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-09 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-10 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-13 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-08 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-04 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-07 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-14 | pass→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-22 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-03 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-02 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-05 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-19 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-01 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-17 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-16 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-11 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-18 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-20 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-21 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted, and 17 counted toward the lift figure. The other 5 produced results that are not comparable between the two arms, so they are excluded from the headline rather than averaged into it. The headline lift of +41 percentage points is the difference between those two pass rates over the 17 comparable cases. 1 case got worse with the skill loaded, and it is included in that figure.
The per-case answers from this run were removed by the retention sweep, so the case table below shows the verdicts without the text either arm produced. The counts above were recorded at the time and are unaffected. Answers are now kept for 180 days.
Other measured skills in the registry, with their headline benchmark lift.