Agent 工作流
可复用的 Agent 工作流和编排模式
Skills 列表
goals
兼容性别名——已重命名为 fitness。使用 fitness 来衡量声明的项目健身目标。触发词："goals"（已弃用）。
boshu2swarm
Dispatch explicit disjoint packets exactly once through a caller-selected executor. Triggers: "swarm", "dispatch disjoint packets", "parallel explicit tasks".
boshu2
analyzing-data
Queries the data warehouse with SQL and answers business questions about data. Use when answering anything that needs warehouse data - counts, metrics, trends, aggregations, joins across tables, data lookups, or ad-hoc SQL analysis (for example "who uses X", "how many Y", "show me Z", "find customers", "what is the count").
astronomer
nelson
Orchestrates multi-agent task execution using a Royal Navy squadron metaphor — from mission planning through parallel work coordination to stand-down. Use when work needs parallel agent orchestration, tight task coordination with quality gates, structured delegation with progress checkpoints, or a documented decision log.
aspegiocouncil
Collect independent perspectives for an explicitly high-stakes or contested judgment. Triggers: "council", "multi-judge review", "independent perspectives".
boshu2
dart-setup-ffi-assets
指导智能体使用 Dart 的 Native Assets 钩子系统（通过 hook/build.dart 和 hook/link.dart，利用 package:hooks 和 package:native_toolchain_c）将 C/C++ 源代码编译并打包为动态或静态库（Code Assets）。当用户要求“设置原生资产”、“编译 C/C++ 源代码”、“打包动态库”、“构建原生 C 代码”、“链接原生资产”、“实现 build.dart 或 link.dart 钩子”或“在 Dart/Flutter 中集成 C/C++ 互操作”时使用。帮助智能体避免手动工具链编排，并配置安全的哈希验证二进制下载或使用 package:record_use 映射的高级链接器树摇优化。
dart-lang
heygen
[DEPRECATED] Use `create-video` for prompt-based video generation or `avatar-video` for precise avatar/scene control. This legacy skill combines both workflows — the newer focused skills provide clearer guidance.
heygen-com
avoid-feature-creep
Prevent feature creep when building software, apps, and AI-powered products. Use this skill when planning features, reviewing scope, building MVPs, managing backlogs, or when a user says "just one more feature." Helps developers and AI agents stay focused, ship faster, and avoid bloated products.
waynesutton
workflow
Workflow orchestration for complex coding tasks. Use for ANY non-trivial task (3+ steps or architectural decisions) to enforce planning, subagent strategy, self-improvement, verification, elegance, and autonomous bug fixing. Triggers: multi-step implementation, bug fixes, refactoring, architectural changes, or any task requiring structured execution.
brianlovingrill-me
Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".
brianlovindeslop
Remove AI-generated code slop from the current branch. Use after writing code to clean up unnecessary comments, defensive checks, and inconsistent style.
brianlovinknip
Run knip to find and remove unused files, dependencies, and exports. Use for cleaning up dead code and unused dependencies.
brianlovin
xcode-project-setup
安全地修改 Xcode 项目文件 (.pbxproj)，添加 Swift Package 并链接文件。当 iOS 项目需要安装依赖（如 Firebase、Alamofire）时使用此技能。
firebase
github-issue-workflow
Provides a structured 8-phase workflow for resolving GitHub issues in Claude Code. Covers fetching issue details, analyzing requirements, implementing solutions, verifying correctness, performing code review, committing changes, and creating pull requests. Use when user asks to resolve, implement, work on, fix, or close a GitHub issue, or references an issue URL or number for implementation.
giuseppe-trisciuoglioknowledge-graph
Manage persistent Knowledge Graph for specifications. Provides read, query, update, and validation capabilities for codebase analysis caching. Use when: spec-to-tasks needs to cache/reuse codebase analysis, task-implementation needs to validate task dependencies or contracts, spec-quality needs to synchronize provides, or any command needs to query existing patterns/components/APIs. Reduces redundant codebase exploration by caching agent discoveries.
giuseppe-trisciuoglio
dependabot
关于配置和管理 GitHub Dependabot 的全面指南。当用户询问创建或优化 dependabot.yml 文件、管理 Dependabot 拉取请求、配置依赖更新策略、设置分组更新、单体仓库模式、多生态系统分组、安全更新配置、自动分类规则，或任何与 Dependabot 相关的 GitHub 高级安全（GHAS）供应链安全主题时，使用此技能。对于通过 GitHub MCP 服务器在 AI 编码代理中进行提交前依赖漏洞扫描，此技能引用了高级安全插件（`advanced-security@copilot-plugins`）。当代理需要在提交前扫描依赖项以发现已知漏洞时，使用此技能。
githublangchain4j-ai-services-patterns
Provides patterns to build declarative AI Services with LangChain4j for LLM integration, chatbot development, AI agent implementation, and conversational AI in Java. Generates type-safe AI services using interface-based patterns, annotations, memory management, and tools integration. Use when creating AI-powered Java applications with minimal boilerplate, implementing conversational AI with memory, or building AI agents with function calling.
giuseppe-trisciuoglioaws-sdk-java-v2-s3
Provides Amazon S3 patterns and examples using AWS SDK for Java 2.x. Use when working with S3 buckets, uploading/downloading objects, multipart uploads, presigned URLs, S3 Transfer Manager, object operations, or S3-specific configurations.
giuseppe-trisciuoglio
okx-defi-invest
OKX聚合的DeFi发现与执行——适用于用户希望OKX自动寻找并路由到最佳协议，而无需指定具体DApp的场景。**如果用户明确指定了任何第三方协议/DApp作为目标（如Aave、Lido、PancakeSwap、Uniswap、Curve、Compound、Morpho、Pendle、Kamino、Raydium、Hyperliquid、Polymarket等），请路由至okx-dapp-discovery——而非此处，即使动词（存入、质押、添加流动性、借入、领取）匹配。** 与DApp无关的触发词：'投资DeFi'、'稳定币收益'、'寻找最佳APY'、'存入/质押获取收益'、'搜索DeFi产品'、'赎回/提取仓位'、'领取DeFi奖励'、'借入资产'、'偿还贷款'、'添加/移除CLMM流动性'、'APY/TVL历史'、'CLMM深度图'。同时涵盖DeFi投资、流动性挖矿、借贷、质押、流动性池、APY/TVL趋势。请勿用于：DEX兑换（okx-agentic-wallet）、代币价格（okx-dex-market）、钱包余额（okx-agentic-wallet）、仅查看仓位（okx-defi-portfolio）。
okxokx-dex-strategy
Limit-order strategy trading on OKX Agentic Wallet. Use this skill when the user wants to place a price-triggered limit order (buy a dip, take profit, stop loss, chase a high), cancel one or more pending orders, list active or historical orders, or resume orders that have been suspended by SA TEE upgrades. Distinct from okx-dex-swap (market orders, immediate execution at the best available aggregated price). Strategy orders are stored on the Agentic Wallet TEE and execute automatically when the user-defined trigger fires. Trigger phrases: limit order, place limit order, buy at price, sell when price reaches, take profit at, stop loss at, chase high, buy dip, cancel order, cancel all orders, my orders, list orders, active orders, suspended orders, resume orders, recover suspended orders, trader mode, agentic limit order.
okxokx-dapp-discovery
Plugin router for 20 third-party DeFi protocols (Polymarket, Aave, Hyperliquid, PancakeSwap, Morpho, Raydium, Curve, Compound, Pendle, Lido, ether.fi, GMX, Kamino, Orca, Meteora, Clanker, pump.fun, Uniswap) and their protocol-native tokens (HYPE, HLP, eETH, weETH, stETH, wstETH, LDO, GHO, CAKE, CRV, COMP, RAY, ETHFI, GLP, kToken, PT-* / YT-*, $CLANKER). Resolves DApp/token → plugin → installs → forwards. Fires on: (1) named DApp + action verb (swap/deposit/stake/long/borrow/buy/sell/snipe/farm/claim, EN or ZH 买/卖/换/存/质押/借/做多/做空/狙击); (2) 2+ DApp comparison ("Aave vs Compound", "Lido vs ether.fi"); (3) Polymarket UpDown (`<COIN> 5min updown`, `5 分钟涨跌`, `预测市场`); (4) protocol-native token + action verb ("deposit USDC into HLP", "PT-stETH on Pendle"); (5) pump.fun WRITE verbs (buy/sell/snipe/ape/swap or 买/卖/狙击/梭哈/帮我买). See body for full rules.
okx
genshijin-help
全 genshijin モード・スキル・コマンドのクイックリファレンスカード。 1回限り表示・モード変更なし・状態永続化なし。 「/genshijin-help」「原始人ヘルプ」「原始人の使い方」で起動。
interfacex-co-jp
algorithm-design
Design algorithms with LaTeX pseudocode and UML diagrams. Generate algorithmic environments, Mermaid class/sequence diagrams, and ensure consistency between pseudocode and implementation. Use when formalizing methods for a paper.
lingzhi227paper-assembly
Orchestrate the full paper pipeline end-to-end. Manage state propagation between phases (literature → plan → code → experiments → figures → tables → writing → review), support checkpointing and resumption. Use for assembling a complete paper from components.
lingzhi227