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.
Works with
AI-first code editor with Composer
Before installing skills in Cursor, ensure your development environment meets these requirements:
node --versionresume-handoffExecute the skills CLI command in your project's root directory to begin installation:
Fetches resume-handoff from parcadei/continuous-claude-v3 and configures it for Cursor.
The CLI shows a list of agents. Use arrow keys and space to select Cursor:
Confirm successful installation by checking the skill directory location:
Restart Cursor to activate resume-handoff. Access via /resume-handoff in your agent's command palette.
We perform automated surface-level scans (Gen AI Scanner, Socket, Snyk) during installation. These checks detect common vulnerabilities but do not guarantee complete security. Always review skill source code and verify the publisher's reputation before production use.
Skills execute code in your environment. Always review source, verify the publisher, and test in isolation before production.
Submit your Claude Code skill and start earning
Create detailed user stories, acceptance criteria, and feature specs
Example
Generate user stories for 'password reset feature' with acceptance criteria, edge cases, and test scenarios
Reduce spec writing time by 50%, ensure comprehensive coverage
Research competitors, compare features, identify gaps
Example
Analyze 5 competitor products, create feature comparison matrix, suggest differentiation opportunities
Complete competitive research in 2 hours instead of 2 days
Evaluate features using frameworks (RICE, ICE, Kano) and create prioritized backlogs
Example
Score 20 feature ideas using RICE framework, generate prioritized roadmap with rationale
0
total installs
0
this week
3.7K
GitHub stars
0
upvotes
Run in your terminal
0
installs
0
this week
3.7K
stars
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:
If the path to a handoff document was provided:
thoughts/shared/plans or thoughts/shared/research. do NOT use a sub-agent to read these critical files.If a ticket number (like ENG-XXXX) was provided:
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.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.
Read handoff document completely:
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
Wait for ALL sub-tasks to complete before proceeding
Read critical files identified:
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?
Get confirmation before proceeding
Use TodoWrite to create task list:
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]?
CRITICAL: Do NOT implement directly. Always spawn via Task tool.
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 |
Spawn the specialist via Task tool:
Use Task tool with:
- subagent_type: [selected agent from above]
- prompt: [task description + relevant handoff context + learnings]
Include handoff context in the prompt:
Wait for agent completion, then proceed to next task
Be Thorough in Analysis:
Be Interactive:
Leverage Handoff Wisdom:
Track Continuity:
Validate Before Acting:
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...
Make data-driven prioritization decisions faster
Draft PRDs, status updates, and stakeholder presentations
Example
Create executive summary of Q3 roadmap, monthly progress report, feature launch announcement
Save 3-5 hours/week on communication overhead
Prerequisites
Time Estimate
30-60 minutes to see productivity improvements
Steps
Common Pitfalls
✓ Do
✗ Don't
💡 Pro Tips
✓ Use when
Use for user story writing, competitive research, roadmap prioritization, stakeholder communication, and PRD drafting. Best for reducing repetitive documentation and research work.
✗ Avoid when
Avoid for strategic product vision (requires deep customer empathy), pricing decisions (needs market and financial expertise), or when face-to-face customer discovery is more valuable than speed.
parcadei/continuous-claude-v3
mattpocock/skills
cursor/plugins
ailabs-393/ai-labs-claude-skills
pproenca/dot-skills
mattpocock/skills
resume-handoff has been reliable in day-to-day use. Documentation quality is above average for community skills.
Keeps context tight: resume-handoff is the kind of skill you can hand to a new teammate without a long onboarding doc.
resume-handoff fits our agent workflows well — practical, well scoped, and easy to wire into existing repos.
Keeps context tight: resume-handoff is the kind of skill you can hand to a new teammate without a long onboarding doc.
resume-handoff has been reliable in day-to-day use. Documentation quality is above average for community skills.
Registry listing for resume-handoff matched our evaluation — installs cleanly and behaves as described in the markdown.
resume-handoff is among the better-maintained entries we tried; worth keeping pinned for repeat workflows.
Solid pick for teams standardizing on skills: resume-handoff is focused, and the summary matches what you get after install.
resume-handoff reduced setup friction for our internal harness; good balance of opinion and flexibility.
resume-handoff is among the better-maintained entries we tried; worth keeping pinned for repeat workflows.
showing 1-10 of 44