Loading...
Loading...
Found 5,143 Skills
Benchmark any agent skill to measure whether it actually improves performance. Use when the user wants to evaluate, test, or compare a skill against baseline, or when they mention "benchmark", "eval", "skill performance", or "does this skill help". Runs isolated eval sessions with and without the skill, grades outputs via layered grading (deterministic checks + LLM-as-judge), analyzes behavioral signals, and generates a comparison report with a USE / DON'T USE verdict.
Merge the winning agent's branch into base, archive losers, and clean up worktrees.
Install and use Marketing Skills for AI agents — CRO, copywriting, SEO, analytics, and growth engineering skills for Claude Code and other coding agents.
Read, write, and browse the AgentHub message board for agent coordination.
Update agent skills installed with the `skills` CLI. Use when asked to refresh installed skills, keep a project's skills current, or troubleshoot cases where `npx skills update` reports that everything is up to date. For project-scoped installs, a no-change update must immediately run the bundled reinstall script so tracked skills from `skills-lock.json` are reinstalled without extra investigation.
Use this skill when working with A2UI (Agent-to-User Interface) - Google's open protocol for agent-driven declarative UIs. Triggers on tasks involving A2UI message generation, component catalogs, data binding, surface management, renderer development, custom components, or integrating A2UI with A2A Protocol, AG UI, or agent frameworks like Google ADK. Covers building agents that generate A2UI JSON, setting up client renderers (Lit, React, Angular, Flutter), creating custom catalogs, and handling client-to-server actions.
Expert skill for memory-lancedb-pro — a production-grade LanceDB-backed long-term memory plugin for OpenClaw agents with hybrid retrieval, cross-encoder reranking, multi-scope isolation, and smart auto-capture.
Professional prompt engineering, context engineering, and AI agent orchestration for coding agents (Claude Code, Codex, Cursor, Gemini CLI). Use when designing CLAUDE.md/AGENTS.md files, writing skills, planning multi-agent pipelines, optimizing token usage, managing session handoffs, or structuring any prompt for maximum agent performance. Do NOT use for general coding tasks or code review.
[Trigger] When PPT workflow needs SVG slide quality review via Gemini. [Output] Structured review assessment with scores, pass/fail, and fix suggestions. [Skip] For content authoring or SVG generation tasks (those are handled by Claude). [Ask] No user input needed; invoked by review-core agent. [Resource Usage] Use references/, scripts/ (`scripts/invoke-gemini-ppt.ts`).
Use when setting up a new AI agent from scratch — asks 10 discovery questions, configures the correct files for the target system, tests integrations, and implements security guardrails
Classify user requests and route to the correct agent + skill combination. Use for any user request that needs delegation: code changes, debugging, reviews, content creation, research, or multi-step workflows. Invoked as the primary entry point via "/do [request]". Do NOT handle code changes directly - always route to a domain agent. Do NOT skip routing for anything beyond pure fact lookups or single read commands.
Interact with the learning system: show stats, list/search accumulated knowledge, and graduate mature entries into agents/skills. Backed by learning.db (SQLite + FTS5). Use when user says "retro", "retro list", "retro search", "retro graduate", "check knowledge", "what have we learned", "knowledge health", "graduate knowledge".