Каталог навыков агентов

Train vision models to predict optimal Camelot extraction strategies for PDF tables.

Interactive wizard to create PRD or task lists for /task-batch. Uses /clarify and /ask-questions-if-underspecified for p...

Create an Agent Team with two explorer agents that independently explore a directory, then compare their findings. Use w...

Create complete user-context instruction files using a structured discovery workflow and repository format rules.

Use when creating custom agents for Claude Code, configuring specialized AI assistants, or when the user asks about agen...

Create and validate skills. USE WHEN create skill, new skill, skill structure, canonicalize. SkillSearch('createskill')...

Use when creating or improving Claude Code agents. Expert guidance on agent file structure, frontmatter, persona definit...

Use when creating or publishing Claude Code hooks - covers executable format, event types, JSON I/O, exit codes, securit...

Creates GitHub Copilot custom agents (`.agent.md`) for VS Code. Use when defining a specialized agent role, selecting a...

Create new domain expert with expertise file and workflows. Use when adding new technology or domain area.

Use when creating OpenCode agents - provides markdown format with YAML frontmatter, mode/tools/permission configuration,...

Creates agent orchestration packs: cooperating `.agent.md` files with an orchestrator, subagents, matched handoffs, mini...

Guides creation of effective Agent Skills with proper structure and validation. Use when users want to create a new skil...

How to create new Agent Skills following the open standard. Use when authoring new skills, extending agent capabilities,...

Guide for creating Claude Code skills following Anthropic's official best practices. Use when user wants to create a new...

Use when creating new Claude Code skills or improving existing ones - ensures skills are discoverable, scannable, and ef...

Guide for creating custom Claude Code subagents (Task tool agents). Use when building specialized autonomous agents for...

Use when creating Windsurf rules - provides plain markdown format with NO frontmatter, 12,000 character limit, and singl...

Генерация рекламных изображений через Gemini. Используй для создания креативов с текстом.

Generates Blender Python scripts for infrastructure visualization and ffmpeg commands for video production and social me...

Applies cognitive science frameworks for creative thinking to CS and AI research ideation. Use when seeking genuinely no...

Transform Claude Code into your personal Jarvis - an AI operating system that knows your projects, preferences, and work...

Expert in CrewAI - the leading role-based multi-agent framework used by 60% of Fortune 500 companies. Covers agent desig...

Apply — Expert in CrewAI - the leading role-based multi-agent framework

CrewAI multi-agent orchestration setup for collaborative AI systems

Detect crisis signals in user content using NLP, mental health sentiment analysis, and safe intervention protocols. Impl...

Handle mental health crisis situations in AI coaching safely. Use when implementing crisis detection, safety protocols,...

CRISP session manager — detects project state and routes to the right phase. Use /crisp to start or resume any CRISP eng...

---name: crispr-design-agent

Designs guide RNA (gRNA) sequences for CRISPR-Cas9 editing, including off-target analysis. Use when a user needs to edit...

CRISPResso2 for analyzing CRISPR gene editing outcomes. Quantifies indels, HDR efficiency, and generates comprehensive e...

Independent re-derivation gate for proposed changes during autonomous execution. Evaluates a change (code diff, config e...

Peer-review-style manuscript critique. 6 modes: full (5-reviewer report + editorial decision + revision roadmap), quick...

Runs a panel of blind reviewers on any deliverable (report, deck, workbook, memo, proposal, CV, cover letter, essay), co...

Audit and critique builtin MCP tool implementations in LibrAgent. Use when auditing existing builtin MCP server implemen...

跨境电商运营 (cross-border e-commerce operations) Master OS — automated mastery of cross-border e-commerce operations: top bui...

How to gate a multi-agent kickoff batch before calling it a real vertical slice

bstack P20 — Cross-Model Adversarial Review Gate. The model that wrote the code cannot be the final judge of the code. B...

<!-- Copyright (c) 2026 defconxt. All rights reserved. -->

Use when multi-company coordination, cross-team communication, or inter-company workflow execution is needed. This skill...

Cross Validation Setup - Auto-activating skill for ML Training. Triggers on: cross validation setup, cross validation se...

Generate character reference sheets (nine-grid pose sheets, turnarounds, expression sheets, design sheets, hero portrait...

Generate multi-panel educational comics, science explanatory cartoon strips, infographic storyboards, concept illustrati...

---name: cryoem-ai-drug-design-agent

> Production-tested patterns for building AI agents that autonomously discover,

ML: supervised/unsupervised/RL, CNN/RNN/Transformer, training, evaluation, MLOps, LLM fine-tuning

Read, search and analyze Claude Code session transcripts (the .jsonl under ~/.claude/projects). Use this INSTEAD of grep...

Requirement planning to wave-based CSV execution pipeline. Decomposes requirement into dependency-sorted CSV tasks, comp...

---name: ctdna-dynamics-mrd-agent

Provides AI and machine learning techniques for CTF challenges. Use when attacking ML models, crafting adversarial examp...

Thin PRIMARY for CTF / AWD / 靶场 multi-type orchestration. Hands off to the sidecar CTF-Sandbox-Orchestrator. Use when th...

CTO Platform lifecycle expertise - Play workflow orchestration, intake processing, MCP tools, and agent sequencing. Use...

Use ctx as working memory for prior agent work. Before starting or continuing work in an unfamiliar area, resuming earli...

Use when starting a session on a project, returning after time away, or before making significant changes. Essential for...

Load PRD, FRD, Tech Spec, or RFC into context

The shared context core, phase 1: a read-only shared board for every Claude Code session in a workspace scope. Hooks pub...

Use the ctx7 CLI to fetch library documentation, manage AI coding skills, and configure Context7 MCP. Activate when the...

Diagnose and repair CTXORA local context health and run repository-safe CI checks. Use when indexing is stale, retrieval...

Expert integration with NVIDIA GPU-accelerated math libraries. Configure cuBLAS tensor core operations, generate cuBLAS...

统一入口和智能路由中心，自动识别用户意图并路由到相应技能。基于 Cue 产品设计，提供专业化的深度研究体验。

Adds developer-authored annotations to the gauntlet knowledge base. Use when capturing tribal knowledge or rationale not...

Mine agent work into durable knowledge.

Full curator pipeline for autonomous learning from quality repositories. Executes: discovery → scoring → ranking → inges...

Learn patterns from a specific GitHub repository. Clones, analyzes code structure, extracts patterns, and populates proc...

Curiosity is the engine behind learning, research, and first-principles thinking. Lead with questions, treat surprise as...

Currency analysis, FX rate forecast, carry trade analysis, purchasing power parity, central bank divergence, currency re...

Reference system prompt and tool schemas for Cursor. Use when imitating, comparing, or analyzing Cursor's prompting styl...

Specialized agent for Cursor IDE integration and workflows.

Manage master Cursor AI chat interface for code assistance. Triggers on "cursor chat", "cursor ai chat", "ask cursor", "...

Guides explicit questions about pstack setup, $cursor-poteto-mode, and choosing a skill, playbook or principle; answer w...

Creates Cursor-specific AI subagents with isolated context for complex multi-step workflows. Use when creating subagents...

[AI & Tools] Create, verify, or enhance Claude Code custom agents (.claude/agents/*.md). Triggers on: create agent, new...

This document describes the GitHub custom agent file format used by GitHub Copilot to provide repository-specific or tas...

Generates a complete, customized Non-Disclosure Agreement with plain English annotations, tailored to the specific parti...

Guide for creating custom Claude Code slash commands - shortcuts for frequently-used prompts and workflows. Use when cre...

Manage custom template overrides for vault skills

U.S. customs and trade-law research assistant for HTS classification, CROSS ruling research, CIT/CAFC decision briefing,...

High-performance kernel template libraries and DSLs. Generate CUTLASS GEMM configurations, implement Triton kernel defin...

Select center slices from a 3D volume and zero-pad along depth when the scan has fewer slices than the target count

Applies Mixup augmentation to 3D volumetric images and their segmentation masks, interpolating both inputs and loss targ...

Detect all-black DICOM/MRI slices (mean==0) and replace them by randomly sampling a non-black slice from the same series

Models multiple conditions with a single flat output layer of N_labels × N_classes logits, sliced into per-condition sof...

Apply radiological windowing to HU images — clamp to center/width range for tissue-specific visualization (lung, bone, s...

Use linear assignment problem (LAP/lapjv) on a score matrix to select globally optimal hard-negative pairs for metric le...

Trainable nonlinear distance metric that transforms (v1-v2) and (v1-v2)^2 through a linear layer before computing square...

Computer vision ML pipelines for image classification, object detection, semantic segmentation, and image generation. Ac...

Parameter-efficient Continuous-Variable photonic Quantum Neural Networks for edge AI deployment. Simplified CV-QNN archi...

Use this skill for any question or action about the user's AI/GenAI applications or agents — their behavior, prompts/res...

Use this skill when the user asks about AI Center Coding Agents data, wants to reproduce or extend the Coding Agents das...

Use to design or audit complaint identification and classification in customer support, especially in regulated sectors....

Use to build a defensible cost per contact and cost to serve by driver, channel or customer segment, for automation busi...

Use to staff and schedule QA reviewers for sustainable throughput without grading quality collapsing — fatigue, drift, a...

Use to assess whether support conversations can be used to train, fine-tune or evaluate a model, and to build a filtered...

MUST USE for past-session recall — when a term from prior work is unfamiliar, context feels lost after a compact/restart...

把文章主题、AI/技术概念、Agent 工作流、数据判断编译成「赛博终端示意图」风格生图提示词：纯黑底 + 单一霓虹绿荧光，八族终端原生图面（节点拓扑 / 条形排行 / 时序折线 / 矩阵网格 / 层级堆叠 / 时间轴 / 巨型指标 / 左...