agents/skills/handoff/SKILL.md
Generate a continuation prompt so the next session can pick up where this one left off
npx skillsauth add carterdea/dots 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.
Generate a continuation prompt so the next session can pick up where this one left off.
/handoff
Scan conversation for which commands were used (/design-doc, /execute-plan, /qa, /de-slop, /pre-pr). Read the plan file (if one exists) and classify its state:
| Plan state | Suggested next step |
|---|---|
| All implementation tasks unchecked | /execute-plan <plan-path> |
| Some tasks checked, some unchecked | /execute-plan <plan-path> (resume) |
| All tasks checked, unchecked - [ ] QA: items | /qa <plan-path> [--url <dev-server-url>] |
| All QA items checked | /de-slop -> code-simplifier -> /pre-pr |
| No plan file | /design-doc if the goal is clear |
If mid-execution: count checked vs total tasks, note the first unchecked (e.g., "Paused at Phase 2, Task 3 -- 5/12 complete"). /execute-plan handles resuming.
git branch --show-current git status --short git log --oneline -20 git diff --stat origin/$(git rev-parse --abbrev-ref HEAD 2>/dev/null || echo main)...HEAD 2>/dev/null
Output a single fenced markdown block the user can paste into a new session. Use the template in Output Format below.
Tell the user to copy the prompt and paste it into a new session.
I'm continuing work on: [task description]
Branch: [branch-name]
Repo: [repo path]
[path to planning doc, or "None created"]
[git status summary, any failing tests]
[Pipeline-aware instruction, e.g.:] [- "Design doc complete. All implementation tasks unchecked -- start execution."] [- "Execution paused at Phase 2, Task 3 (5/12 complete). Resume execution."] [- "All implementation tasks checked. QA items remain -- run QA."] [- "QA complete. Run de-slop, then code-simplifier, then pre-pr."]
Run: [copy-pastable command with args]
tools
Build or refine single-file information-first HTML artifacts, especially index.html or text.html pages, with strong information hierarchy, restrained styling, accessible semantics, and minimal AI-generated frontend tells. Use when creating HTML reports, research pages, explainers, briefs, dashboards, note indexes, annotated code reviews, planning/spec docs, or focused single-purpose editing/triage tools with copy-out export — front ends whose goal is comprehension or action rather than marketing conversion. Reach for this whenever the user wants a standalone HTML page, report, one-pager, explainer, or "quick HTML" to present or organize information, even if they just say "make an HTML file" without mentioning design. Not for multi-page sites, React/framework apps, or marketing landing pages.
development
Ship a Trello ticket end to end on any web app (Vercel, Fly.io, or other host — no Shopify): pull the latest main, read the card including Figma links, implement the change in a worktree, run the project's own tests/lint/typecheck, run de-slop and code-simplifier and fold the worthwhile cleanups in, QA desktop and mobile on a local Portless preview URL, capture screenshots, open or update the GitHub PR, link the PR and Trello to each other, attach screenshots to both, comment on the card, and move it to review. Use this whenever the user points you at a Trello card or ticket for a code task and wants it delivered as a reviewable PR — phrases like 'do this Trello ticket', 'ship this card', 'pick up this ticket and open a PR', 'update the PR for this card', or names a card/list/board with a feature or bug to implement. This is the default Trello-to-PR workflow for non-Shopify projects; for Shopify theme work use shopify-trello-delivery instead.
tools
Install or upgrade a quality baseline for Shopify theme repos. Use this whenever the user asks to add Shopify theme linting, Biome, Theme Check, Playwright accessibility checks, Vitest, Vite build tooling, lefthook hooks, GitHub Actions CI, Shopify Lighthouse CI, Claude Code PR review workflows, or a context-efficient run_silent.sh setup across Shopify sites.
development
Run an extremely strict maintainability review for abstraction quality, giant files, and spaghetti-condition growth. Use for a thermo-nuclear code quality review, thermonuclear review, deep code quality audit, or especially harsh maintainability review.