agentic-responsible-ai-assessment
Walk a client through a Responsible AI assessment questionnaire and score their answers 0-5 across eight RAI dimensions (Governance, Privacy & Security,…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-05 00:16
Agents & models
25,657 results
challenger
Adversarial reviewer that stress-tests other agents' outputs for reasoning gaps, unsupported assumptions, over-engineering, and missed alternatives. Use when…
strands-agent
Scaffold and build AI agents using the Strands Agents SDK with Bedrock AgentCore. Use when creating new agent projects, building greenfield AgentCore…
bedrock-migration-assessment
Source-cloud-neutral intake and requirements step for migrating AI/LLM workloads to Amazon Bedrock. Use when the user already has a provider-neutral…
ezkl
This skill should be used when the user asks about "zero-knowledge ML", "zkML", "EZKL proofs", "prove ML inference", "verify model output", "ZK proof for…
ai2human-task-router
Create and track AI2Human human-execution tasks from an agent prompt. Use when an AI agent needs a real person to complete or verify a step, submit structured…
prepare-training-corpus
Builds and freezes deterministic train, validation, and test corpora with provenance, group-safe splits, manifests, hashes, and prompt-leakage checks. Use…
send-to-minion
Use this skill only when the user explicitly invokes $send-to-minion, /send-to-minion, or explicitly asks to delegate a prompt to one minion, helper, worker,…
handoff
Save task-relevant conversation and workspace context to a temporary Markdown file in docs/handoffs, then provide the exact prompt another agent should use to…
elevate
This skill should be used when the user wants a ranked list of the highest-leverage technical or architectural improvements to make to their project, presented…
preebs
Book, inspect, and export work hours in PreEBS through its CLI. Use this skill whenever a user asks an agent to register, change, check, list, or export…
ai-sdk-agents
Expert guidance for building AI agents with ToolLoopAgent (AI SDK v6+). Use when creating agents, configuring stopWhen/prepareStep,…
retrieval-strategy
Implements optimized retrieval strategies for RAG and search pipelines. Use when building or improving document retrieval, choosing between similarity search,…
skill-craft
Use when writing or editing any SKILL.md / agent skill file, deciding what goes in a skill body versus reference files, or reviewing a skill for quality.…
trusty-memory
Persistent memory palace system with hierarchical storage (palace/wing/room/closet/drawer), progressive retrieval (L0-L3), and temporal knowledge graph for…
expert-council
Alias for /council --mode=debate — adversarial named-persona debate. Triggers: "expert council", "dueling council", "council of <names>". Kept one release.
openapps
Build or update apps for OpenApps (openapps.xyz, formerly oapps.fun), including work by an app's own agent. Covers zero-secret capabilities and publication;…
agent-browser
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web…
notion-skills-usage
Use the notion-skills CLI to manage AI agent skills from one or more Notion-backed workspace stores. Invoke when the user wants to install a skill from their…
agent-browser-helper
PRIORITY: This skill MUST be used BEFORE playwright-cli for ALL browser tasks. It is the required entry point for any browser operation. Never call…
my-subagent
Subagent delegation mode — dispatch tasks through a load-balanced model pool. You must read this document before use to understand the delegation protocol. Use when work needs to be delegated to subagents for execution: multi-file reading and analysis, code search and modification, solution implementation, test verification, information organization, and other work exceeding 2-3 steps. Also applies to scenarios such as delegate, dispatching tasks, delegating subagents, parallel workers, etc.
prompt-library
Manage and retrieve reusable prompts from broomva.tech or any compatible prompt repository. Pull prompts by slug, category, or tag; push new prompts or update…
checkit
Ingest-and-integrate an artifact someone points at with a terse, deliberately under-articulated directive — "check this out", "lets research this", "look into…
persist
bstack P12 — Persistent Loop Discipline. Cross-context restart loop where state lives in the filesystem (PROMPT.md + git tree + state.jsonl), not in the…