Loading...
Loading...
Found 11,954 Skills
oh-my-agent project setup verification and configuration
Three-layer security ecosystem for Agent Platforms covering pre-deployment skill auditing, real-time message protection (adaptive-guard), and continuous adaptive defense. Coordinates security-auditor and adaptive-guard. Trigger on 'security ecosystem', 'agent security', 'skill protection', or 'runtime defense'.
ABSOLUTE MUST to debug and inspect LLM/AI agent traces using PostHog's MCP tools. Use when the user pastes a trace URL (e.g. /llm-observability/traces/<id>), asks to debug a trace, figure out what went wrong, check if an agent used a tool correctly, verify context/files were surfaced, inspect subagent behavior, investigate LLM decisions, or analyze token usage and costs.
Guidance for creating, running, fixing, and promoting behavioral evaluations. Use when verifying agent decision logic, debugging failures, debugging prompt steering, or adding workspace regression tests.
Use when context is growing large (50k+ tokens), performance is degrading, instructions are being ignored mid-conversation, or planning multi-agent workflows. Triggers on "lost context", forgotten instructions, or sessions exceeding 30 minutes.
Command-line interface for CloudAnalyzer — Agent-friendly harness for CloudAnalyzer, a QA platform for mapping, localization, and perception outputs. Supports 27 commands across 8 groups: point cloud evaluation, trajectory evaluation, ground segmentation QA, config-driven quality gates, baseline evolution, processing, visualization, and interactive REPL.
Full optimization workflow, sub-agent launch templates, agent communication contracts, default configurations, tuning strategy, and knowledge base update protocol. Use when: (1) starting an optimization cycle, (2) launching a Profiler or Designer sub-agent, (3) interpreting or formatting agent communication, (4) updating the knowledge base after a profiling or implementation iteration, (5) deciding default configurations or tuning strategy for a kernel.
Internal conversation-entry router for Claude Code. Performs a lightweight intake pass at the start of substantive work: decide whether a more specific skill should be invoked first, whether specialized agent delegation is warranted, how much context is actually needed, and whether the task needs planning or can proceed directly. Not a user-facing slash command.
Execute tasks through competitive multi-agent generation, meta-judge evaluation specification, multi-judge evaluation, and evidence-based synthesis
Framework for collective skill evolution in multi-user LLM agent ecosystems — automatically distills session experience into reusable SKILL.md files and shares them across agent clusters.
Generative ideation engine. Takes a domain, trend, question, or constraint and produces 15-30 novel possibilities — things that might be true, businesses that could exist, futures that could unfold. Spawns a team of 6 specialist agents — Signal Scout, Analogist, Inverter, Combinator, Contrarian, Futurist — who each generate ideas from a distinct creative angle. The lead cross-pollinates across agents, finds unexpected combinations, and ranks the output by novelty × plausibility. Use when the user says "brainstorm", "what could exist", "what's possible", "generate ideas", "what might be true", "possibilities", or presents a domain and wants divergent exploration rather than evaluation of a specific idea.
Richard Feynman's Integrity Audit applied to any analysis, business plan, or decision. Spawns a team of specialist agents — Source Auditor, Self-Deception Hunter, Translation Tester, Cargo Cult Inspector, Confidence Inverter — who each apply a distinct lens from Feynman's framework to detect dishonesty, self-deception, and cargo cult reasoning. The lead synthesizes into a verdict: is this analysis honest, or is it fooling itself? Use when the user says "feynman this", "integrity audit", "is this honest", "am I fooling myself", "cargo cult check", or wants to stress-test any analysis, plan, or claim before trusting it. Works standalone or as a meta-audit after /munger or /thiel.