Agent runtime lifecycle hooks. Use for before/after tool or step hooks, tool mocks, human intervention, sub-agent calls, context compression, evals, callAgent, or lifecycle events.
Agent runtime lifecycle hooks. Use for before/after tool or step hooks, tool mocks, human intervention, sub-agent calls, context compression, evals, callAgent, or lifecycle events.
Agent skill published as a SKILL.md in lobehub/lobehub (folder .agents/skills/agent-runtime-hooks). Install it with one command using the open skills CLI, or copy the folder into ~/.claude/skills/.
Same corner
ARIS ⚔️ (Auto-Research-In-Sleep) — Lightweight Markdown-only skills for autonomous ML research: cross-model review loops, idea discovery, and experiment automation. No framework, no lock-in — works with Claude Code…
Trigger Stripe API actions (payments, invoices, customers, refunds) from agent frameworks with restricted-key safety.
Low-code agent builder + marketplace. Drag-block workflows, run on AutoGPT Server, deploy pre-built agents like Viral Video Generator.
Coming soon
The submission portal opens next sprint. For now, ship to GitHub and tag claude-skill.
Free PDF
The full Skills Bank, organized by category, with install commands and 1-line verdicts.
