skills/handoff/SKILL.md
Compact the current session into a handoff document for another agent or future session to pick up. Captures mission, repo state, role, scope, locked decisions, dispatch sequence, and a pickup checklist. Studio-aware. Use when pausing work, ending a session, switching contexts, or preparing for a fresh agent to continue.
npx skillsauth add koolamusic/claudefiles handoffInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Write a handoff document that lets a fresh agent continue this work cold. The reader has zero context from this conversation — the handoff is their entire briefing.
Gather state. Run these in parallel:
git log --oneline -20 (recent commits)git status (working tree)git branch --show-current (active branch).jira/CURRENT (active sprint).project/PROJECT.md (project context).workspacerc (studio workspace)Determine the output path.
.workspacerc exists: read the workspace path, write to <workspace>/handoff.md.jira/ exists: write to .jira/sprints/<active-slug>/HANDOFF.md$TMPDIR or /tmp)Write the handoff using the structure below. If the user passed arguments, treat them as a description of what the next session will focus on and tailor accordingly.
Don't duplicate. Reference existing artifacts (CONTEXT.md, PLAN.md, RESEARCH.md, PRDs, issues) by path or URL. The handoff points to them — it doesn't restate them.
Redact secrets. Strip API keys, passwords, tokens, PII. If a secret is relevant context, note its purpose without the value.
# Handoff — <date> — <one-line mission>
## Repo state
- **Branch:** <branch>
- **Clean:** yes/no (if dirty: what's uncommitted and why)
- **Active sprint:** <slug> or none
- **Last meaningful commit:** <hash> <subject>
## Your role
<ORCHESTRATOR or IMPLEMENTER — and what that means for this session>
## Mission
<2-3 sentences: what you're trying to accomplish and why it matters>
## Scope
<Numbered list of scope items. Each item: what it is, rough effort, status (done/in-progress/not-started)>
## Locked decisions
<Decisions already made that the next session must not revisit. Reference D-XX from CONTEXT.md if available.>
## Open gates
<Decisions still pending that the next session needs to resolve before proceeding.>
## Dispatch sequence
<If orchestrating: recommended wave/agent breakdown. Which items can parallelize, which are sequential.>
## Operational practices
<Branch naming, commit conventions, PR process, testing expectations — anything non-obvious about how this repo works.>
## Pickup checklist
1. Read this handoff
2. <specific first action>
3. <specific second action>
...
## Not your problem
<Explicit scope boundaries: what's out of scope and should not be touched.>
## Suggested skills
<Skills the next session should invoke, e.g. /grill, /jira:plan, /spawn>
Scale sections to their relevance. A simple handoff (one task, no orchestration) might skip Dispatch sequence and Locked decisions entirely. A complex handoff (multi-wave sprint, multiple agents) needs all sections. Don't pad short handoffs with ceremony.
chore: write session handoffdevelopment
Test-driven development with red-green-refactor loop. Use when user wants to build features or fix bugs using TDD, mentions "red-green-refactor", wants integration tests, or asks for test-first development.
data-ai
Turn the current session into a coordination thread that routes per-branch implementation work to durable, reusable child agents. Use when the user says 'orchestrator on', wants this session to act as chief-of-staff across branches, or asks to route work without implementing locally.
development
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes - four-phase framework with built-in backward tracing for deep-stack failures, ensuring root-cause understanding before implementation
development
Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like "the xlsx in my downloads") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved.