tool-use-structured-output
Use Bedrock tool_use to guarantee structured JSON outputs from Claude models. Eliminates JSON parsing failures by forcing responses through typed tool schemas.
377 repo starsObserved in 1 repos
Agent Building
Agent Building skills
Browse reusable Agent Skills, each with a clear purpose and practical guidance.
registry-broker
Search and chat with AI agents across the Universal Agentic Registry via the Hashgraph Online Registry Broker API. Use when discovering agents, starting conversations, finding incoming messages, or registering new agents.
376 repo starsObserved in 2 repos
Agent Building
agent-email-inbox
Use when building any system where email content triggers actions — AI agent inboxes, automated support handlers, email-to-task pipelines, or any workflow processing untrusted inbound email. Always use this skill when the user wants to receive emails and act on them programmatically, even if they don't mention "agent" — the skill contains critical security patterns (sender allowlists, content filtering, sandboxed processing) that prevent untrusted email from controlling your system.
375 repo starsObserved in 21 repos
Agent Building
deep-agents
Build batteries-included agents with planning, context management, subagent delegation, and sandboxed execution. Use for complex, multi-step tasks that need built-in capabilities.
375 repo starsObserved in 1 repos
Agent Building
inngest-agents
Use when building durable AI agents or agentic workflows with Inngest and AgentKit, including model calls, tool calls, multi-agent networks, human approval, realtime progress, provider rate limits, and crash-safe execution. Covers AgentKit, `step.ai`, `step.run`, `step.waitForEvent`, native realtime, and when to use lower-level Inngest primitives instead of an in-memory agent loop.
375 repo starsObserved in 1 repos
Agent Building
built-in-ai
Teaches the AI about modern Chrome Built-in AI APIs (Prompt, Translation, Writing Assistance) and their polyfills.
374 repo starsObserved in 1 repos
Agent Building
craftbot-skill-creator
Create a brand-new reusable skill from a single completed task. Read the per-task SKILL_SOURCE markdown the handler wrote, distil the workflow into a generalised SKILL.md, save it at skills/<name>/SKILL.md. Use this when CraftBot has spawned a 'Create Skill' workflow task and you need to author the new skill end-to-end without user interaction.
374 repo starsObserved in 1 repos
Agent Building
craftbot-skill-improve
Refine an existing CraftBot skill using evidence from one completed task that used it. Read the per-task SKILL_SOURCE markdown the handler wrote, diff it against the existing SKILL.md, apply surgical edits to skills/<target>/SKILL.md. Use this when CraftBot has spawned an 'Improve Skill' workflow task and you need to refine the skill's accuracy or token efficiency without redesigning it.
374 repo starsObserved in 1 repos
Agent Building
memory-processor
Process raw events into distilled long-term memories using batch processing.
374 repo starsObserved in 1 repos
Agent Building
create-validation
Generate a draft VALIDATION.md for a skill by analyzing its SKILL.md construction steps
373 repo starsObserved in 1 repos
Agent Building