Каталог навыков агентов

Prompt + image gen. 6000+ examples. Dual-option: Standard (Flash) or Creative (Pro). Generate infographics, thumbnails,...

Generate images via Nano Banana with 129 curated prompts. Mandatory validation interview refines style/mood/colors (use...

Generate images via Nano Banana with 129 curated prompts. 3 modes: search (best match), creative (remix), wild (experime...

Create, modify, validate, and analyze Claude Code AI assets (rules, workflows, skills, hooks, CLAUDE.md) with prompt eng...

Build AI assistant application with NLU, dialog management, and integrations

The in-app assistant: scripted scenario engine (default, offline, deterministic), optional LLM via an OpenAI-compatible...

Leveraging AI coding assistants and tools to boost development productivity, while maintaining oversight to ensure quali...

AI-powered issue summarization, auto-labeling, and Q&A using gh-models with 88% effectiveness. Use when analyzing issue...

Evaluate performance fairly when output is AI-assisted — what still measures the human, what now measures the tooling, a...

Review organizational defenses against AI-assisted spearphishing, voice cloning, synthetic identity fraud, deepfake exec...

Use this skill when you need AI-assisted testing workflows such as test data generation, root-cause analysis, and priori...

Comprehensive AI/ML attack surface assessment mapped to MITRE ATLAS v2026.09 with explicit framework gap flags

Audit existing business processes to identify AI automation opportunities. TRIGGERS - Use when user wants to find AI opp...

SOP for auditing AI-generated code. Trigger when: - Reviewing, refactoring, or cleaning up AI-generated code to prevent...

Turn account usage data into a concise AI audit outreach package.

Review an AI system's audit logging for completeness, tamper-resistance, and regulatory readiness — covering what events...

网站诊断助手适合市场营销、运营、software、教育培训在用户提出“网站哪里拖后腿”这类问题，需要快速拆解目标、判断重点并形成可执行结果时使用，帮助基于输入材料生成研究摘要、关键发现、引用/验证清单。

Review DSPy code for correctness and best practices. Use when you want a code review of your DSPy program, need to check...

Use when keeping AI-authored or procedurally-generated content coherent at scale — single voice across a corpus, a machi...

Identify a feasible first business automation from real tasks, examples, volumes, and correction costs. Use for AI autom...

Generate AI avatars from photos or text descriptions using each::sense. Create professional headshots, cartoon avatars,...

视频质量诊断助手适合市场营销、运营、内容媒体、电商在用户提出“这段视频够发布吗”这类问题，需要快速拆解目标、判断重点并形成可执行结果时使用，帮助基于输入材料生成摘要、诊断结论、行动建议和可复用交付物。

Create AI avatar, talking-head, and lip-sync videos on RunComfy via the `runcomfy` CLI. Routes across ByteDance OmniHuma...

Research and create a channel-ready commercial banner for a specific placement such as a website or SaaS hero, YouTube c...

图片生成助手适合内容创作者、市场营销、运营、内容媒体在用户提出“这张图能用吗”这类问题，需要快速拆解目标、判断重点并形成可执行结果时使用，帮助基于输入材料生成视觉/创意诊断、提示词或分镜方案、发布规格检查。

Build a production behavior-tree runtime (Blackboard, action/condition leaves, sequence/selector/parallel composites, de...

Specifies an AI's sentiment, tone, and precision ("temperature") as an explicit design artifact — a Behavioral Document...

Design and verify provider-neutral spend, token, request, and concurrency controls for AI workloads. Use when an applica...

Advanced multi-agent reasoning system for complex questions requiring maximum accuracy. Uses adaptive technique selectio...

Builds production AI bots with Python for support, sales, and custom domains. Use when designing conversation flows, per...

Audit server access logs (logs serveur) for AI crawlers (robots IA) like GPTBot, ClaudeBot, PerplexityBot. Use for AI cr...

Use when claiming the AI bounty on the tDVV mainnet sidechain. This public claim skill now supports Portkey AA/CA only,...

Give Claude a permanent, searchable long-term memory using an Obsidian vault as the store. At the end of a session, summ...

Start and run a listen-first braindump session for tickets, issues, ADRs, worktasks, PR descriptions, requirements, desi...

Use when the user wants to design, architect, or explore a feature before building it. HARD GATE: no implementation unti...

Build comprehensive AI-native brand asset systems that maintain consistency across all AI-generated content. Train AI to...

Analyze a supplied reference video or motion clip and reconstruct it through a mandatory two-stage review by default—fir...

Hybrid fingerprint + LLM pipeline for bug classification, deduplication, and ticket generation. Normalizes CI logs, crea...

Write the build spec for an AI feature — components, prompt files, retrieval pipeline or tool definitions, configuration...

Writes a PRD (Product Requirements Document) as a work order for an AI build agent — problem, vision, core features, sco...

Chain multiple AI steps into one reliable pipeline. Use when your AI task is too complex for one prompt, you need to bre...

Facilitate evidence-based AI product and business learning for non-technical professionals. Use when a user wants to und...

Detect AI-isms in user-facing text

Detect adversary use of AI APIs as covert C2 — SesameOp pattern, PROMPTFLUX/PROMPTSTEAL behavioral signatures, response...

Embedding/vector caching for AI cost optimization

Uses a ready-made, research-based library of 13 AI capability patterns (see ../../references/ai-capability-pattern-libra...

Builds the organization's AI capability map and roadmap from the current state to the target state across three horizons...

Use when the user wants an AI Systems Engineering Signal Radar: researching AI systems engineering trends, AI infrastruc...

Creates a complete onboarding package for department-level AI champions who will drive adoption within their teams. Incl...

Read Simon's latest AI Champions weekly task from

Use AI to merge individual page HTML files into a unified chapter document. Creates continuous document format for impro...

Access 50+ LLM models through a unified OpenAI-compatible API via AceDataCloud. Use when you need chat completions from...

Complete guide to building AI chat applications with Vercel AI SDK. Orchestrates streaming routes, useChat integration,...

Persist AI chat conversations to Neon Postgres with full support for AI SDK message parts including tools, reasoning, an...

Full-featured AI chatbot with Next.js 15, Auth.js, Drizzle ORM, and multi-model support.

"Detect AI/LLM-generated text patterns in research writing. Use when: (1) Reviewing manuscript drafts before submission,...

Use when someone asks "does this sound AI?", "check if this is AI-written", "what gives this away as AI", "run ai-check...

Verify and validate AI output before it reaches users. Use when you need guardrails, output validation, safety checks, c...

Pick the right DSPy module and architecture for your AI feature. Use when you are not sure whether to use Predict, Chain...

Plan AI short films with story, shots, prompts, and continuity.

Scores every passage of a page for AI citability (citabilité, GEO, AEO), maps what ChatGPT can quote as is, rewrites the...

Build a bounded, evidence-first SEO/GEO/AIO editorial wave for any website. Use after a site is production-ready to scan...

After any AI-generated explanation, require the learner to identify one place it could be wrong, one thing to check, and...

Normalize and fix messy data fields using AI. Use when normalizing addresses, standardizing company names, fixing incons...

Use when cleaning up the repository: safe migration to default branch, branch cleanup with merged/stale detection, and r...

Canonical Claude Code authoring kit covering Skills, sub-agents, plugins, slash commands, hooks, memory, settings, sandb...

Diagnose a business's most evidenced go-to-market constraint and recommend the next one to three marketing workflows. Us...

联合营销策划助手适合内容创作者、市场营销、运营、内容媒体在用户提出“合作营销怎么做”这类问题，需要快速拆解目标、判断重点并形成可执行结果时使用，帮助基于输入材料生成转化问题优先级、可复制改稿、实验或跟进行动清单。

Multi-turn conversational AI for intent extraction, clarification, and generation readiness detection. Guides users thro...

Remove AI-generated code slop from branches. Use after AI-assisted coding sessions to clean up defensive bloat, unnecess...

──────────────────────────────────────────────

AI-powered code review with security scanning, performance analysis, and best practices checking. Supports multiple lang...

Review AI-authored code for its characteristic failure modes — plausible-but-wrong logic, hallucinated APIs, over-engine...

Use when an AI coding agent must review a single file or snippet, pull request, branch, commit range, AI-generated diff,...

Expert guide for multi-pass autonomous AI code self-review — syntax validation, logic correctness, architectural conform...

available code reviewers, review prompts and model routing

WHEN: Deep AI-powered code analysis, multi-model code review, security scanning with Codex and GeminiWHAT: Comprehensive...

- constraints: 限制條件（可選）

Generate codemods for large-scale code changes. Use when refactoring patterns across many files.

Autonomous full-stack software architect and security auditor. Writes clean modular services, generates comprehensive un...

Use when developing software with AI coding agents such as Claude Code and Codex — splitting work between an implementer...

Creates coding-agent definitions (review, test, refactor, team) for Claude Code, Codex, and Agent SDK. Use when writing...

Designs plugin systems for coding-agent runtimes and CLIs. Use when adding plugin manifests, extension points, built-in...

Designs session and task state for coding-agent runtimes: resume, checkpoints, compaction, cancellation, background and...

Designs background task systems for coding-agent runtimes. Use when implementing task lists, worker tasks, background ex...

Designs tool runtimes for coding agents. Use when modeling tool registries, deferred loading, permission-aware execution...

Use when an AI coding agent is writing or refactoring production code and its known failure modes need to be held in che...

冷邮件诊断助手适合销售、市场营销、运营、software在用户提出“客户为什么不回我”这类问题，需要快速拆解目标、判断重点并形成可执行结果时使用，帮助基于输入材料生成转化问题优先级、可复制改稿、实验或跟进行动清单。

When the user wants to build an AI-powered outreach system, write cold emails, improve deliverability, or scale personal...

Surface in-task-collaboration protocols when the user describes an AI workflow informally — URL-as-entity-reference, PR-...

把「AI 协作文档体系」（AGENTS.md 入口 + .agents 规则/工作流/技能/决策记忆 + doc 分层文档 + 机器校验闸门）落地的完整方法论与可复制模板。当用户要求为新项目搭建 AI 协作体系、初始化 AGENTS.md...

Design co-learning experiences using the Three Roles Framework (AI as Teacher/Student/Co-Worker). Use when teaching AI-d...

协作校准 / 认知校准 / 问题脑暴：当用户有模糊感受说不清问题、方案越补越复杂、想挑战假设、 想重新定义问题、想知道成熟领域里怎么叫这个问题时使用。 可用中文唤起："帮我想想""先聊一下""一起脑暴""我感觉有问题但不清楚是什么" "先别...

Prevent AI hallucination and ensure evidence-based responses when analyzing code or making suggestions. Use when: analyz...

Cross-AI CLI communication for Kitty terminal. Use when collaborating with other AI assistants (Codex, Gemini, Aider, Cu...