skills/agent-handoff/SKILL.md
Write or update a handoff document so the next agent with fresh context can continue this work.
npx skillsauth add dopiotrek/dotclaude 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 or update a handoff document so the next agent with fresh context can continue this work. The handoff should be concise but complete enough that a fresh agent can pick up immediately without asking clarifying questions.
.docs/handoff.md already existsgit diff, git log --oneline -10, and any open files to capture the full picture.docs/handoff.md using the template below — skip any sections that don't apply# Handoff
## Goal
What we're trying to accomplish (the why, not just the what).
## Current State
Where we left off. Be specific: which file, which function, what's working vs broken.
## Key Decisions Made
Important choices, tradeoffs, or conclusions reached during this session. Include the reasoning so the next agent doesn't relitigate them.
## What Worked
Approaches that succeeded — keep doing these.
## What Didn't Work
Approaches that failed or were abandoned. Include why, so they're not retried.
## Recent Changes
Files modified, commands run, dependencies added. Keep it factual.
- `path/to/file.ts` — what changed
- `path/to/other.ts` — what changed
## Important Context
Technical constraints, environment details, gotchas, or user preferences that aren't obvious from the code alone.
## Next Steps
Ordered action items for the next session. First item should be immediately actionable.
1. ...
2. ...
+page.server.ts line 42" beats "Made progress on auth."Save as .docs/handoff.md. Tell the user:
claude "Read .docs/handoff.md and continue where we left off"development
Pre-landing PR review. Analyzes diff against the base branch for SQL safety, LLM trust boundary violations, conditional side effects, and other structural issues. Use when asked to "review this PR", "code review", "pre-landing review", or "check my diff". Proactively suggest when the user is about to merge or land code changes. (gstack)
development
Weekly engineering retrospective. Analyzes commit history, work patterns, and code quality metrics with persistent history and trend tracking. Team-aware: breaks down per-person contributions with praise and growth areas. Use when asked to "weekly retro", "what did we ship", or "engineering retrospective". Proactively suggest at the end of a work week or sprint. (gstack)
development
Systematically QA test a web application and fix bugs found. Runs QA testing, then iteratively fixes bugs in source code, committing each fix atomically and re-verifying. Use when asked to "qa", "QA", "test this site", "find bugs", "test and fix", or "fix what's broken". Proactively suggest when the user says a feature is ready for testing or asks "does this work?". Three tiers: Quick (critical/high only), Standard (+ medium), Exhaustive (+ cosmetic). Produces before/after health scores, fix evidence, and a ship-readiness summary. For report-only mode, use /qa-only. (gstack)
development
Report-only QA testing. Systematically tests a web application and produces a structured report with health score, screenshots, and repro steps — but never fixes anything. Use when asked to "just report bugs", "qa report only", or "test but don't fix". For the full test-fix-verify loop, use /qa instead. Proactively suggest when the user wants a bug report without any code changes. (gstack)