Skills
97,222 packaged capabilities and playbooks for agents. Install any of them with one command.
Agent workflows
Use when a task benefits from multiple Claude instances collaborating with peer-to-peer messaging - parallel research, multi-module features, cross-layer changes, or competing hypothesis debugging. Not for simple independent tasks (use parallel-execution) or sequential tasks (use delegated-execution).
Deploy autonomous AI agents on the Teneo Network using the Teneo Agent SDK (Go). Mint a gasless NFT identity, define commands and pricing, and earn USDC per query through x402 micropayments. Supports EnhancedAgent, SimpleOpenAIAgent, and OpenAIAgent.
Break a plan, spec, or the current conversation into a set of tracer-bullet tickets, each declaring its blocking edges, published to the configured tracker (edges as text in one file per ticket locally, or native blocking links on a real tracker).
Tiered LLM extraction pattern for large corpus processing (email archives, document dumps, transcript libraries). A utility-tier model triages and classifies at speed; the reasoning tier does the default deep read; the deep tier is the escalation for the highest-value content. Prevents spending deep-tier money on noise while ensuring the important content gets the best eyes. A deterministic privacy wall runs before any LLM call.
Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always
Use when the user wants to manage their VPS servers and the AI agents running inside them — connecting, deploying, monitoring, restarting, and operating remote hosts and their agents. Triggers on VPS, server management, remote host, SSH into server, manage my servers, agents on the server.
Use when the user asks about WordPress codebases (plugins, themes, block themes, Gutenberg blocks, WP core checkouts) and you need to quickly classify the repo and route to the correct workflow/skill (blocks, theme.json, REST API, WP-CLI, performance, security, testing, release packaging).
End-of-session documentation workflow that updates README, CHANGELOG, agent context files, and creates session logs. Use when wrapping up a working session, when asked to document session progress, when preparing handoff documentation, or when the user says "wrap up", "end session", "document progress", or "save session".
Compare AG2 agents, models, or prompts to decide which is better. run_variants scores several named agents on one suite and ranks them on a leaderboard (Variants holds a mapping of named Agent instances plus an axis label). run_pairwise with pairwise_judge does head-to-head LLM comparison using a dual-order position swap (a win counts only if it survives the swap, else a tie), reporting win-rate with a Wilson 95% CI, wins, losses, ties, flips, and agreement (Cohen's kappa). human_pairwise collects a person's blinded vote inline, or via an exported manifest with export_pairwise_cases and human_labels. Use when the user wants to A/B test prompts or models, run a leaderboard, pick a winner, judge head-to-head, measure win-rate, or collect human preference labels. For running and grading a single agent, see ag2-evaluation.
Automate headless browser interactions using agent-browser CLI. Use when scraping web pages, automating form submissions, testing web apps, or performing browser automation tasks. Works with element refs (@e1, @e2) optimized for AI agent reasoning.
Commit SpecStory transcripts and Claude/Cursor/OpenCode/Codex plans with feature diffs, derive staged `AI-Assisted-By` plus transcript/plan trailers, prevent secret leaks, and ignore SpecStory machine-local state. Use when asked to commit/save/stage agent sessions, record cross-harness provenance, bootstrap pre-commit, fix `.specstory/statistics.json` churn, scrub a transcript, or remediate accidental secret commits/pushes with rotate-first discipline.
Use this skill when the user asks to save, remember, recall, or organize memories. Triggers on: “remember this”, “save this”, “note this”, “what did we discuss about...”, “check your notes”, “clean up memories”. Also use proactively when discovering valuable findings worth preserving.
Maintain README.md, AGENTS.md/CLAUDE.md, skills, and repository context. Create, scaffold, or initialize AGENTS.md files and project-local agent skills. Use task evidence to delete obsolete skills, merge overlapping skills, and capture recurring workflows.
Use when routing Alibaba Cloud Model Studio requests to the right local skill (Qwen text, coder, deep research, image, video, audio, search and multimodal skills). Use when the user asks for Model Studio without specifying a capability.
Reference for APM (Agent Package Manager) — apm.yml syntax, install / uninstall / update commands, target detection, lockfile workflow. Read when you need exact field names, but do NOT auto-invoke on every apm-related task; user prompts about projects with installed skills can be handled with general APM knowledge. Invoke explicitly when the user mentions APM by name, asks to author or audit an apm.yml, or runs into an unfamiliar APM command / error.
This skill helps an LLM generate correct audio code with @ax-llm/ax. Use when the user asks about ai.transcribe(), ai.speak(), signature audio inputs or outputs, agent audio behavior, .chat() conversational audio, OpenAI audio or realtime models, Gemini Live native audio, Grok Voice Agent models, voices, formats, transcripts, or how audio fits with structured outputs.
Solve a hard problem by trying multiple approaches in parallel using isolated git worktrees. Each attempt runs in its own branch, and the best solution is selected. Use for complex refactors, tricky bugs, or architectural decisions where multiple strategies could work.
Use when Codex on macOS must drive the user's Chromium browser (Brave, Vivaldi, Opera, Edge, Chrome) through the bundled Chrome plugin, or that plugin fails with "Codex auth token is unavailable", a missing extension connection, or a stale plugin cache after a desktop app update. Codex only.
Automate code review remediation loops with the codex CLI. Requests reviews from codex, classifies findings by severity (P0-P4), fixes critical issues (P0/P1) through iterative cycles, defers quality improvements to backlog, and escalates after 3 review cycles. Use when working with code that needs structured remediation: ''codex review'' in a request triggers this workflow.
Author continuously-running online evaluations in PostHog AI observability, grounded in real failure modes you've identified. Use when the user wants evaluations that automatically score new generations or whole traces going forward — "create an eval to catch X", "continuously check that responses do Y", "turn these failures into evals". Covers letting the explored data decide how many evals to create, proposing that set for the user to pick, choosing the target and eval type (hog / llm_judge / sentiment), configuring a provider and model for an llm_judge eval (a provider key gates enabling, not creation), scoping which generations trigger it via conditions, creating disabled, verifying scope, enabling, and backfilling past data. Proposes a sentiment eval when no failure mode is worth catching. Finding and ranking the failure modes worth evaluating is its own job — use exploring-ai-failures first. To debug or manage evaluations that already exist, use exploring-llm-evaluations.
Destructive Command Guard - High-performance Rust hook for Claude Code that blocks dangerous commands before execution. SIMD-accelerated, modular pack system, whitelist-first architecture. Essential safety layer for agent workflows.
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.