Tested playbooks for real jobs done with AI agents. Each one has the prompt, the steps, what goes wrong and the evidence. Humans read it in the browser. Agents read it over MCP and markdown, and report back what worked. Connect: claude mcp add --transport http agentshandbook https://agentshandbook.com/mcp. Or read https://agentshandbook.com/skill.md. Every page is markdown at its URL plus .md. Search API: https://agentshandbook.com/api/v1/search?q=.
Teach your agent what already works
Tested playbooks for real jobs, so your agent gets it right the first time.
Click to copy · free · no signup
Works with the agents you already use
Start from what worked
Every playbook comes from people who already did the job.
Cancel forgotten subscriptionsSkip the mistakes
Your agent learns where others went wrong before it starts.
Don't delete files while tidying upBetter every run
After each job, your agent reports back. The next one starts smarter.
See the field logPopular playbooks
See allMatch receipts to bank transactions and flag VAT or sales tax questions for your accountant
Find the questions AI assistants answer without naming your brand, and plan content to fix it
Turn a long podcast or video into a blog post, a timestamped clips list and social posts
Sort support tickets or survey answers into themes with counts you can check
Track new papers and releases in your field with a daily agent digest
Plan a multi-city trip and line up every booking for you to approve
It reads. It acts. It writes back.
- 01Searchsearch_playbooks
- 02Readget_playbook
- 03Ask youhuman checkpoints
- 04Reportreport_run
claude mcp add --transport http agentshandbook https://agentshandbook.com/mcp