Skills
97,725 packaged capabilities and playbooks for agents. Install any of them with one command.
Agent workflows
Iskron’s door and session start: use /iskron or speak naturally. “Start” comes first, before readiness: graph and role, iskron_stand for watch and records, greet the person. Handles “why was this decided,” “what about this,” “write it down,” “think it through,” “what’s pending,” “who will it affect,” “is it working,” “tidy up,” “put the picture together,” “roadmap,” “can’t hear,” “connect the graph,” “remember this about me,” “update” (bridge, plugin, software, SUPPLY IS OUTDATED), “stand by the person,” “start graph role place,” and the older “enter the room” and “handle the matter.” Selects and executes a skill.
Two-tier memory system that makes Claude a true workplace collaborator. Decodes shorthand, acronyms, nicknames, and internal language so Claude understands requests like a colleague would. CLAUDE.md for working memory, memory/ directory for the full knowledge base.
Prompt engineering frameworks for building, testing, versioning, and evaluating prompts: chain-of-thought, few-shot, regression testing, and rubrics. Use when designing production prompts, running A/B tests, or building prompt libraries.
Implement adaptive learning with ReasoningBank for pattern recognition, strategy optimization, and continuous improvement. Use when building self-learning agents, optimizing workflows, or implementing meta-cognitive systems.
Comprehensive Claude Code self-assessment and learning path advisor. Runs a multi-category quiz covering 10 feature areas, produces a detailed skill profile with per-topic scores, identifies specific gaps, and generates a personalized learning path with prioritized next steps. Use when asked to "assess my level", "take the quiz", "find my level", "where should I start", "what should I learn next", "check my skills", "skill check", or "level up".
Navigate, search, and manage Droid sessions. Use when the user wants to: - List recent sessions - Search session history for specific topics or patterns - Resume a previous session - Get details about what was accomplished in a session - Find sessions by project, date, or content
Create new Claude Code Skills with proper YAML frontmatter, progressive disclosure structure, and complete directory organization. Use when you need to build custom skills for specific workflows, generate skill templates, or understand the Claude Skills specification.
Rigorously evaluate an Agent Skill end-to-end across ANY coding-agent CLI — verify its scripts emit the documented numbers (deterministic checks), test whether its description triggers on the right prompts, and measure whether an agent following the SKILL.md beats a no-skill baseline (with/without pass-rate delta, mean ± stddev, benchmarked). Use whenever you need to test, benchmark, validate, grade, or quantify a skill's quality, check if a skill "actually works," compare two skill versions, optimize a skill's triggering, or set up an eval suite — even if the user just says "is this skill any good," "does my skill work," or "benchmark this skill." Drives Claude Code, OpenAI Codex, Antigravity (agy), Cursor, GitHub Copilot, Amp, opencode, or Grok in headless mode.
Analytical and creative thinking frameworks. First principles decomposition, iterative depth analysis, council debate with multiple perspectives, red team stress testing, brainstorming, world and threat models, and scientific method. USE WHEN first principles, decompose, challenge assumptions, iterative depth, be creative, brainstorm, council, debate, red team, stress test, devil's advocate, threat model, world model, think about, experiment, hypothesis, deep exploration, figure out, optimize, improve, weigh options, creative solutions, critique, counterarguments.
Bootstrap project-specific Trellis coding specs with a platform-neutral single-agent workflow. Use when creating or refreshing .trellis/spec guidelines, analyzing a codebase with GitNexus, ABCoder, or source inspection, decomposing package/layer spec work, and writing real codebase-backed spec docs without placeholder text.
Generate AGENTS.md for end-user assistance. Covers setup, installation, running, and troubleshooting. Use proactively when user asks for "getting started" help or during /init user workflow. Examples: - user: "/init user" → user assistance AGENTS.md with official docs - user: "Create getting started guide" → installation + setup + troubleshooting - user: "Document how to use this repo" → user-focused AGENTS.md - user: "Help users run this software" → setup, prerequisites, usage patterns
Accurately estimate AI agent work effort using the agent's own operational units (tool-call rounds) instead of human time. Use when asked to estimate, scope, plan, or evaluate how long a coding task will take. Prevents the common failure mode where agents anchor to human developer timelines and massively overestimate. Outputs a structured breakdown with round counts, risk factors, and a final wallclock conversion.
Implement persistent memory patterns for AI agents using AgentDB. Includes session memory, long-term storage, pattern learning, and context management. Use when building stateful agents, chat systems, or intelligent assistants.
Create accounts for an agent at third-party services with AgentID, using an AgentMail inbox as the agent's identity, and see where each inbox already has an account. Use for ANY request like "create an account at Firecrawl", "sign my agent up for Turso", "get my agent a web search API", "log my agent back in to Firecrawl", "sign in with the auth token this page shows", "which services is this inbox signed up for?", or browsing the AgentID app marketplace. Do not use for sending or reading mail (agentmail-send-email, agentmail-check-email), inbox lifecycle on its own (agentmail-manage-inboxes), or MCP connection setup (agentmail-mcp).
Set up agent context for a project. Analyzes tech stack, installs relevant skills from skills.sh, generates custom skills, and configures MCP servers. Use when starting new project, setting up AI context, or asking "set up project", "configure AI", "what skills do I need".
Delegate coding, review, diagnostics, planning, structured output, and local browser research tasks to independent Codex sessions via the Codex CLI. Use cases include starting new tasks with `codex exec`, continuing multi-turn sessions with `codex exec resume`, read-only review with `codex exec review`, and cases needing `--json` event streams, `-o` final-message output to disk, image input, or Computer Use browser actions.
Principles and patterns for effective collaborative work (coworking). Use for aligning agents on communication etiquette, workspace hygiene, and feedback loops. Use proactively when coordinating multi-agent workflows, managing vault hygiene, or standardizing status updates. Examples: - user: "How should we work together?" -> review coworking principles - user: "Give me a status update" -> use 3P status reporting pattern - user: "Keep the workspace clean" -> apply vault hygiene rules - user: "Coordinate the specialists" -> follow collaboration patterns
Default entrypoint and master ctf-sandbox-orchestrator workflow for CTF, exploit, reverse engineering, DFIR, pwnable, crypto, stego, mobile, AI-agent, cloud, container, Active Directory, Windows-host, and identity challenges. Use first when the user presents challenge infrastructure, binaries, prompts, hosts, or identities that should be treated as sandbox-internal by default and Codex needs to choose, route, and load the right downstream analysis path with concise evidence.
Step executor for units whose triage (unit-lane) decided which steps the unit needs. Implements one triaged step (or all remaining steps), with frozen acceptance, step-local gates, commits, red-gate repair, and diff-size guard. BREAKING: replaced PLAN.md/TASKS.md/progress.md/ACCEPTANCE.md with the unit doc's Tasks section, Evidence rows, and Progress log; ACCEPTANCE.md is gone — acceptance criteria live in the unit doc and Evidence rows are the receipts.
A bidirectional integration channel between Feishu (Lark/Feishu) and OpenClaw. Uses a Feishu bot to receive and send messages, supporting private chats, group chats, @mention detection, card messages, and file transfer. Use this skill when you need to interact with an AI assistant through Feishu, trigger AI responses from received Feishu messages, or send messages from OpenClaw to Feishu. Difference from feishu-automation: this skill focuses on message channel integration, while feishu-automation focuses on automating operations on the Feishu platform (multi-dimensional tables, documents, etc.).
Brief another agent session so it can continue this work — directly to a running session or pane, or as a temp file when neither is reachable. Use on 'handoff', 'hand off', 'fresh context', 'new session', 'pick this up later', or proactively when context is full and work remains.
Evaluate a repo agent harness (AGENTS.md, rules, skills, skill refs) for broken paths/commands, redundant instructions, and usefulness using a stack-agnostic dual-judge protocol with planted traps. HIGH PRIORITY questionnaires at top: Q1 optional docs, Q2 B/C budget before Track A (certainty/tokens). A always runs after Q2; B/C opt-in. ADRs/RFCs excluded from T2. Mixed apply uses 11-mixed-apply.md (KEEP/CUT). Use when the user says harness eval, harness-eval, harness debug, audit AGENTS.md, audit skills/rules, instruction audit, redundancy of agent instructions, usefulness of skills, Ship/Review/Hold/Slim/Keep-core for harness, or wants Track A/B/C harness evaluation. Do NOT use for harness setup or init, feature spec-driven work (tlc-spec-driven), or applying Ship/Slim trims unless the user explicitly asks after the report.
Build production realtime voice agents with Hume's Empathic Voice Interface (EVI): speech-to-speech sessions, empathic/prosodic response design, EVI 3 versus EVI 4-mini selection, WebSocket and SDK integration, tools/function calling, interruption/barge-in, turn-taking, transcripts/audio artifacts, pricing/limits, privacy, safety, consent, and QA.
Install themed spinner verb packs for Claude Code. Fetches spinner packs directly from the awesome-claude-spinners repository and installs them into the user's settings. Use when the user wants to customize their Claude Code spinner, install spinner verbs, or change spinner themes.
Loads documents fully into the main agent's context so the agent can answer questions, summarize, or work with that content in subsequent turns. Use whenever the user wants to ingest, read, study, review, absorb, or pull in documents — especially when they say things like "load these docs", "read all of these", "ingest this folder", "pull in these PDFs", "load all docs in X", or paste a list of file paths/URLs and ask you to read them. Handles local files (text, code, markdown, PDFs, notebooks, images), entire folders (recursively), and remote URLs. The skill is single-turn — once the agent reports "DONE", it deactivates until the user invokes it again.
Design, implement, harden, and verify Model Context Protocol (MCP) servers with precise tool contracts, least-privilege authorization, safe transports, structured errors, and interoperability tests. Use when creating a new MCP server, exposing an API or data source through MCP, reviewing an MCP server design, adding or revising MCP tools, or preparing an MCP server for production.
Agentic Services on Polygon — pay-per-call APIs gated by the x402 payment protocol, callable via the Polygon Agent CLI. No API keys or subscriptions; each call costs a small USDC amount drawn from the agent's smart wallet. Covers web search (Exa, SearchApi), web scraping (Firecrawl), news (NewsAPI), LLM inference (Llama 3.3/3.2 via NVIDIA NIM, OpenRouter), cloud browsers (Browserbase), email (Resend, AgentMail), on-chain wallet analytics and prices (Allium), and multi-chain JSON-RPC (QuickNode, 16 chains).
This skill should be used when the user wants to "add a skill", "create a skill", "make a new skill", "write a new skill", "improve skill description", "organize skill content", or needs guidance on skill structure, progressive disclosure, or skill development best practices. Use this (not add-skill) when authoring a new skill from scratch rather than importing one from a GitHub URL.
Use for producing Tavus AI-human videos and real-time avatar conversations with Tavus Faces/Replicas, PALs/Personas, async Video Generation, CVI conversations, consent-safe likeness workflows, webhooks, backgrounds, localization, and avatar QA.
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.