提示词与推理
提示词工程、角色设定和推理模式
Skills 列表
m03-mutability
CRITICAL: Use for mutability issues. Triggers: E0596, E0499, E0502, cannot borrow as mutable, already borrowed as immutable, mut, &mut, interior mutability, Cell, RefCell, Mutex, RwLock, 可变性, 内部可变性, 借用冲突
actionbookm09-domain
CRITICAL: Use for domain modeling. Triggers: domain model, DDD, domain-driven design, entity, value object, aggregate, repository pattern, business rules, validation, invariant, 领域模型, 领域驱动设计, 业务规则
actionbookm12-lifecycle
Use when designing resource lifecycles. Keywords: RAII, Drop, resource lifecycle, connection pool, lazy initialization, connection pool design, resource cleanup patterns, cleanup, scope, OnceCell, Lazy, once_cell, OnceLock, transaction, session management, when is Drop called, cleanup on error, guard pattern, scope guard, 资源生命周期, 连接池, 惰性初始化, 资源清理, RAII 模式
actionbook
eli5
Explain any topic, code, concept, or error tailored to a specific audience's level of understanding. Use this skill whenever the user says 'explain like I am', 'ELI5', 'explain this to my', 'break this down for', 'dumb it down', 'simplify this for', or asks you to explain something to a specific person or audience type (e.g., 'explain this to a manager', 'how would I explain this to my mom', 'make this understandable for a 5th grader'). Also trigger when the user mentions wanting to understand something at a particular level, or asks for an explanation targeting a non-technical audience. Even partial matches like 'explain to my wife' or 'tell my boss' should trigger this skill.
dreambigou
managing-up
Help users master the art of proactive communication and alignment with their managers and founders to unlock autonomy, secure resources, and drive business impact.
refoundaifundraising
Help users navigate the end-to-end lifecycle of funding a startup, from choosing between bootstrapping and VC to closing a Series A or managing a strategic exit.
refoundai
langsmith-online-eval-engineering
Iteratively inspect traces, interview the user, and create LangSmith online evaluators one at a time. Use specifically for creating online evaluators for use within LangSmith -- use "eval-engineering" for Harbor-style online evaluations.
langchain-ai
financekit
使用 FinanceKit 和 FinanceKitUI 获取符合条件的 Wallet 财务数据。适用场景包括：查询交易明细或余额，读取 Apple Card、Apple Cash、Savings 存款账户及英国关联账户数据，请求财务数据授权，使用 TransactionPicker，开启 iOS 26 后台推送，以及保存和检查 Wallet 订单。
dpearson2699
prompt-optimizer
Creates, optimizes, and iteratively refines agent prompts, system prompts, developer prompts, and reusable prompt templates. Use when asked to improve a prompt, optimize a system prompt, rewrite an agent prompt, tune prompt wording, make a prompt more reliable, port prompts between OpenAI, Claude, or Gemini, or build prompt evals.
getsentry
music-caption-rewriter
Turn a brief music description and optional tagged lyrics into a professional MiniMax Music 3 structured caption with Global Metadata, Vocal Details, and a section-aware Arrangement. Use when users ask to enhance a music-generation prompt, preserve lyric-section directives, retrieve a similar style from bundled templates, fuse styles, or produce JSON or JSONL caption output.
minimax-ai
agentforce-observe
Analyze production Agentforce agent behavior using session traces and Data Cloud. TRIGGER when: user queries STDM session data or Data Cloud trace records; investigates production agent failures, regressions, or performance issues; asks about session traces, conversation logs, or agent metrics; wants to reproduce a reported production issue in preview; runs findSessions or trace analysis queries. DO NOT TRIGGER when: user creates, modifies, or debugs .agent files during development (use agentforce-generate); writes or runs test specs (use agentforce-test); uses sf agent preview for local development iteration; deploys or publishes agents.
forcedotcomagentforce-d360-analyze
Data Cloud 360° view of a single Agentforce session. TRIGGER when user asks to trace, inspect, summarize, or describe a specific Agentforce session by session id (Agent Session UUID `019d…` or MessagingSession id `0Mw…`). Also triggers on session discovery — find/list/search sessions by time, agent, channel, outcome, or conversation text — when the user has no session id yet. DO NOT TRIGGER for design-time architecture questions (use agentforce-architecture-analyze instead) or for runtime perf/latency/SLO questions that require platform telemetry beyond Data Cloud.
forcedotcom
kibana-agent-builder
Create and manage Kibana Agent Builder agents and custom tools. Use when asked to create, update, delete, test, or inspect agents or tools in Agent Builder, or when the user wants to understand what agents or tools already exist.
elastic
ucp
当用户想要使用UCP CLI来查找、比较、购买或追踪来自在线商家的产品，或者设置和排查本地UCP配置文件（用于商家范围操作）时使用。涵盖全局目录搜索（“帮我找X，价格低于Y”）、指定商家交易（“从Z.com购买这个”）、订单追踪、`ucp profile init`、`ucp doctor`、购物车、结账、订单以及UCP设置/帮助。当直接协议内结账不可用时，回退到商家托管的交接。
shopify
content-pattern-analyzer-sms
When the user wants to find patterns in what content works and what doesn't. Also use when the user mentions 'what's working,' 'content patterns,' 'best topics,' 'best format,' 'best time to post,' 'analyze my content,' 'do more of,' 'do less of,' or 'what should I change.' For raw metrics, see performance-analyzer-sms. For audience-specific analysis, see audience-growth-tracker-sms. For actionable recommendations, see optimization-advisor-sms.
blacktwist
aws-sdk-java-v2-bedrock
Provides Amazon Bedrock patterns using AWS SDK for Java 2.x. Invokes foundation models (Claude, Llama, Titan), generates text and images, creates embeddings for RAG, streams real-time responses, and configures Spring Boot integration. Use when asking about Bedrock integration, Java SDK for AI models, AWS generative AI, Claude/Llama invocation, embeddings for RAG, or Spring Boot AI setup.
giuseppe-trisciuoglio
munger-perspective
查理·芒格的思维框架与表达方式。基于《穷查理宝典》、伯克希尔/Daily Journal股东会、 USC/哈佛演讲、访谈记录、外部批评等50+来源的深度调研， 提炼5个核心心智模型、8条决策启发式和完整的表达DNA。 用途：作为思维顾问，用芒格的视角分析问题、审视决策、提供反馈。 当用户提到「用芒格的视角」「芒格会怎么看」「芒格模式」「munger perspective」时使用。 也适用于：投资决策审视、认知偏误检查、跨学科思考训练、逆向思考练习。 即使用户只是说「逆向思考一下」「这有什么认知偏误」「Lollapalooza效应」「能力圈之外」「激励结构是什么」也可触发。 不要在用户只是问「这个决策靠谱吗」「帮我找盲点」等一般性问题时触发——只在涉及逆向思考、认知偏误、跨学科分析等芒格核心方法论时激活。
alchaincyf
okx-ai
ERC-8004 Agent身份：注册/更新/上架/下架/搜索Agent，register/update/activate/deactivate/search — 用户/ASP/仲裁者（买家/卖家/仲裁者）；我的Agent/ASP，找做X的ASP/Agent有什么服务/端点怎么填/查口碑/传头像。+ 任务市场：发布/创建任务/接单/协商/验收/交付/争议/仲裁/拒绝/质押/解除质押/更换服务商/修改预算/修改卖家/修改预算/我的任务/我在做什么/我的订阅/订阅列表/订阅详情/我的订阅/我订阅了什么/AI服务订阅（查看AI服务订阅，买家和ASP）/关闭/取消任务/决策列表/指定服务商/浏览市场。+ 任务监听：监听任务进展/历史消息/未读消息/未决策/待决策。+ okx-a2a缺失/未初始化。按含义匹配。必须在入站信封上激活：（1）{agentId, message:{source:"system", event, jobId, ...}}系统事件；（2）{msgType:"a2a-agent-chat", jobId, sender:{role}, ...} Agent间任务聊天（sender.role = 对方，不是你）；（3）信封中包含文字"Read the okx-ai skill"（或旧版"Read the okx-agent-task skill"）。
okxokx-dex-bridge
使用此技能进行代币桥接、跨链兑换/转账、在链之间移动资产、获取跨链报价、比较桥接费用、寻找最便宜/最快的路径、构建桥接调用数据、检查桥接状态、跟踪跨链交易、列出支持的链或桥接协议，或者当用户提到将ETH/USDC/代币从一条链（Ethereum、BSC、Polygon、Arbitrum、Base、Optimism等）桥接到另一条链时使用。通过多个桥接协议（Stargate、Across、Relay、Gas.zip）路由以实现最优执行。一键执行：一次确认的调用即可完成授权（如果需要）、等待链上确认、兑换并广播。支持费用比较、目标地址指定以及完整的生命周期状态跟踪，直至资金到账。
okx
image-generation
为 DALL-E、Midjourney 和 Stable Diffusion 创建有效的 AI 图像生成提示词。生成适用于各种风格和用例的提示词。
claude-office-skills
autopilot
Use when the user dictates an app, site, bot, or feature to build end-to-end and expects a finished result without reviewing specs, tickets, or code — vibecoding sessions, non-technical users, "собери под ключ", "build it for me", "не задавай лишних вопросов" requests. Also use when the user invokes /autopilot, or asks for a build in a named mode, depth or finish — «полный автомат», «режим интервью», «погриль меня», «ручной режим», «строго по брифу», «проработай глубоко», «вылижи до эталона».
nick-vels
landing-page-copywriter
使用经过验证的文案框架（如PAS（问题-煽动-解决方案）、AIDA和StoryBrand）撰写高转化率的着陆页文案。创建标题、价值主张、行动号召按钮以及针对转化优化的完整页面部分。当用户需要着陆页文案、销售页面内容或营销网站文本时使用。
onewave-ai
debug-model
Debug silent corruption when a MAX model loads, compiles, serves, and generates tokens but output disagrees with a reference implementation. Use whenever parity debugging stalls on scalar taps, the model returns gibberish or wrong greedy tokens, logit cosine is high but argmax differs, or generation is coherent then diverges — during an architecture port, a quantization bring-up, a multi-GPU conversion, or after a MAX upgrade. Triggers on "parity failure", "silent corruption", "logits match but tokens diverge", "top-1 mismatch", "greedy divergence", and "model serves but generates garbage". Not for crashes on load or pre-serve scaffolding (use import-model). Mandates reference-vs-MAX tensor-dump comparators first, verify fixes numerically before recompiling, and serve-vs-pipeline bisect when dumps match but text diverges.
modular
influence-and-negotiation
Influence and negotiation toolkit for any interaction requiring another person's agreement, even when not framed as 'negotiation'. Covers: B2B sales, salary review, collective bargaining/unions, hard 1:1s, decision announcements, mediation, cross-cultural deals, recruitment, reaching out to a manager, CFO, customer, vendor, or colleague, responding to feedback, headcount requests, declining, pushing back on scope, justifying a delay, explaining a decision, raising a concern, getting alignment. Apply when preparing, live, or drafting any diplomatic message. Triggers: coaching prompts ('they just said X', 'what do I say', 'draft a reply'); counterparty cues (buyer, customer, champion, procurement, RFP, sponsor, HR, union, CHRO, ExCo, candidate, counter-offer, partner, peer); situation cues (pushback, refusal, ghosted, no-decision, escalation, fixed budget, MFN, raise, comp band, strike, layoff, recadrage, expectation reset, M&A, BATNA, objection, concession, anchor, mirroring).
samber