Skills
97,725 packaged capabilities and playbooks for agents. Install any of them with one command.
Agent workflows
Runs continuous AI iteration loops that repeat build-test-fix cycles until success criteria are met. Use when building features requiring test-driven refinement, implementing tasks with clear pass/fail criteria, or automating iterative improvement workflows.
AI-powered browser automation SDK for web scraping, testing, and workflow automation. Use when automating web browsers, extracting data from websites, testing web applications, or building web automation workflows. Supports both API key and AWS credential authentication.
Agent onboarding automation for AIBTC first-hour setup. Use when a new or existing agent needs a structured bootstrap flow: wallet readiness, AIBTC registration check, heartbeat health checks/check-in, safe skill-pack installs, and a one-command doctor summary with next actions.
Executes a complete 7-stage deep research process. Accepts structured research tasks, automatically deploys multiple parallel research agents, and generates a comprehensive research report with full citations. Use this skill when the user has a structured research prompt.
Место роли и обмен делателей. Стояние: «встань на канал», «открой сокет», «меня не слышно», undelivered, hold the socket, «записи уходят без автора», «кадр срезан», перевзвод сторожа, «уйди с места», revoke. Обмен: «это не моя зона», «спроси у второго агента», ask another agent, «слово в дело», escalate to the owner, «кто этим владеет», «сведи их», «не пилите одно и то же». Обычно место берёт iskron_stand на старте двери; сюда — без тула, при отказе, починке, уходе, и за тем, кому и чем говорить: слово в деле, строка, вимарша. Нужны iskron_*.
Write English that a reader cannot misread: one meaning per word, active voice, simple tenses, one idea per sentence, short sentences. Based on ASD-STE100 (Simplified Technical English), the controlled-language standard written for aircraft maintenance manuals. Use it for any prose an agent produces that someone else acts on. That covers reports and findings, PR descriptions and commit messages, instructions handed to another agent, tool descriptions, error messages, status summaries, and prompts. Also use it on request, with triggers like "simplify this", "make this readable", "too dense", "rewrite in STE", "simplified technical english", "ASD-STE100".
Build AI agents and automate Claude Code programmatically via the Claude Agent SDK and headless CLI mode. Covers Python SDK, claude -p, SDK MCP servers, hooks, sessions. Triggers on: "build an agent", "agent SDK", "headless mode", "automate Claude", "programmatic agent".
Canonical guide to authoring Claude Code agent frontmatter and system prompts. PROACTIVELY activate for: (1) creating a new agent, (2) adding an agent to a plugin, (3) writing agent frontmatter, (4) designing a system prompt, (5) configuring <example> trigger blocks, (6) restricting tools, (7) setting model inherit, (8) migrating deprecated agent true flag, (9) fixing "agent never triggers", (10) ensuring skills have agent trigger coverage. Provides: agent templates, lean-orchestrator pattern, and validation checklist.
Design, review, and debug agent workflows, and decide when a request should use a prompt, instruction, skill, agent, or hook before escalating to multi-agent design. Use for .agent.md / .instructions.md / .prompt.md / AGENTS.md work, workflow architecture, orchestration planning, scheduled automation model allocation, or when agent workflows may be overkill. Triggers on 'agent workflow', 'create agent', 'automation models', 'ワークフロー設計', 'orchestrator'.
Use for any task requiring a real browser: viewing web pages, accessing login-gated sites, operating web UIs, scraping social media (Xiaohongshu/Weibo/Twitter/X, etc.), reading JS-rendered or dynamic pages, bypassing bot detection, form filling, e2e checks, and general web automation. Prefer this over WebFetch whenever the page needs JS execution, authenticated session, interaction, or stealth. Invoke via terminal CLI (`bridgic-browser ...`) or Python SDK (`from bridgic.browser.session import Browser`, `from bridgic.browser.tools import BrowserToolSetBuilder`). Also covers accessibility snapshot refs, CLI-SDK mapping/migration, and generating SDK code from CLI action steps.
Ultra-compressed communication mode. Distills AI output to its core — ~65% fewer tokens while keeping full technical accuracy. Use when user says "caveman", "terse", "kurz", "kurz&knapp", "kurz bitte", "less tokens", "weniger text", or invokes /caveman-distillate.
Audit the Claude Code ecosystem — skill health and staleness, project activity pulse, CLAUDE.md instruction drift, Mac Mini service status. Use this skill whenever the user asks about ecosystem health, stale skills, abandoned projects, system status, infrastructure check, "what's broken", "what's stale", "how's my setup", or any request to review the state of their Claude Code environment. Also triggers on "/ecosystem", "audit my ecosystem", "ecosystem health", "ecosystem audit".
Use this skill BEFORE drafting any agentic primitive module (skill, persona scoping file, scope-attached rule file, orchestrator workflow) or when refactoring an existing one. Activate whenever the task asks to design, restructure, or critique an agentic module across any agent harness (Claude Code, Copilot, Cursor, OpenCode, Codex), or when the task asks to make a workflow cost-effective, route model calls by capability, design for cache discipline, prune token spend, or pick a model class. This skill drives an 8-step disciplined design process whose output is mermaid diagrams + an interface sketch + a persisted plan (including a cost projection) that the calling thread (or a coder persona it loads) then turns into natural-language modules. Do not skip to natural-language drafting before the design artifacts exist.
Inspect bundled agent skills and install, list, or update bundled and curated remote skills for GitLab CLI. Use when printing a bundled skill file, installing agent skills, checking the skill catalog, updating installed skills, or installing the remote Orbit wrapper skill. Triggers on skills, agent skills, glab skills, skill get, skill install, skill update, skill bundles
Use when the user wants to learn Godot while building — teaching mode that explains the concept, the editor setup, and what to verify, instead of just delivering code. Triggers on "teach me", "explain as we go", "I'm learning Godot", "guide me", "walk me through", "help me understand".
Test a learner on a single Claude Code tutorial lesson (01-10) with 10 questions, scoring answers and flagging weak spots. Use before, during, or after a lesson. Don't use for whole-tutorial assessment or explaining a topic instead of testing it.
Methodology for starting a new library-reference distillation skill — one that turns an external library (nuqs, zod, framer-motion, msw, react-hook-form, emilkowal-animations) into an idiomatic-usage rule pack — or evolving one against a new upstream release. Distills the conventions empirically shared across shipped library-ref skills in this repo — the source-priority ladder (docs → blog/changelog → issues → types → examples), version pinning that inverts with API velocity, the universal 4-tier category ladder (CRITICAL setup → HIGH isolation → MEDIUM composition → LOW edge cases), the 4-slot When-to-Apply template, the failure-gap exemplar heuristic (privilege production lessons over API restatement), and metadata.references[] as cite-set checksum. Triggers on "I want to write a skill for library X", "refresh against new upstream", "where should I source rules from", "what categories should this skill have", and on /dev-skill:new for a library-reference distillation.
Evaluate MCP (Model Context Protocol) servers and tools end to end — deploy from a GitHub URL or npm package, test protocol communication and tool calls, run AI-generated smart tests, and score repository sustainability and popularity. Use this skill whenever the user wants to test, evaluate, audit, score, or vet an MCP server, MCP tool, or MCP package, or asks "does this MCP work" or "is this MCP any good", even if they only paste a GitHub URL or a package name.
Pincaimao platform basic capabilities. Use when calling any Pincaimao platform API — file upload, presigned URL, conversation list, message history, audio-to-text, resume JSON upload, or the base chat-messages interface. Reference this skill before building any PCM agent skill.
Unified project scaffolder that works across all platforms. Scaffold .agent folders, backend (NestJS), frontend (NextJS), mobile (Expo), and browser extensions (Plasmo) with interactive prompts. Supports both monorepo and separate repository structures, and can add components to existing projects.
Break a Roblox game PRD, roadmap, or plan into small independently-playtestable vertical slices instead of building the whole game at once. Use when the user wants to turn a concept or PRD into buildable tickets, split work into slices, plan what to build next, or stop Claude from trying to build an entire game in one pass. Each slice cuts through client, server, remotes, data, and UI for one small player-facing capability, verified with a Studio playtest.
Encodes a continuous improvement loop for goal-seeking agents: EVAL, ANALYZE, RESEARCH (hypothesis + evidence + counter-arguments), IMPROVE, RE-EVAL, DECIDE. Auto-commits improvements (+2% net, no regression >5%) and reverts failures. Works with all 4 SDK implementations. Auto-activates on "improve agent", "self-improving loop", "agent eval loop", "benchmark agents", "run improvement cycle".
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.