Skills
97,222 packaged capabilities and playbooks for agents. Install any of them with one command.
Agent workflows
Scans all skill directories in the repository to generate a comprehensive global map of agent capabilities, inputs, and outputs. Use when you need to understand the full potential of your agent library or when a master agent needs to decide which sub-agent skill to invoke for a complex task.
Audit MCP servers for tool poisoning, tool shadowing, rug pulls, SSRF, and unauthenticated exposure using Invariant Labs' mcp-scan for static/runtime scanning plus manual SSRF/auth checks and description pinning. Use before adding a new MCP server to an agent stack, when reviewing an internal MCP server, detecting rug pulls, or investigating an agent's unexpected tool-driven behavior.
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
(NS) Harness boot + brownfield prepare. Triggers: /ns-harness, prepare this repo, harness prepare, generate architecture rules, architecture-rules.md, write AGENTS.md, reverse-engineer codebase, engenharia reversa, brownfield map, bootstrap brownfield, ns-harness-prepare, ns-architecture-rules, ns-agent-generator, ns-codebase-reverse-spec, ns-bootstrap-brownfield. Do NOT: coding, SDD, GitLab.
Act as a Senior QA Engineer covering the complete software testing lifecycle, from requirements analysis through test automation and continuous improvement. Always orchestrate available skills to determine the best approach before executing tasks.
Manually invoked skill that makes the agent compress its current answer — remove filler, simplify wording, and cut length while preserving the substance. Use when the user says "short", "shorter", "simpler", "too long", "tl;dr", or asks for a more concise version of the previous response.
Designing CLIs that AI agents will invoke — non-interactive flags, layered --help with examples, stdin/pipeline composition, actionable errors, idempotency, dry-run, destructive-action safety, and predictable command structure. Use when designing, building, or reviewing a command-line tool that AI agents or automation will invoke. Trigger even if the user doesn't explicitly say "agent-friendly" — apply whenever they are writing `--help` text, adding a new subcommand, designing error messages, or reviewing a CLI's UX.
Use when you find a gap or repetitive issue caused by you or an implementation agent. Essentially, use it whenever you say, “You’re absolutely right, I should have done it differently.” Create a rule for the issue so it doesn’t happen again.
Primes the agent with focused understanding of the frontend portion of the codebase — components, routing, state management, and styling — without loading unrelated backend code. Use at the start of a session when the work is scoped to UI or client-side features. Optionally pulls external task context from Jira issues and Confluence pages first.
Set up your project's global rules, a lean and well-structured root CLAUDE.md (plus a starter .claude/), following the course methodology. Greenfield: pass your PRD and/or architecture-spec path and it derives rules from your engineering decisions (a PRD alone is product context). Brownfield: leave it blank to derive from your primed codebase (run /prime-codebase first), or pass a codebase-analysis doc for a large repo. Use when initializing or re-deriving the AI Layer's rules, onboarding a codebase, or replacing a generic /init output. The customizable replacement for /init.
Entry point for evals. Use when the user asks for help with evals, does not know where to begin, or asks for something no other skill in this plugin matches. Do NOT use when a more specific skill in this plugin already matches; load that skill directly.
WAVES — Workers · Aggregate · Verify · Extend — wave-based orchestration for Cursor. Decompose a big goal into independent slices, fan them out to isolated parallel subagents via parallel Task tool calls as a bounded "wave", verify each structured handoff, then synthesize, and extend into another wave only when warranted. Invoke explicitly with /waves; bounded by design to avoid runaway token loops. For big research, analysis, audits, and codebase or data exploration where one linear pass is slow. Formerly parallel-orchestrate; also fan out, parallelize, orchestrate subagents, multi-agent.
Make an AI agent run on a schedule, loop, or interval — cron, heartbeats, recurring autonomous checks. Use for "run every N minutes", "schedule a task", "run on a loop", "heartbeat". Covers external clocks (Claude Code, Codex, Pi) vs Hermes' built-in scheduler
Eva Link standalone local workflow integration entry point. Handles existing Link calls, connecting prompts/SOPs/private methodologies to Eva, custom Links, and Link checks. Triggers: /eva-link, /eva-link-builder, /eva-link-diy, /eva-link-doctor, custom Eva-skill, make my own Link, connect prompts to Eva, check local Link, use one of my Links.
Eva-skill 2.5.0 shared support package. Install alongside eva, eva-teaching, eva-positioning, eva-think, eva-audience-finder, eva-create, eva-preflight, eva-learn, eva-brief, eva-link, eva-review, and eva-lens so sibling Eva skills can read shared schemas, references, examples, and validation scripts. Do not use directly for user tasks.
Measures whether Claude uses an MCP server's tools correctly—tests tool selection accuracy, analyzes schema quality, and iteratively optimizes descriptions. Triggers when the user asks to evaluate MCP tools, test tool selection, improve tool descriptions, check MCP schema quality, or evaluate their MCP server. Companion to build-mcp-server.
Help users find suitable tools from the currently released PostPlus skill surface and provide public installation commands. Use this when the user asks which skill can do a task, which skill to install, or what the released skill surface covers.
Use when turning local, private, or personal Agent Skills into publishable skills for GitHub, marketplaces, teams, or public sharing, especially when private paths, personal habits, credentials, internal hosts, or user-specific context must be removed
Complete AI agent operating system with Kanban task management, multi-agent coordination, human approval gates, and autonomous task discovery via heartbeat polling. Use when setting up multi-agent coordination, task tracking, or configuring an agent team. Includes theme selection (DBZ, One Piece, Marvel, etc.), workflow enforcement (all tasks through board), browser setup, GitHub integration, and memory enhancement (Supermemory, QMD).
Generate interactive AI transformation context-builder prompts for consulting clients. Use when creating structured discovery session prompts that guide a company through context gathering about their business, pain points, tech stack, and AI opportunities. Produces a resumable, multi-section prompt with Express/Deep Dive modes.
Create a specialized CLAUDE.md (+ AGENTS.md symlink) inside a specific folder to give future agents folder-scoped context. Use when the user asks to create a CLAUDE.md for a folder, write folder instructions, or add agent context to a directory.
Agentic eyes for Godot work: cross-platform screenshot CLI (asset/region/window/screen) to budgeted WebP, TEMP editor viewport bridge under .gdskills/, and Taste Receptor Atlas v2 (~237 micro-receptors × 0–2: hierarchy, contrast, typography×41, affordance, space, color, icon, composition, light/FX, motion-tells, anti-slop, originality, identity). Use when agents must see UI, assets, or the editor — not for in-game screenshot Autoloads. Keywords: agent vision, screenshot, WebP, visual QA, taste receptors, typography, UI review, asset sheet, editor viewport, anti-slop
Session primitive for html-skills: starts the per-session local receiver and `Monitor` so submissions from html-skills artifacts arrive as session notifications instead of copy-paste. Every html-skills content skill invokes it from its pre-flight block before writing an artifact; idempotent. Returns the localhost URL to inject as `window.__CLAUDE_SUBMIT_URL__`. Don't invoke outside that flow.
Write-side memory: stores decisions, patterns, and outcomes in the MCP memory knowledge graph as entities with typed observations and relations. Use when something worth persisting across sessions was just learned or decided. To search or read existing memory, invoke memory; to debug retrieval internals, memory-fabric; to consolidate, dream.
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, update or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
Skill security auditing tool. Verifies the security of Claude Code skills by checking for malicious code, sensitive information leaks, dangerous operations, and more. Conducts a security assessment and generates a security report before installing or using new skills.
Meta-router for the tmux-agent-tools plugin. Invoke BEFORE choosing a wrapper or delegating any tmux-agent work — it decides inline vs worker, picks the right script, and points to the canonical capability table. Invoke it even if there is only a 1% chance it applies.
Rules for writing code that coding agents (and humans) can find and understand through plain-text search. Apply whenever writing or renaming code: functions, types, constants, files, error messages, doc comments. Grounded in measurement: agents navigate by plain-text search, not by AST or language server, so every identifier is a search query and every search miss costs wasted reads
Access 50+ LLM models through AceDataCloud's unified chat APIs. Use when you need native Claude Messages, native Gemini audio analysis, OpenAI-compatible chat/responses calls, text embeddings for search or RAG, or stateful conversations and scheduled agent tasks across GPT, Claude, Gemini, Grok, Kimi, GLM, and DeepSeek models. Supports streaming, multimodal input, and tool calling.
Coordinates a large batch of GitHub issues through separate Codex worker threads, tested pull requests, review loops, and gated merges. Use when the user asks one Codex thread to manage several coding sessions or complete a parent issue, milestone, or issue batch
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.