81 个 · 按相关度排序
Heuristic story-point estimation for a single Jira ticket via the jira-estimator agent. Read-only. Triggers: 'estimate KEY', 'story points for KEY', 'how complex is KEY'. NOT for complexity-only analysis (mk:jira-evaluator); NOT for full RCA (mk:jira-analyst).
中文简介正在准备中。当前显示原文说明。
Use this skill for ANY of the following — do not skip it even if the query seems simple: strategic decisions, business analysis, thesis building, complex problem solving, geopolitical analysis (non-market), philosophical reasoning, academic research, system design, decision under uncertainty, long-form thinking, or any question that benefits from First Principle deconstruction and multi-agent reasoning. ALWAYS use this skill when the user asks about: why something works the way it does, whether a decision is correct, how to think about a complex problem, what could go wrong, analyzing a situation from multiple angles, or any "should I..." question involving real-world trade-offs. This is NOT a market/trading skill — for financial markets, BTC, gold, stocks, forex, macro economics, use money-atlas-intelligence-os instead.
中文简介正在准备中。当前显示原文说明。
Apply the four published expert-consensus clinical scenarios to manage GI adverse events in complex GLP-1 receptor agonist patients — persistent nausea mid-titration, GERD/heartburn after up-titration, elderly with sarcopenia risk, and insulin-treated elderly with CKD plus diarrhoea. Use when a clinician describes a patient resembling one of these archetypes, or asks "how to manage GLP-1 in an elderly patient with CKD", "patient on liraglutide developed reflux", "sarcopenia worry on semaglutide in 80-year-old", or "persistent nausea on semaglutide despite escalation". Grounded in Gorgojo-Martínez 2023 Table 4.
中文简介正在准备中。当前显示原文说明。
Add or define specific fields in a collection's readSchema. Use when fields are missing from materialization field selection, pruned by complexity limit, need type refinement, need to be protected from future inference changes, or need to be required for downstream consumers. Use when user says "missing fields", "pruned fields", "field not showing up", "complexity limit", "define field in read schema", "restrict field type", or "protect field from inference".
中文简介正在准备中。当前显示原文说明。
Design state-of-the-art multi-agent systems, orchestration patterns, and wiring from scratch. Load when the user asks to build an agent system from scratch, design agent orchestration patterns, choose between sequential/parallel/hierarchical workflows, or define how multiple agents should collaborate. Also triggers on "agent architecture", "multi-agent wiring", "agent orchestration pattern", "how to connect these agents", "design the communication structure". Called by agent-builder for complex topologies (>4 agents or hierarchical). For process-driven agent design, use agent-builder instead.
中文简介正在准备中。当前显示原文说明。
[00] META. Orchestrate skills into dynamic chains for complex tasks. Analyzes the task, discovers available skills, builds an optimal chain, explains why each skill is needed, and executes step-by-step with user confirmation. Use for any complex task requiring multiple thinking/research/analysis steps. Triggers on "plan this", "how to approach", "what's the strategy", "build a plan", or any multi-step problem requiring skill orchestration.
中文简介正在准备中。当前显示原文说明。
Tracks complex, multi-session work using the Beads issue tracker and dependency graphs, and provides persistent memory that survives conversation compaction. Use when work spans multiple sessions, has complex dependencies, or needs persistent context across compaction cycles. Trigger with phrases like "create task for", "what's ready to work on", "show task", "track this work", "what's blocking", or "update status".
中文简介正在准备中。当前显示原文说明。
使用D3.js制作可交互的图表，让读者在阅读时探索数据。借助多种图表与表现手法的示例，可用于报告、仪表盘、数据原型和文章配图。
Coordinate multiple AI agents with agentic-flow to run tasks in parallel or through ordered stages. Configure shared memory, team structure, workload distribution, retries, and task reassignment, then monitor how the group performs.
中文简介正在准备中。当前显示英语简介。
Coordinate multiple AI agents for research, development, testing, and system analysis using Claude Flow. Choose how agents communicate, assign specialist roles, combine parallel and sequential tasks, and monitor progress through reporting and recovery workflows.
中文简介正在准备中。当前显示英语简介。
Build attack trees, diagrams showing paths toward an attacker's goal. Break scenarios into required or alternative steps, assess effort and detectability, and map defenses to identify gaps and prioritize security work.
中文简介正在准备中。当前显示英语简介。
Design reusable interface components in React, Vue, and Svelte. Organize how components fit together, define clear configuration options, and choose styling approaches while addressing accessibility, responsive layouts, and maintenance across component libraries or design systems.
中文简介正在准备中。当前显示英语简介。
Design reusable TypeScript components and API types with checks at compile time. Use generics, conditional rules, property transformations, and string patterns to derive types from existing definitions and verify how those types behave.
中文简介正在准备中。当前显示英语简介。
Design and build an OpenMAIC lesson series using a spiral curriculum: core ideas return with deeper explanations, new representations, and unfamiliar applications. It maps conceptual growth across lessons and checks that revisits add understanding.
中文简介正在准备中。当前显示英语简介。
Plan how users discover, try, and pay for a product through self-service. Compare product-led growth with sales-led approaches, improve the first useful experience, assess acquisition channel economics, and identify when sales support should step in.
中文简介正在准备中。当前显示英语简介。
Build custom interactive charts, maps, and network diagrams with d3.js. The skill guides data preparation, styling, resizing, and interactions such as zooming and tooltips, giving detailed control over how data appears and responds to users.
中文简介正在准备中。当前显示英语简介。
Model up to three overlapping business risks and trace how their effects spread across teams. Compare three severity levels, identify early warning signals, and define preventive actions with costs, owners, and deadlines to support strategic decisions.
中文简介正在准备中。当前显示英语简介。
Turn requirements for software or other multi-step work into a structured plan with an approach, constraints, and verification steps. It also helps develop existing plans, researching decisions before handing the work over for execution.
中文简介正在准备中。当前显示英语简介。
Write and troubleshoot n8n expressions, the formulas that pass and transform data between workflow steps. Covers field references, webhook inputs, dates, strings, and choosing between expressions and Code nodes for data transformations.
中文简介正在准备中。当前显示英语简介。
Write JavaScript for n8n Code nodes to aggregate, filter, and transform workflow data. Guidance covers data access, output formats, execution modes, common errors, and performance choices when processing large numbers of records.
中文简介正在准备中。当前显示英语简介。
Guides you through setting up RWKV, generating text, processing long documents in chunks, and fine-tuning models. Explains how to carry context between steps and compare memory use with Transformer models.
中文简介正在准备中。当前显示英语简介。
Assesses smart contract and blockchain codebases against Trail of Bits’ nine-category maturity framework. Produces evidence-backed ratings covering areas such as arithmetic, access controls, documentation, and testing, plus a prioritized improvement roadmap with effort estimates.
中文简介正在准备中。当前显示英语简介。
Write and troubleshoot n8n expressions, the formulas that pass and transform data between workflow steps. Correct field references, read webhook inputs, format dates and text, and query nested JSON while checking for silently missing results.
中文简介正在准备中。当前显示英语简介。
Write JavaScript for n8n Code nodes to aggregate, filter, and transform workflow data. Guidance covers data access, output formats, execution modes, common errors, and performance choices when processing large numbers of records.
中文简介正在准备中。当前显示英语简介。