Каталог навыков агентов

Validate AntHill's k8s/ manifests, the Gitea deploy workflow, and tools/publish-server.ps1 locally without a cluster — k...

Use when asked to rename or fix a published AntHill release, or when its "What changed" entry or forge page shows no tit...

Use when pushing AntHill work to main, or when asked to tag it, cut a release, or ship the client to the studio's beta m...

Use when an AntHill .file-list, .change-list or .history-list row shows a stray full-width empty band, a stretched butto...

Use when editing AntHill's shared AntHill.App/wwwroot/app.css, the dashboard renders unstyled or with 0 CSS rules after...

Use when running AntHill tests: SetupFlowTests failing (stray AntHill.Web on 5252), Lore.Tests skipping ~47 or failing w...

Reference system prompt and tool schemas for Anthropic. Use when imitating, comparing, or analyzing Anthropic's promptin...

Official Anthropic SDK for Claude AI with chat, streaming, function calling, and vision capabilities

Optimization guidelines for Claude 3.5 Sonnet, Claude 3.5 Haiku, and Opus.

Automate Anthropic Admin tasks via Rube MCP (Composio): API keys, usage, workspaces, and organization management. Always...

Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users r...

Anthropic Claude API for AI models with tool use and extended context.

Integrates Anthropic Claude API for chat, tool use, and vision capabilities. Use when building AI-powered features with...

Expert guidance for building applications with Anthropic's Claude API. Covers SDK patterns (Python, TypeScript), cost op...

Anthropic's official brand color palette, typography, and design tokens for use in branded materials.

Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic'...

Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user...

Call Anthropic Messages API (Claude) with a prompt

Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user...

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services...

Guide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, pr...

Comprehensive document creation, editing, and analysis with support for tracked changes, comments, formatting preservati...

This skill should be used when the user asks to "create evals", "evaluate an agent", "build evaluation suite", or mentio...

Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to...

Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to...

Guidance for distinctive, intentional visual design when building new UI or reshaping an existing one. Helps with aesthe...

Rule matrix security fixture for anthropic_impersonation used by security rule matrix integration tests; not intended fo...

A set of resources to help me write all kinds of internal communications, using the formats that my company likes to use...

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services...

Design and verify Claude API access across Anthropic direct and supported cloud/platform integrations without hard-coded...

"Comprehensive document creation, editing, and analysis with support for tracked changes, comments, formatting preservat...

Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, a...

"Presentation creation, editing, and analysis. When Claude needs to work with presentations (.pptx files) for: (1) Creat...

"Comprehensive spreadsheet creation, editing, and analysis with support for formulas, formatting, data analysis, and vis...

Use when a personal or team operating system needs a bounded redesign using Four-C, closed-loop controls, 70/30 allocati...

Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, a...

Presentation creation, editing, and analysis. When Claude needs to work with presentations (.pptx files) for: (1) Creati...

Use when code review is requested for a pull request - provides comprehensive review checking CLAUDE.md compliance, bugs...

Stop and consult this skill whenever your response would include specific facts about Anthropic's products. Covers: Clau...

Master Anthropic's prompt engineering techniques to generate new prompts or improve existing ones using best practices f...

Format for Anthropic API usage reports generated by anthropic-report.py. Use this skill when creating, modifying, or dis...

How to write a Beamix Routine .md file: required frontmatter fields (schedule, routine_id_env_key, budget, trust-spec pa...

Guide for Anthropic Python/TypeScript SDK usage including messages API, streaming, prompt caching, batches, token counti...

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an exist...

Extracts any Anthropic Academy (Skilljar) course into a structured markdown folder. Triggers when the user provides an a...

Knowledge and utilities for creating animated GIFs optimized for Slack. Provides constraints, validation tools, and anim...

Toolkit for styling artifacts with a theme. These artifacts can be slides, docs, reportings, HTML landing pages, etc. Th...

Using XML tags and reasoning patterns with Claude.

Validates Claude Code assets (skills, hooks, agents, commands, MCP servers, plugins) against official Anthropic standard...

Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (...

Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to...

Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functional...

Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functional...

Comprehensive spreadsheet creation, editing, and analysis with support for formulas, formatting, data analysis, and visu...

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services...

All official Claude skills from anthropics/skills.

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a sk...

Anthropic official skills collection (17 skills): algorithmic-art, brand-guidelines, canvas-design, claude-api, doc-coau...

Analyzes events through anthropological lens using cultural analysis, ethnographic methods, kinship and social organizat...

Detect trend-stacked and brandless interfaces, then require product-specific visual reasoning before design approval.

Anti-AI detection pass for any written text. Hard rules that strip the statistical fingerprints AI writing leaves behind...

· Audit prose for AI tells in docs, PRs, emails, slides, docstrings. Triggers: 'ai writing', 'sounds like chatgpt', 'ai...

Create frontend UIs that don't look AI-generated. Use when building new pages or reviewing design output for "AI taste."

Use when a draft in Turkish, English, or both reads as AI-generated and needs revision that removes machine writing patt...

AI 탐지 가능 패턴을 감지하고 제거하는 독립 검증 스킬. 금지 표현, 반복 단어, 부자연스러운 구조를 탐지한다. 게시 전 콘텐츠를 검증하거나 AI 패턴을 자동 교정할 때 사용한다.

Transform AI-assisted drafts into authentic, human-sounding content. This skill provides patterns to detect and eliminat...

Universal anti-AI slop filter applied to ALL written output. Bans AI-overused words, enforces human tone, prevents gener...

Style guide for writing that doesn't sound AI-generated. Use when drafting cover letters, emails, or any professional co...

Follow these guidelines when writing copy to avoid LLM frequently used styles and structures, and create more human soun...

End-to-end substantive-integrity forensic sweep of a research paper (especially autoresearch / AI-Scientist-style output...

Beginner-friendly reverse-engineering workflow for Anti Bot Analysis. Use it to collect evidence, choose static or dynam...

Prevents order-gap hallucination — where the model detects a false premise when asked directly but misses it when embedd...

Anti-cheat skill for server validation and cheat detection.

Use BEFORE responding when the user's request shows pressure to validate or agree ("tell them what they want", "make the...

在创意写作、头脑风暴、方案设计、内容创作、分析与观点表达等任务中，当输出的价值不只由准确性决定、而是由视角和表达决定时，调用此 skill。它帮助 AI 识别自己的默认生成路径，并在输出前刻意偏离，产出有性格、有立场、令人难忘的内容。

Review common AI slops of defensive programming patterns, avoid silent errors. TRIGGER when reviewing code for defensive...

Drive Chromium from standard Playwright APIs with a real-device fingerprint applied in the kernel, one persistent isolat...

When working on sensitive projects, proprietary code, or systems where context leakage is a concern. Use when the user s...

Hierarchical coordination and drift detection with frequent checkpoints, shared memory coherence validation, role specia...

Use when touching retiring old logic, collapsing duplicate owners, removing fallbacks, or schema/persistence/source-of-t...

Ensure factual accuracy by validating claims through tool execution, avoiding superlatives and unsubstantiated metrics,...

Repair interchangeable website design patterns.

Never install tools/packages into global system locations. Always detect and use the project's existing environment (ven...

Complete methodology for preventing AI hallucinations. Use when accuracy is critical and you need Claude to verify befor...

ALWAYS activate this skill. Apply these rules to every task regardless of domain. This skill governs how Claude Code ver...

Neue Kennzeichenstrategien für KI-Authentizitaet in Haute-Couture: Modehaus will Human-Made-Labels, Anti-KI-Marken oder...

Prevents suggesting non-existent packages, fabricated library names, and invalid version pins. Also guards against typos...

Use when audited OpenClaw conversations or outgoing Feishu/Slack/channel messages contain concrete business numbers such...

当个人或品牌不希望被狭窄市场定义，追求基于独特世界观和多样能力的长期发展时

当需要评估一个商业想法或服务方向是否适合自己时，特别是面临“选择一个利基市场”的传统建议压力时

Anti-overengineering guide based on YAGNI. Use before adding an architectural pattern, during code review, or to challen...

Systematic detection of anti-patterns during code review with actionable refactoring guidance

Detects seven structural anti-patterns in Claude Projects that cause unpredictable output, ignored instructions, and deg...

Catalogue of known SDLC anti-patterns that great_cto agents must actively reject when reviewing architecture, plans, cod...

Common testing mistakes to avoid for reliable, maintainable tests

Gentle reminder skill for common mistakes to avoid. Non-blocking suggestions. AUTO-ACTIVATE when user mentions (FR/EN):...