plugins/cc-meta/skills/handing-off-session/SKILL.md
Generate structured session handoff notes for cross-session continuity. Use at end of session or when switching context.
npx skillsauth add qte77/claude-code-utils-plugin handing-off-sessionInstall 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.
Target: $ARGUMENTS
Captures session state as a structured markdown note for the next session to pick up. Stateless — markdown files only, no database, no daemon.
| Position | Name | Required | Default | Description |
|----------|------|----------|---------|-------------|
| 1 | output-path | no | auto | Where to write the handoff note. |
Default output path: .claude/handoffs/YYYY-MM-DD-<short-description>.md
The <short-description> is a 2-4 word slug derived from the session's primary
focus (e.g. 2026-04-06-session-handoff-skill.md).
Scan conversation — Identify completed actions, decisions, and pending work from the current session context.
Check git state — Run git diff --stat and git log --oneline -10 to
capture recent changes and commits.
Extract signals — Collect decisions made, alternatives rejected, blockers encountered, and open questions.
Ensure output dir — Create .claude/handoffs/ if it doesn't exist.
Write handoff note — Use the template below. Be concise — enough to resume, no more.
# Session Handoff — <date>
## What Was Done
[Completed work, key commits, PRs created/merged]
## What's Pending
[Open tasks, unfinished work, next steps]
## Key Decisions
[Architectural choices, trade-offs made, rejected alternatives]
## Modified Files
[List of files changed with brief reason]
## Blockers
[External dependencies, open questions, things that need user input]
Next session can read the latest handoff:
# Find latest handoff
ls -t .claude/handoffs/*.md | head -1
Or read all recent handoffs to rebuild context across multiple sessions.
development
Verify an external or AI-generated security report against the actual codebase before acting on it. Use when handed a scanner PDF, automated teardown, audit report, or bug-bounty submission — classifies every finding CONFIRMED / OVERSTATED / FALSE-POSITIVE / FABRICATED and salvages the real work items.
development
Audits a site's SEO and AI-search (GEO) readiness — meta tags, Open Graph/Twitter, JSON-LD, robots/llms conventions — and generates fixes. Use when reviewing search visibility, social previews, structured data, or LLM/AI-crawler discoverability.
development
Analyzes industry websites for design patterns, layout, typography, and content strategies using first-principles thinking. Use when researching website design, UI patterns, or competitive design analysis.
development
Audits website usability for UX optimization, covering forms, navigation, validation, and microcopy. Use when reviewing user experience, task completion flows, or interface friction points.