Каталог навыков агентов

Strukturierte KI-Risikobewertung pro KI-System – Identifikation, Risikoklassifizierung (KI-VO-Trigger + interner Risk-Sc...

Gestaltung und Prüfung von Verträgen über KI-Systeme: Leistungsbeschreibung und Gewährleistung (§ 434, § 633, § 327 BGB)...

KI-VO Betreiber-Pflichten für Kanzleien erlaeutern und umsetzen: Anwendungsfall Kanzlei als Betreiber von KI-Diensten mu...

Session 开场：读 HANDOFF/MEMORY/current-focus 并用 git 实际状态核验，输出「我在哪 / 上次遗留 / 建议下一步」。新开 session 或 /clear 之后的第一件事。

Deliberative consultation with Kimi API. Ask, evaluate, critique, iterate until workable agreement.

Kimi K2.5 setup and usage patterns. Most capable subagent with 256K context and built-in vision. Use for complex reasoni...

Token-efficient multi-agent orchestration. Claude spawns Kimi for research + MiniMax for review. 85-93% token savings on...

Prüfung und Berechnung des Kindesunterhalts – Verwandtenunterhalt §§ 1601 ff. BGB, gesteigerte Erwerbsobliegenheit und S...

把主题确定性推进为短视频成片的通用工作流与集群流程真源。用户要文案、分镜、提示词、生图、配音、字幕、动态化和合成，或未指定专门画风时使用；支持 16:9、9:16、1:1 与 kenburns、dubbed、native 三种渲染模式。

把一段实拍视频的人物运动复刻到本项目的角色身上。用户提到照着这段视频动、复刻动作、翻跳同一支舞、让我的角色跳这个、把实拍运动迁移到 AI 片段，或手上有参考视频想让角色照做时使用；引擎在本机把源片处理成人物深度与骨骼的控制视频，绑到分镜后作...

Robot kinematics and dynamics computation including forward/inverse kinematics and dynamics

K-Scale kinfer model inference engine for deploying trained RL policies to real robots via ONNX Runtime in Rust

Reference system prompt and tool schemas for Kiro. Use when imitating, comparing, or analyzing Kiro's prompting style; d...

Quick spec generation with interactive or automatic mode

(ePost) Use when user says "create an agent", "add a skill", "write a hook", "optimize a skill", or "kit authoring" — en...

(ePost) This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent fr...

(ePost) Use when creating, modifying, or auditing agents, skills, commands, hooks, or planning kit ecosystem changes

Build ClaudeKit Marketing components - skills, agents, commands, workflows. Use when creating new automation, extending...

Post-compaction/resume recovery for the guardrails kit — re-run the SESSION.md S1 sequence manually. Use after a compact...

(ePost) This skill should be used when the user wants to "create a skill", "add a skill to plugin", "write a new skill",...

Create or refresh docs/STATE.md before pausing, stopping, compaction, or handoff — guardrails session state. Use when as...

Create optimized prompts for agent-to-agent pipelines with research, planning, and execution stages. Use when building p...

Expert guidance for creating Claude Code slash commands. Use when working with slash commands, creating custom commands,...

Turn three or four key frames into a 30-second action montage with Kling 4 (kling_v4): a breakdance battle, BMX or skate...

Make a cinematic short film, music video or story video with Kling 4 the way it works best: beat sheet, a cast and look...

How to prompt Kling 4 (Kling 4.0, kling_v4) for cinematic AI video that does not look like AI slop: let a strong image m...

生成符合 Kling 3.0（可灵 3.0，快手）规则的视频提示词。三种写法自适应：4 部分基础公式（短视频）/ 5 层进阶公式（剧情+音频）/ 图生视频专用（只描述运动）。Kling 是 2026 年中文理解最强、原生音画同步、最长 2...

Full-featured Kling 3.0 Omni video generation skill. Covers text-to-video, image-to-video, video editing (base mode), vi...

Generate AI videos with Kuaishou Kling via AceDataCloud API. Use when creating videos from text or images, extending exi...

Build explore Kling AI models and their capabilities for video generation. Use when selecting models or understanding fe...

把主题或故事制作成赛博朋克短片。用户提到雨夜霓虹都市、未来世界、黑客叙事、AI 觉醒、都市怪谈或废土科幻时使用；默认写实 CG，可按明确意图切换 2D 赛博动画。

把故事或主题制作成游戏画面叙事视频。用户提到 HD-2D、GBA、SNES、像素 RPG、实况 HUD、PS1 低模、体素、等距 CRPG、卡通渲染、视觉小说或街机格斗时使用；负责选择十一种游戏 profile 与叙事机制。

制作素材复用型解说短片。用户要产品讲解、功能演示、方案宣讲、房产汽车数码展示、PPT 式视频或用少量图片讲清内容时使用；以 explainer 为默认 profile，资产跨分镜复用降低生图成本。

Display knowledge base status and recent learnings

Query knowledge artifacts across all locations. Triggers: "find learnings", "search patterns", "query knowledge", "what...

Activate mature .agents knowledge.

Build and query AI-powered knowledge bases from claude-mem observations. Use when users want to create focused "brains"...

Design knowledge systems using ontological principles—organizing by what things ARE rather than arbitrary hierarchies. U...

Delegates knowledge bank lookups to Explore subagents with reflections-first strategy that learns from past mistakes. Ch...

Ground answers in the project's ingested docs via the search_knowledge tool.

Query memory graph, vault-rag, and Obsidian KB docs to find existing knowledge before investigating

Build a searchable knowledge base from external sources -- URLs, documents, transcripts, PDFs. Uses the existing MemoryI...

Use when recording ADRs, saving debug findings, persisting patterns, or referencing past decisions in docs/

Create, organize, audit, or maintain a durable Markdown knowledge base with an index, atomic notes, stable identifiers,...

Build and maintain AI-accessible knowledge bases for projects

Create and manage a layered knowledge base with hot/cold/warm cache tiers. Provides component-based architecture with Wo...

智能管理和整理本地知识库文档。扫描、分析、整合由conversation-knowledge-extractor生成的知识库文件，生成结构化索引、专题整理报告、进步追踪分析。支持增量/全量整理，按日期范围筛选。重点处理学术写作和学术探讨内容...

Use this skill whenever you learn something important during a conversation: a key architectural decision, a project-spe...

Updates the system knowledge base with new best practices and constraints.

Use when converting completed work into durable knowledge. This skill provides a systematic process for extracting lesso...

(ePost) Use after completing a task — capture learnings, save patterns, record post-mortems to docs/

This skill should be used when the user asks to audit, health-check, or structurally validate one or more SPECIFIC named...

知识库生成工具。将网站分析结果转化为可复用的 Skill 文档、测试用例、代码模板。支持自动化文档生成和知识提取。

Manages persistent Knowledge Graph for specifications. Caches agent discoveries and codebase analysis to remember findin...

Knowledge graph integration for token-efficient codebase understanding. Uses codebase-memory MCP for AST indexing, depen...

Process external resources into stored knowledge with quality evaluation, curation routing, and application decisions.

智能知识管理助手,自动分析和优化知识库结构。

Use when an Obsidian knowledge system needs classification, deduplication, retrieval, synchronization, debt queues, or g...

Patterns for learning from corrections, capturing instincts, extracting stable patterns, and building cross-session know...

Use before starting any new work to check for existing knowledge. This skill provides a systematic search and retrieval...

(ePost) Use when you need prior art, past decisions, or existing patterns — checks docs/, skills, and RAG before externa...

Route end-to-end personal knowledge-base work across setup, intake, organization, growth, projects, self-observation, re...

Run an iterative audit-and-fix loop on Thai prose using the kien-thai skill — repeats audit/fix passes until a full pass...

Talk to Koerner Office King Of Hustle about their expertise. Koerner Office King Of Hustle provides authentic advice usi...

Kolmogorov complexity as the ultimate intelligence measure. Shortest

KOMODO v1.0 — Momentum Event Consensus. Uses leaderboard_get_momentum_events (real-time threshold crossings) to detect w...

Council — 5 independent AI perspectives + mutual critique + synthesis (adapted from karpathy/llm-council for Claude Code...

The workspace's Drive under `/drives`: the user's own folder (their desktop, also at `~/Desktop`) and any other folder `...

How to read, write, and curate workspace memory in `memory/` — the workspace brain. Load this skill whenever you (or a s...

How to read, write, and curate project memory in `memory/` — the project brain. Load this skill whenever you (or the har...

Orchestrates knowledge pack content generation pipeline: batch scheduling, completion tracking, cross-pack dependency or...

한국 특허 종속항·시스템항·프로그램항·추가 독립항(청구항 2~N) 작성 스킬. 논문(또는 발명 자료)과 확정된 청구항 1을 입력받아 KIPO 청구범위 작성 실무에 정통한 변리사 관점으로 청구항 2번부터 N번까지를 작...

한국 특허 명세서 본문 작성. 청구항 초안 및 발명 자료를 입력받아 한국 특허청(KIPO) 출원 표준 구조에 따른 명세서 본문을 S1~S7 단계로 작성. 금지 표현("종래", "구성되는") 회피, 효과 3단 인과(구...

Taxonomic classification of metagenomic reads using Kraken2. Fast k-mer based classification against RefSeq database. Us...

This skill should be used when the user asks to "update AGENTS.md", "add to AGENTS.md", "maintain agent docs", or needs...

Marktmissbrauch bei Kryptowerten – Geltungsbereich der Vorschriften über Marktmissbrauch Art. 86 VO (EU) 2023/1114, Begr...

RL training library for humanoid locomotion and manipulation built on MuJoCo and JAX. Provides PPO, AMP, and custom task...

Rechtliche Vollprüfung einer ordentlichen oder außerordentlichen Kündigung im deutschen Arbeitsrecht – KSchG (allgemeine...

A package manager for AI knowledge. Meta-skill for on-demand skill discovery and installation — search curated local rep...

Generate accessibility alt text for an image with a local vision LLM. Wraps kuzco's tool_llm_image_alt_text() ellmer too...

Classify an image and describe its contents with a local vision LLM. Wraps kuzco's tool_llm_image_classification() ellme...

Run a custom computer-vision prompt against an image with a local vision LLM. Wraps kuzco's tool_llm_image_custom() ellm...

Extract text visible in an image (OCR) with a local vision LLM. Wraps kuzco's tool_llm_image_extract_text() ellmer tool....

Recognize and locate instances of an object in an image with a local vision LLM. Wraps kuzco's tool_llm_image_recognitio...

Analyze the sentiment or mood conveyed by an image with a local vision LLM. Wraps kuzco's tool_llm_image_sentiment() ell...

Syncs Claude Skills with other AI coding tools like Cursor, Copilot, and Codeium by creating cross-references and shared...

L0 regularization for neural network sparsification and intelligent sampling - used in survey calibration

Use when the agent needs to control who can submit transactions on an Avalanche L1 (write access) via the Transaction Al...

Final retrospective and self-assessment for participants of Claude Code Lab. Runs four sequential interactive parts — pr...

Internal runtime support for universal skills that validate, render, and discover authoring guidance from label-registry...

Comprehensive guide for Label Studio setup and usage on local server for data labeling and annotation.

Detect what the system actually does by reading the code, and map the security-relevant findings (login, uploads, paymen...

Apply the defense plan's fixes to the code, safely and one at a time, then record what was applied and what is left. Rea...

Prove each applied control holds by confronting the hardening record with the code, writing each verdict back into that...

On-demand GPU cloud instances for ML training.

Reserved and on-demand GPU cloud instances for ML training and inference. Use when you need dedicated GPU instances with...