Loading...
Loading...
Found 5,789 Skills
This skill should be used when the user asks to "design agent tools", "create tool descriptions", "reduce tool complexity", "implement MCP tools", or mentions tool consolidation, architectural reduction, tool naming conventions, or agent-tool interfaces. Part of the context engineering skill suite — also activates when the user mentions "context engineering" or "context-engineering" in the context of designing tools that shape how agents receive and process context.
Comprehensive security auditor for AI agent skills, prompts, and instructions. Checks for typosquatting, dangerous permissions, prompt injection, supply chain risks, and data exfiltration patterns — before you use any agent or skill.
Debugs errors and traces failures in AI agents and their tools. Use this skill when the user says: "the agent is failing", "tool call not working", "error in the pipeline", "debug this", "why is the agent doing X instead of Y", "trace the execution", "agent is stuck", "infinite loop", "model response won't parse", "context overflow". Identifies context errors, infinite loops, malformed tool calls, response parsing issues and subagent conflicts.
Build browser-based VoIP calling apps using Telnyx WebRTC JavaScript SDK. Covers authentication, voice calls, events, debugging, call quality metrics, and AI Agent integration. Use for web-based real-time communication.
Single entry point for all AEM 6.5 LTS Replication skills. Covers configuring replication agents, activating/deactivating content, using the Replication API programmatically, and troubleshooting distribution issues for Adobe Experience Manager 6.5 LTS.
6-phase interactive interview that generates the agent's identity (SOUL.md), user profile (USER.md), access control (ACCESS_POLICY.md), and operational cadence (HEARTBEAT.md). Re-runnable anytime to update any section.
Comprehensive security auditor for AI agent skills, prompts, and instructions. Checks for typosquatting, dangerous permissions, prompt injection, supply chain risks, and data exfiltration patterns — before you use any agent or skill.
Browser automation CLI using DOMShell MCP server. Maps Chrome's Accessibility Tree to a virtual filesystem for agent-native navigation.
Daniel Kahneman's Cognitive Diagnostic applied to a decision, strategy, or business evaluation. Spawns a team of specialist agents — System Detector, Substitution Mapper, Prospect Theorist, Noise Auditor, Outside Viewer — who each apply a different lens from Kahneman's cognitive architecture to audit the decision for bias, noise, and cognitive traps. The lead synthesizes into a contamination assessment: which cognitive systems are operating, which substitutions are active, and whether the decision should proceed, be corrected, or be restructured. Use when the user says "kahneman this", "check my thinking", "am I biased", "audit this decision", "what am I missing", or presents any decision, strategy, or evaluation they want cognitively stress-tested. Works standalone or as a companion to /munger (Munger evaluates the business; Kahneman audits the thinking about the business).
Lindy platform help — no-code AI agent builder for email triage, meeting notes, calendar management, custom workflow automation, chatbots, and AI phone agents. Use when setting up Lindy agents for inbox management, meeting recording not working or transcripts missing, credits burning too fast and need to optimize usage, building custom AI workflows with triggers and actions, choosing between Lindy and a dedicated note-taker or automation tool, or debugging agent errors in multi-step workflows. Do NOT use for picking a dedicated AI note-taker across vendors (use /sales-note-taker) or general workflow automation without AI reasoning (use /sales-integration).
Create and run orq.ai experiments — compare configurations against datasets using evaluators, analyze results, and generate prioritized action plans. Use when evaluating LLM agents, deployments, conversations, or RAG pipelines end-to-end. Do NOT use without a dataset and evaluators. Do NOT use for cross-framework comparisons with external agents (use compare-agents).
Generate a test suite of natural-language → SQL pairs that becomes the quality benchmark for a nao agent, then run it via `nao test`. Use when the user wants to start measuring agent reliability, extend an existing test suite, or add tests for new metrics. Tests are the only honest answer to "is the context working?". Do not use for writing rules (write-context-rules) or diagnosing failures (audit-context).