npx agentspec-cli install 076648fd-a0ef-4240-9573-72284f72cc3e --framework ClaudeCode→ .claude/skills/claude-handoff/SKILL.md
Write a handoff summary of the current conversation so a fresh agent can continue the work. Save it to the temporary directory of the user's OS, then launch a background agent seeded with it as its prompt: `claude --bg --name "<descriptive name>" -- "$(cat <summary file>)"`. Passing the file keeps the shell from running backticks or expanding `$` in the summary. It starts in the current working directory and returns immediately; the user manages it with `claude agents`. Always pass `-n`/`--name` with a descriptive name (e.g. `--name "Fix login bug"`); it sets the display name shown in the job list, session picker, and terminal title. Include a "suggested skills" section in the summary, naming which skills the next agent should call the Skill tool for. Do not duplicate content already captured in other artifacts (specs, plans, ADRs, issues, commits, diffs). Reference them by path or URL instead. Redact any sensitive information, such as API keys, passwords, or personally identifiable information, since the summary becomes the agent's prompt. If the user passed arguments, treat them as a description of what the next session will focus on and tailor the summary accordingly.
Built on the Agent Skills standard
handoff
Compact the current conversation into a handoff document for another agent to pick up.
by AgentHub Crawler
Claude Developer Agent
You are a thin orchestrator that delegates ALL work to **Claude Code CLI** (`claude`).
by AgentHub Crawler
Agents & Skills Reference
Skill Master uses the **Claude Agent SDK** to orchestrate an agentic pipeline that generates Claude Agent Skills from unstructured inputs. This document explains the agent architecture, skill generation flow, and how to work with the skills in this project.
by AgentHub Crawler
Sign in to leave a comment.
Next Move Theory — rules for your AI agent
Drop this file into your project as `CLAUDE.md` (Claude Code) or `AGENTS.md` (Codex and most other agents), or paste its contents into the one you already have. It teaches your agent to do product work with **Advanced Jobs To Be Done (AJTBD)** and **Next Move Theory** — Ivan Zamesin's methodology — instead of the generic, often-wrong version of Jobs To Be Done that lives in training data.
by AgentHub Crawler