mcp-server-auth
Implements MCP server authorization - OAuth 2.1 resource server role, RFC 9728/8414 discovery, PKCE, RFC 8707 audience validation, scopes, client registration.…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-05 00:16
Agents & models
25,663 results
stitch-mcp-list-projects
Lists all Stitch projects accessible to the user.
figure-it-out
Design an auditable playbook when no narrower one fits: a large migration, an ambitious multi-part change, or work a human reviews after stepping away. Scales…
agents-context
Use to create or polish repo agent context files: README.md, AGENTS.md/CLAUDE.md symlinks, and existing project .agents/skills/SKILL.md files. Updates existing…
openclaw
This skill should be used when the user mentions "openclaw", "OpenClaw CLI", asks to "send a message via openclaw", "manage openclaw agents", "configure…
ai-prompt-writer
Use when the user needs a prompt for ChatGPT, Claude, Gemini, Midjourney, Sora, or another external AI tool. Use content-writing for general copy and…
saas-agent-unit-economics-and-cogs
Use when producing or reviewing the saas agent unit economics and cogs component of a business plan; applies its specialist evidence, decisions, and acceptance…
ai-agent-approval-audit-completeness
Use when proving that every irreversible agent action in the audit window had a documented, signed approval — completeness check (gap-detection job),…
ai-agent-ux
Use when designing UX for agentic AI, AI copilots, agent status, approvals, uncertainty, mobile and web agent workflows, and user trust surfaces.
orchestrate-engineering
Coordinate complex engineering work across bounded subagents while protecting the main context, preventing edit conflicts, and measuring whether delegation was…
nix-self-iteration-protocol
Use for evaluating, rewriting, refactoring, splitting, streamlining, or evolving AGENTS.md, SKILL.md, prompt architecture, skill description, and routing; also for diagnosing prompt failure, prompt failure, models not following global prompts, false triggering, missed triggering, instruction conflicts, rules placed at the wrong level, and various kinds of instruction system usage friction.
ai-agent-basics
Master AI agent fundamentals - architectures, ReAct patterns, cognitive loops, and autonomous system design
agent-frameworks
AI agent development with LangChain, CrewAI, AutoGen, and tool integration patterns.
adversarial-examples
Generate adversarial inputs, edge cases, and boundary test payloads for stress-testing LLM robustness
code-injection
Test AI systems for code injection vulnerabilities including prompt-to-code attacks and agent exploitation
prompt-injection-testing
Master prompt injection attacks, jailbreak techniques, input manipulation, and payload crafting for LLM security testing
rag-exploitation
Attack techniques for Retrieval-Augmented Generation systems including knowledge base poisoning
codereview-roasted
Brutally honest code review in the style of Linus Torvalds, focusing on data structures, simplicity, and pragmatism. Use when you want critical, no-nonsense…
social-emergence-protocol
Minimal interaction patterns that bootstrap complex social behaviors in distributed systems
unified-reafference
Cross-agent session database with B3 Poset and Bumpus sheaves
world-memory-worlding
World memory is world remembering is world worlding - the autopoietic loop where memory enables remembering enables worlding enables memory
agent-spec-generator
Write a production-ready spec for an AI agent: scope, tools and permissions, autonomy levels, stop rules, escalation, failure modes, evals, and rollout. Use…
implementing-agent-modes
Guidelines to create/update a new mode for PostHog AI agent. Modes are a way to limit what tools, prompts, and prompt injections are applied and under what…
implementing-mcp-tools
Guide for exposing PostHog product endpoints as MCP tools. Use when creating new or updating API endpoints, adding MCP tool definitions, scaffolding YAML…