数据分析、机器学习、LLM 应用、提示词设计（9139 个）
Use when the user asks how to build with OpenAI products or APIs and needs up-to-date official documentation with citations, help choosing the latest model for a use case, or explicit GPT-5.4 upgrade and prompt-upgrade guidance; prioritize OpenAI docs MCP tools, use bundled references only as helper context, and restrict any fallback browsing to official OpenAI domains.
中文简介正在准备中。当前显示原文说明。
Use when designing, optimizing, testing, or deploying robust prompt systems for AI agents. This skill provides frameworks for structured prompt engineering, meta-prompting, and automated optimization workflows.
中文简介正在准备中。当前显示原文说明。
Build Shopify applications, extensions, and themes using GraphQL/REST APIs, Shopify CLI, Polaris UI components, and Liquid templating. Capabilities include app development with OAuth authentication, checkout UI extensions for customizing checkout flow, admin UI extensions for dashboard integration, POS extensions for retail, theme development with Liquid, webhook management, billing API integration, product/order/customer management. Use when building Shopify apps, implementing checkout customizations, creating admin interfaces, developing themes, integrating payment processing, managing store data via APIs, or extending Shopify functionality.
中文简介正在准备中。当前显示原文说明。
Use when needing 100% type-safe, schema-valid data extraction from LLMs. Keywords: structured output, JSON schema, Pydantic, Zod, type-safe, constrained decoding, validation, tool use.
中文简介正在准备中。当前显示原文说明。
Master context engineering for AI agent systems. Use when designing agent architectures, debugging context failures, optimizing token usage, implementing memory systems, building multi-agent coordination, evaluating agent performance, or developing LLM-powered pipelines. Covers context fundamentals, degradation patterns, optimization techniques (compaction, masking, caching), compression strategies, memory architectures, multi-agent patterns, LLM-as-Judge evaluation, tool design, and project development.
中文简介正在准备中。当前显示原文说明。
Use when needing global or relational understanding of codebases or knowledge corpora. Keywords: GraphRAG, knowledge graph, entity extraction, community summarization, graph traversal, Microsoft GraphRAG.
中文简介正在准备中。当前显示原文说明。
Use when validating, benchmarking, or monitoring LLM application performance. Keywords: RAG evaluation, LLM-as-a-judge, CI/CD gating, trajectory scoring, test suites, prompt quality.
中文简介正在准备中。当前显示原文说明。
Use when optimizing token usage, KV cache efficiency, or context window management for LLM agents. Keywords: context optimization, KV cache, prompt caching, token budget, semantic pruning, lost-in-the-middle.
中文简介正在准备中。当前显示原文说明。
Use when building self-correcting retrieval systems for AI agents. Keywords: RAG, retrieval, Corrective RAG, Self-RAG, query decomposition, reranking, hallucination, grounding.
中文简介正在准备中。当前显示原文说明。
Process and generate multimedia content using Google Gemini API. Capabilities include analyze audio files (transcription with timestamps, summarization, speech understanding, music/sound analysis up to 9.5 hours), understand images (captioning, object detection, OCR, visual Q&A, segmentation), process videos (scene detection, Q&A, temporal analysis, YouTube URLs, up to 6 hours), extract from documents (PDF tables, forms, charts, diagrams, multi-page), generate images (text-to-image, editing, composition, refinement). Use when working with audio/video files, analyzing images or screenshots, processing PDF documents, extracting structured data from media, creating images from text prompts, or implementing multimodal AI features. Supports multiple models (Gemini 2.5/2.0) with context windows up to 2M tokens.
中文简介正在准备中。当前显示原文说明。
Reference documentation for embedding Prismatic's integration marketplace and workflow builder in a web application. Covers JWT authentication, the embedded SDK, marketplace and workflow embedding, theming, i18n, additional screens, and custom marketplace UI. Use when the user asks about embedding Prismatic, JWT tokens for embedded apps, marketplace iframes, workflow builder integration, custom marketplace UI, or frontend SDK setup.
中文简介正在准备中。当前显示原文说明。
Marketing analytics and data-driven optimization for B2B SaaS campaigns. Use this skill when analyzing marketing performance, optimizing conversion rates, running A/B tests, conducting customer research, creating marketing dashboards, building attribution models, analyzing funnel metrics, or storytelling with data. Also triggers on: marketing ops, performance analytics, CRO, A/B testing, data storytelling, customer insights, tracking plan, event taxonomy, UTM taxonomy, GA4 audit, consent mode, instrumentation contract, sample size calculation, minimum detectable effect, test duration, not enough traffic to A/B test, statistical significance, Bayesian vs frequentist, sample ratio mismatch, experiment feasibility, martech stack, marketing tech stack audit, tool consolidation, build vs buy, vendor evaluation, shadow IT tools, ESP/CRM/platform migration, switching cost, cutover plan, suppression list migration, data portability, customer interviews, survey design, sampling frame, non-response bias, how many people should I interview, thematic saturation, voice of customer, jobs-to-be-done, buyer persona research, is this finding real, data enrichment, which enrichment provider should we buy, waterfall enrichment, contact data quality, match rate, our list data is bad, email verification, catch-all domain, accept-all, bounce rate from bad data, B2B data decay, how often should we re-verify contacts, ZoomInfo vs Apollo vs Clearbit evaluation, cost per usable record, where did this list come from, GDPR Article 14 notice, purchased list compliance, suppression screening, TAM list building, demand planning, marketing plan, how many leads do we need, what pipeline target should marketing carry, funnel model, top-down vs bottom-up plan, plan of record, annual marketing planning, quarterly planning, pipeline coverage we have to create, sales cycle lag, our leads cannot close this quarter, carry-in pipeline, scenario planning, conservative moderate aggressive forecast, stretch target, reforecast, re-forecast triggers, assumption register, capacity ceiling, addressable audience ceiling, marginal cost per lead, blended CPL is wrong, we missed plan and nobody knows why, AI policy for the marketing team, AI governance, AI acceptable use policy, which AI tools are we allowed to use, can I paste customer data into ChatGPT, shadow AI, AI use register, human review of AI output, when can we stop reviewing every AI draft, can the agent send on its own, the AI made a mistake now what, pull back AI autonomy, AI evals, our AI vendor changed the model, AI output went out wrong, prompt injection, can our AI read prospect replies safely, lethal trifecta, the AI leaked internal notes, turn off auto-generated ad assets, auto-applied recommendations, AI literacy training, EU AI Act Article 4, duplicate records in the CRM, dedupe before import, which value wins in a merge, CRM cleanup.
中文简介正在准备中。当前显示原文说明。
Account-based marketing for B2B SaaS. Use this skill to build a target account list, tier it 1:1 / 1:few / 1:many, size it against sales capacity, turn intent and engagement signals into plays, write the multi-channel orchestration contract each tier runs on, and measure the program in account coverage, penetration and pipeline instead of MQLs. Also triggers on: ABM, account-based marketing, target account list, TAL, named accounts, account tiering, 1:1 ABM, one-to-few, programmatic ABM, account selection, ideal customer profile fit, intent data, buying signals, 6sense, Bombora, Demandbase, account penetration, account coverage, sales and marketing alignment on accounts, enterprise account program.
中文简介正在准备中。当前显示原文说明。
Product-led growth and customer-base growth for B2B SaaS. Use this skill for self-serve funnel work (activation, time-to-value, free trial vs freemium, PQL definition, in-product upgrade moments, sales-assist triggers), for the self-guided interactive product demo that runs in front of the login wall (demo portfolio and flow design, gated vs ungated policy, demo seed data and privacy, keeping a published demo in sync with the shipping product, step-level demo analytics), and for growing revenue from existing customers (adoption, expansion, churn-save, the self-serve cancel flow and failed-payment recovery, renewal marketing, net revenue retention, and champion tracking: watching the people who bought and used you at each customer, confirming a job change from evidence, and running both plays a move fires, the seat they left and the account they joined). Also triggers on: PLG, product-led growth, activation, aha moment, time to value, free trial, freemium, PQL, product qualified lead, onboarding, self-serve, customer marketing, expansion revenue, upsell, cross-sell, churn, retention, NRR, renewal, cancel flow, cancellation flow, save offer, exit survey, pause subscription, dunning, failed payment recovery, involuntary churn, people keep canceling, champion tracking, job change signals, job change alerts, our champion left, our champion changed jobs, customer alumni, former customers who moved to a new company, interactive demo, self-guided demo, product tour, click-through demo, demo automation, demo library, should our demo be gated, ungated demo, demo without a sales call, our demo is out of date, demo shows the old UI, put a demo on our homepage, demo completion rate, demo drop-off, try before you talk to sales.
中文简介正在准备中。当前显示原文说明。
Create custom modules for [Harbor Boost](https://github.com/av/harbor/tree/main/boost), an optimizing LLM proxy. Use when building Python modules that intercept/transform LLM chat completions—reasoning chains, prompt injection, structured outputs, artifacts, or custom workflows. Triggers on requests to create Boost modules, extend LLM behavior via proxy, or implement chat completion middleware.
中文简介正在准备中。当前显示原文说明。
Use when the user wants to systematically fix AI code slop — duplicated logic, over-engineering, silent error swallowing, convention drift, cargo-cult patterns, and other LLM-introduced architectural decay — over a specified duration
中文简介正在准备中。当前显示原文说明。
Run a task iteratively over a user-specified duration by dispatching subagents. The orchestrator stays strictly linear and time-checked, but each iteration fans out MULTIPLE subagents in parallel over independent units (and those subagents may fan out further). Shared state — a compact progress digest and a growing environment cheatsheet — lives on disk and is passed to every subagent BY REFERENCE, killing the per-subagent rediscovery tax. Every subagent first reads an initialiser preamble that points it at that shared state and makes it write findings back, so the cheatsheet populates itself; role prompts are produced ONCE on the filesystem by a single scaffold command and dispatched by path, never re-typed per dispatch. Subagents persist their results to disk and return only a tiny status, so the orchestrator's context stays small and lasts. The orchestrator classifies the goal as FINITE or OPEN-ENDED: finite lists may finish early; open-ended goals use the full duration, never idle, never manufacture busywork. Use when the user gives a task and a duration and wants it ground out iteratively by subagents over that time.
中文简介正在准备中。当前显示原文说明。
国内电商提示词融合工作流。用于为国内微信生意、微信视频号、朋友圈、淘宝/天猫/京东风格商品展示，生成给豆包使用的中文商品主图提示词、商品宣传图提示词、商品功能细节图提示词、朋友圈营销文案和带货短视频脚本。用户提到国内电商、大牌商品展示感、朋友圈卖货、视频号、商品图、商品宣传图、功能细节图、带货短视频脚本、营销文案、豆包提示词时使用。
中文简介正在准备中。当前显示原文说明。
Scaffold Quarkus + LangChain4j projects end-to-end and add agentic components to existing ones — AI services, tools, agents and multi-agent workflows, RAG pipelines, MCP clients and servers (Model Context Protocol), guardrails, and embedding store setups. Use this whenever the user wants a new Quarkus + LangChain4j project or module created, or an agentic component added to an existing project in this stack, including a baseline pom.xml, application.properties, project layout, or starter classes.
中文简介正在准备中。当前显示原文说明。
Teaches you how to delegate tasks to Cowork so clearly that you get exactly what you asked for — every time. Use when learning how to give better instructions, for improving your delegation technique, during early Cowork adoption when results feel off, when writing clearer task descriptions, or when the user says "how do I ask cowork to do things", "delegation tips", "better instructions", "cowork isn't doing what I want", "help me delegate", "my results are bad", "how do I give better prompts", "cowork keeps getting it wrong", "I don't know how to use this", or "how do I get good results".
中文简介正在准备中。当前显示原文说明。
Run an end-to-end GEO visibility measurement through a real AI interface, persist the captures, and return a portable JSON run artifact plus optional PDF/dashboard outputs. Use automatically on an explicit request to measure a brand's AI-search visibility, and as a composable data-collection step inside another agent workflow; the user should not have to launch the pipeline or dashboard manually.
中文简介正在准备中。当前显示原文说明。
Use the hyalo CLI instead of read/edit/grep/write when working with markdown (.md) files that have YAML frontmatter. This skill MUST be consulted whenever pi is working with markdown documentation directories, knowledgebases, wikis, notes, Obsidian-compatible collections, Zettelkasten systems, iteration plans, or any collection of .md files with frontmatter. Trigger this skill when: searching or filtering markdown files by content, tags, or properties; reading or modifying YAML frontmatter; managing tags or metadata across documents; toggling task checkboxes in markdown; getting an overview of a documentation directory; querying document properties or status fields; bulk-updating metadata across many markdown files; or when you find yourself repeatedly using read/edit/grep/write on .md files. Even if the user does not mention "hyalo" by name, use this skill whenever the task involves structured markdown documents with frontmatter. For pi sessions, ALWAYS use `--format text` for compact, LLM-friendly output.
中文简介正在准备中。当前显示原文说明。
MITRE ATT&CK local dataset reference. Query techniques, groups, software, and mitigations from the local enterprise-attack.json.
中文简介正在准备中。当前显示原文说明。
Use when you need to hunt in the organisation's own Microsoft Sentinel workspace — sweep the logs for IOC hits (IP, domain, hash, URL, account), hunt behavioural TTPs from MITRE ATT&CK techniques, run KQL against live data, or check which tables the workspace actually ingests. Discovers available tables first and only generates KQL for tables that verifiably exist, so hunts adapt to each environment's connectors. Commonly chained by the /*-investigation skills to answer "were we exposed?". Reads $SENTINEL_TENANT_ID, $SENTINEL_CLIENT_ID, $SENTINEL_CLIENT_SECRET, $SENTINEL_WORKSPACE_ID. Read-only.
中文简介正在准备中。当前显示原文说明。