Skills
97,222 packaged capabilities and playbooks for agents. Install any of them with one command.
Agent workflows
Full red team assessment methodology. Use when starting a complete penetration testing project/red team assessment and you need end-to-end orchestration from reconnaissance to reporting. Applies to external-facing footholds, security assessment projects, and periodic penetration tests. This skill handles task scheduling - call specialized skills for specific exploits; do not perform deep vulnerability testing within this skill.
Repository packaging for AI/LLM analysis. Capabilities: pack repos into single files, generate AI-friendly context, codebase snapshots, security audit prep, filter/exclude patterns, token counting, multiple output formats. Actions: pack, generate, export, analyze repositories for LLMs. Keywords: Repomix, repository packaging, LLM context, AI analysis, codebase snapshot, Claude context, ChatGPT context, Gemini context, code packaging, token count, file filtering, security audit, third-party library analysis, context window, single file output. Use when: packaging codebases for AI, generating LLM context, creating codebase snapshots, analyzing third-party libraries, preparing security audits, feeding repos to Claude/ChatGPT/Gemini.
Navigate the Research Agent Skills collection by Kalaris Labs for academia across AI, machine learning, biology, chemistry, medicine, physics, and academic writing. Use when a researcher needs to choose a field of study, identify relevant specialist SKILL.md files, or coordinate a cross-disciplinary research workflow. For a narrow task with a matching specialist skill already available, use that skill directly
Acts as the primary starter that automatically coordinates the entire research workflow, from topic exploration and gap identification through methodology, data experiments, literature synthesis, to publication readiness.
How to author custom PostHog Review skills: the review perspectives, blind-spot checks, validation criteria, and resolution criteria that drive PostHog Review's automated PR reviews. Use when a user wants a new review perspective (a specialist lens on their PRs), a custom blind-spot sweep, their own validation bar for which findings get published, or their own bar for which review comments get implemented. Trigger on "create a PostHog Review perspective", "custom review perspective", "my own blind-spot check", "custom validation criteria", "custom resolution criteria", "tune what PostHog Review publishes", "tune what PostHog Review implements".
Implements the Spec-Driven Development lifecycle (Intent, Requirements, Design, Tasks, Build) for structured feature development. Use when the user wants to scaffold a new feature spec, generate EARS requirements, create a technical design, break work into tasks, or check spec status. Trigger on keywords: sdd, spec-driven, ears requirements, feature spec.
SDD fast path. Runs the full pipeline — analyse → plan → implement → review → archive — with a single confirmation gate before implementation begins. Stops automatically if Critical or Major issues are found in review. Use when you want to ship a well-understood feature with minimal interruptions.
Main Figma orchestration skill for the UI/UX skill system. Use this skill whenever the user asks to read Figma design context, turn Figma frames into implementation plans or code, sync live UI back to Figma, edit Figma canvas objects, manage variables/components/assets/effects, audit Figma MCP workflows, or coordinate Figma work under $senior-ui-ux-orchestrator. Routes to figma-context-reader, figma-design-to-code-bridge, figma-code-to-canvas, figma-canvas-editor, figma-design-system-sync, figma-assets-manager, figma-apply-effects, and figma-workflow-auditor while enforcing privacy, tool availability, and evidence boundaries.
Run an autonomous Humanize-governed SGLang SOTA performance loop for one LLM model: first perform a fixed fair SGLang benchmark against the requested comparison framework set, then start one RLCR loop that repeatedly decides the gap, profiles the current bottleneck, runs layer/kernel pipeline analysis, patches SGLang code, optionally uses ncu-report-skill for kernel evidence, and revalidates until SGLang matches or beats the best observed requested framework under the same workload and SLA.
Build, connect and maintain local knowledge bases, preserving originals and creating a traceable index. Use for "enterprise knowledge base", "company document organization", "product, customer and skill libraries", "turn a folder into a knowledge base", "self-media knowledge base" and "knowledge base health check". Supports three modes: enterprise three-library, general, and self-media; enterprise mode first understands the company and materials, classifies by product, customer and team SOP, and delivers each library's content and material gaps. Works with WorkBuddy, Codex and Claude Code; does not handle cloud RAG, automatic sync, or unauthorized file relocation.
Signals scout for PostHog MCP tool calls. Watches `$mcp_tool_call` telemetry for tools that need improvement — broad-reach failure rates, retry hammering, slow or context-bloating responses — grouped by owning product category, each with a fix suggestion.
This skill should be used when the user asks to "fetch skill", "install skill", "search for a skill", or when a hook outputs "MISSING EXTERNAL SKILL". Searches 9 registries (SkillsMP, GitHub, Anthropic Skills, ClawSkillHub, skills.sh, PolySkill, SkillHub, Skills Directory) with multi-variant search, quality scoring, security labels, pagination, and local/global installation.
Audit and maintain the joelclaw skill inventory. Use when checking skill health, fixing broken symlinks, finding stale skills, or running the skill garden. Triggers: 'skill audit', 'check skills', 'stale skills', 'skill health', 'skill garden', 'broken skill', 'skill review', 'fix skills', 'garden skills', or any task involving skill inventory maintenance.
Design, integrate, evaluate, self-host, and troubleshoot typed System One decision models including TypeSafe Jev, Convai Innovations Laya, CLM, and experimental Strands Decider. Use for Choice/Score/Noul judgments and experimental Jev image/Box queries inside deterministic software, app-control loops, routing, ranking, guardrails, calibration, semantic code linting and post-edit feedback, DevOps decision support, confidence-based escalation, or private open-model inference. Do not use for syntactic/style linting, exact policy or authorization, open-ended generation, or generic LLM serving without a bounded decision contract.
Prepare a self-contained task or agreed GitLab task set, apply shared review and scoped release planning, and produce a local Markdown plan with manual glab commands. Use when the user asks to prepare a task, an issue, or an agreed task set for execution or GitLab publication. Russian discovery terms: подготовить задачу, подготовить issue.
Inspects the OrchestKit telemetry pipeline for the current project — lists all known telemetry files with write counts, sizes, schema status, growth trend, and orphan detection. Use when verifying the observability pipeline is healthy, debugging a missing writer, or auditing which files have schema locks vs. which are drift-vulnerable. Read-only — never modifies telemetry files.
End-to-end work with UiPath Agents of all types: build, integrate with UiPath Products (e.g., Orchestrator, Flow, Maestro), design with UiPath Tools (e.g., Agent Builder/Studio Web), deploy, and configure/validate. Covers Coded Agents (e.g., LangGraph, LlamaIndex, OpenAI Agents) and Low-Code Agents (`agent.json` / Agent Builder). For deterministic Coded Functions — Python or JS/TS (`uip function`, `uipath.json` functions map, no agent runtime/LLM)→uipath-functions.
Use when the user wants to manage Valet agents, channels, connectors, organizations, or environment variables (secrets and plain config) via the valet CLI. Handles creation, deployment, linking, teardown, and all multi-step workflows. Also use when asked to "create an agent", "deploy an agent", "design an agent", "build me an agent that...", "create a connector", "set up a webhook", or anything involving the Valet platform or any request to create and deploy AI agents. Also use when asked to "learn from this session", "capture this workflow", "save this as an agent", "make this repeatable", or when writing SOUL.md files.
Guides beginner-to-intermediate developers through web development, Claude Code skills creation, and AI-assisted coding workflows. Use when the user asks about "vibe coding," "learning to code," "web development basics," "Claude skills," "building websites," "frontend," "backend," or wants help with HTML, CSS, JavaScript, or deployment.
All online operations must be handled through this skill, including searching, web scraping, post-login actions, and online interactions. Use when the user asks to search for information, view web content, visit a site that requires login, interact with a web interface, scrape social media content (Xiaohongshu, Weibo, Twitter, etc.), read dynamically rendered pages, or perform any online task requiring a real browser environment.
Use when putting the agent in this repository on a Veris Bench bench as a "Your image" candidate, when updating that candidate to a new version, or when its bench attempts show empty replies, failed tool calls, no model calls for the grader, or never reach the bench's twins.
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.
Unified management of email inboxes dedicated to Agents: lets Agents on platforms such as Claude Code and Codex send and receive email, tidy up inboxes and distribute tasks with one set of commands. Supports two backends, NetEase ClawEmail (claw.163.com) and Tencent Agent Mail (QQ Mail, agent.qq.com), switched via MAIL_PROVIDER. Use this skill when the user mentions sending or receiving email, checking an inbox, searching email, replying to or forwarding email, downloading attachments, tidying up email, assigning email tasks to other Agents, configuring an Agent mailbox, Tencent QQ Mail Agent, or NetEase ClawEmail.
Delegates non-trivial engineering work to an `explorer` (investigation, research) and a `fixer` (implementation) in a Herdr session, while the current top-level agent keeps strategy and review. Use when a root cause is unclear, code or architecture is unfamiliar, an external API, SDK, or specification needs research, or an implementation spans several files — even when the user never mentions agents, delegation, or orchestration. Do not use when the current agent was itself delegated work as an `explorer` or `fixer`. Requires HERDR_ENV=1. Handle trivial, local, low-risk work directly.
The open protocol for turning AI agents into engineering teams. One Agentera skill with twelve capabilities, each defined by human-readable prose and machine-readable schemas. The agent reads this file to route incoming requests to the right capability. Use this skill for /agentera, Agentera capability requests, and a complete user message exactly `hej`; bare `hej` runs the agentera prime orientation dashboard path instead of a generic greeting.
Use when installing or configuring OpenClaw with DingTalk, Feishu, Discord, and additional channels with Bailian/DashScope models on Linux hosts. Use when provisioning a new OpenClaw node, troubleshooting gateway/channel startup, standardizing openclaw.json mapping, or automatically discovering extra channels from https://docs.openclaw.ai/channels.
Comprehensive Anthropic product expertise covering Claude models, Claude API, Python SDK, Agent SDK, Claude Code, and Model Context Protocol. Six integrated capabilities with complete documentation, searchable references, code examples, and cross-product integration patterns. Use when working with Claude API, building agents, using SDKs, developing with Claude Code, integrating MCP servers, learning Anthropic products, optimizing costs, implementing Anthropic features, managing context, using Opus 4.5, or implementing advanced tool patterns.
Slice-based, evidence-driven framework for explicit codebase migrations and convergence programs. Use when the user is moving from a named source to a named target, running a multi-session standardization effort across a codebase, consolidating parallel implementations into one target architecture, or asking for a migration playbook with slices, ratchets, handoffs, and release closeout. Do not trigger for normal refactors, routine cleanup, or one-off architecture improvements that are not framed as a migration or convergence effort.
Coding Agent Account Manager - Sub-100ms account switching for AI coding CLIs with fixed-cost subscriptions. Vault profiles, isolated profiles for parallel sessions, smart rotation with health scoring, cooldown tracking, automatic failover, TUI dashboard. Go CLI.
Use to drive a slice's phases to completion through in-session capsule subagents in the MAIN worktree — you are the super-orchestrator seat, spawning capsule-orchestrators that each charter ~3 phases and spawn their own planners and workers. No worktrees, no dispatch, no confinement. Use when you want a whole slice implemented under a tight context budget without handing the tree to confined workers. Not for confined or parallel-worktree execution — that is /dispatch.
Orchestrate CAW (Cobo Agentic Wallet) agent evaluations locally on a Mac and dispatch headless claude / openclaw agents to remote servers for execution, finally producing scoring data and analysis reports. Use when: the user wants to run CAW evaluations, run an eval, test a Skill, assess agent quality, generate an evaluation report, or says "跑评测", "测评 CAW", "eval", "评分", "recipe 评测", "弱模型评测", "openclaw 评测", "模型兼容性测试".
Recall project-first and global-supplement ChatCrystal memories before substantive implementation, refactoring, migration, configuration, investigation, or optimization work. Use when the task is non-trivial, has repository or project context, and prior fixes, decisions, pitfalls, or reusable patterns may change the approach.
Write reusable ChatCrystal task memories after substantive work completes. Use when implementation or debugging produced a durable fix, pitfall, pattern, or decision worth preserving, and when the environment can either persist it through `write_task_memory` or emit a structured memory candidate for later save.
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.