Stats
Actions
Tags
From storyhook
Use when ending a work session or switching contexts. Generates a comprehensive handoff document showing what was accomplished, what changed, and what remains. Also runs automatically when sessions end via the stop hook.
How this skill is triggered — by the user, by Claude, or both
Slash command
/storyhook:storyhook-handoff [--since <duration>][--since <duration>]This skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
Generate a session handoff document for continuity across sessions.
Generate a session handoff document for continuity across sessions.
Before running any story command, confirm the CLI is installed by running command -v story. If it is missing, follow references/ensure-cli.md: tell the user, ask permission to install (via AskUserQuestion), and if approved use the storyhook-install skill before continuing. Do not run story commands until this check passes.
Run story handoff --since <duration> where duration defaults to 2h. If the user provided a different duration (e.g., /storyhook:storyhook-handoff --since 4h), use that value.
The handoff command analyzes:
Run story summary --json to capture the current project snapshot:
Synthesize a clear handoff that includes:
story nextThis information helps the next session (whether the same agent or a different one) pick up exactly where this session left off.
Note: This skill also runs automatically via the Stop hook when a session ends. The automatic version uses a 4-hour window. When invoked manually, the user can customize the time window.
npx claudepluginhub mikeydotio/storyhook --plugin storyhookProvides behavioral guidelines to reduce common LLM coding mistakes, focusing on simplicity, surgical changes, assumption surfacing, and verifiable success criteria.
Searches, retrieves, and installs Agent Skills from prompts.chat registry using MCP tools like search_skills and get_skill. Activates for finding skills, browsing catalogs, or extending Claude.
Creates, edits, and optimizes skills for Claude Code, including drafting, evaluating with test prompts, iterating on performance, and improving skill descriptions for better triggering accuracy.