>

>-

Estrategia de marca, identidade visual, brandbook, auditoria de marca

Meta Ads, Google Ads, campanhas, otimizacao, criativos, budget

Reconcile one active execution slice, optionally execute owner-chain routing, and persist checkpointed resume context for one-slice acceleration.

>-

Delegate real-world tasks to human workers via the OpenHumancy API. Use when the user needs physical actions (field verification, photography, deliveries, mystery shopping), human judgment, or any task that requires a person. Manages the full lifecycle — worker search, task creation, chat, payments on the TON blockchain.

Modern Django admin theme - Unfold - customization, settings, components, actions, filters, integrations

Comprehensive guide for building LLM applications with LlamaIndex, including data loaders, indexes, query engines, chat engines, vector stores, retrievers, agents, evaluation, streaming, and observability.

Python 2D game development - sprites, surfaces, events, sound, fonts, game loops, collision detection, and input handling

基于郑总历次亲手修改、明确批注的审稿标准。五轮检查，每轮独立列问题清单，最后给出优先级。

代码库探索与架构理解 Skill。接手任何代码库时激活：扫描目录结构，识别技术栈，读取核心文件，提取架构模式，与产品定义/需求对比，输出可信赖的架构理解文档。触发词：「阅读XXX项目」「理解这个代码库」「写技术架构文档」「这个项目是做什么的」「接手这个项目」「帮我读一下这个代码」。

基于用户自己的认知文档回答问题，严格引用来源，标注置信度，暴露矛盾，识别知识空白。触发词：「基于我的文档」「根据我的想法」「我之前怎么想的」「我说过什么关于X」「我对X的看法是什么」「帮我回忆」「我的认知里怎么说」「我的框架里有没有」「从我的角度」「我如何看待」。

从L2碎片中识别跨领域共同模式，提炼L1.5底层原则候选，经用户确认后写入原则库。触发词：「提炼原则」「有什么规律」「这些碎片有没有共性」「是不是反映了某个习惯」「总结一下模式」「有什么底层逻辑」。

受控更新L1系统性文档：含影响范围预分析、历史版本备份、矛盾检测、级联写入。触发词：「更新[文档名]」「完善[文档名]」「修改[文档名]」「我要改[内容]」「在[文档]里加上」「[文档]需要更新」。

认知-工作对齐健康检查（第四维）。验证五个工作域的核心产出是否可追溯到元思维体系（L1.5原则 or L1文档），识别「漂浮」的工作任务，输出对齐报告。与现有三维健康检查互补：skill-system-health-check（内部一致性）/ cognitive-consistency-check（认知自洽）/ skill-domain-health-check（传播完备性）+ 本Skill（认知根对齐）= 四维完整体系。触发词：「检查工作任务与认知的对齐」「第四维健康检查」「检查工作任务是否有认知根」「认知体系和工作任务是否自洽」「认知对齐检查」。

统一写作流水线。任何文档/文章/报告均走此流程：研究→草稿→逻辑自检→真实性校对→画图规划→批量画图→图片自审→审稿→格式转换（HTML/LaTeX/MD）。可从任意阶段入场（已有草稿直接审核，已审稿直接转格式）。触发词：「写一篇/帮我写/写一份/我有初稿了/帮我检查逻辑/帮我配图/从画图开始/从[Stage名称]开始继续/转成HTML/转成LaTeX」。注意：「只要审稿」请直接触发 article-proofreading；「帮我审稿」不触发本 Skill。

| 层级 | 文档 | 需要理解的概念 |

React Router v7, React Query, and shadcn/ui patterns used in the Rivetr dashboard. Use when writing new frontend components, routes, or API integrations.

source: databricks.com/solutions/industries/financial-services

source: databricks.com/solutions/industries/marketing + retail + media-and-entertainment

| Field | Value |

| Field | Value |

| Field | Value |

| Field | Value |

Turns an Asana bug report into a fully briefed Codeman worktree that autonomously runs the full fix-to-PR pipeline. Source is Asana for v1.

Extracts frames at adaptive rates, creates montage grids, detects scene changes, and dispatches parallel subagents for visual and audio analysis.

**Table of Contents**

> Design intelligence for UI/UX generation and critique; use for layouts, typography, color palettes, tokens, and UX best practices. 50 styles, 21 palettes, 50 font pairings, 20 charts, 9 stacks (Reac

This directory contains CatMaster starter skills grouped by lane. A skill here is prompt-level SOP, not a tool schema dump and not a hidden runtime contract.

Detect chromatin loops and point interactions from Hi-C data using cooltools, chromosight, and HiCCUPS-like methods. Identify CTCF-mediated loops and enhancer-promoter contacts. Use when detecting chromatin loops from Hi-C data.

Use when implementing Disney's 12 animation principles with Lottie animations exported from After Effects

Renders After Effects animations as lightweight JSON on web and mobile using lottie-web. Use when adding vector animations, loading indicators, or complex motion graphics without video files.

lotus-analyze-reference-dependencies

{{SKILL_DESCRIPTION}} Use this skill when working with image operations, texture management, image data manipulation, or any image-related operations in LÖVE games.

Use when implementing Least Significant Bit (LSB) steganography - allows hiding images or text within other images by encoding data in the least significant bits of pixel color channels

This skill should be used when the user asks to “access LSEG data”, “query Refinitiv”, “get market data from Refinitiv”, “download fundamentals from LSEG”, “access ESG scores”, “convert RIC to ISIN”, “get shareholder activism data”, “query poison pills”, “access corporate governance data”, “find activist campaigns”, “get syndicated loans data”, “query loan deals”, “get infrastructure projects”, “query project finance data”, “get private equity data”, “query VC investments”, “find PE-backed companies”, “get M&A data”, “query mergers and acquisitions”, “find acquisition deals”, “get IPO data”, “query equity offerings”, “find new issues”, “get joint venture data”, “query strategic alliances”, “get news headlines”, “query news data”, “fetch news articles”, or needs the LSEG Data Library Python API.

Detect and prevent generic AI aesthetics (purple gradients, flat layouts, predictable patterns) in M3 components. Validates typography, colors, and layout against expressive design standards with 0-100 quality scoring.

Elevate typography with variable fonts, extreme weight contrasts (100 vs 900), and emotional tone guidance. Validates against generic fonts (Inter, Roboto) and enforces M3 expressive principles with high-contrast pairings.

Use when preparing to delegate to MacEff subagents. Read policies to discover current delegation patterns through timeless questions that extract details without prescribing answers.

Use BEFORE significant TODO modifications (adding subtrees, marking complete, reorganizing, collapsing). Ensures policy compliance through extractive questions. Run proactively when planning TODO changes.

Apply Chip and Dan Heath's SUCCESs framework to make ideas memorable, impactful, and actionable. This skill helps you transform abstractions into concrete, sticky communication.

Transform raw captured content into distilled knowledge by extracting topics (outline), summary, key points, principles, patterns, entities, and quotes, storing the result in the distilled/ directory.

Converts highlighted text (typically bullet lists or paragraphs) into an expandable HTML <details> dropdown with a custom summary. Use this skill when the user wants to make content collapsible/expandable in their MDX files.

Makefile Assistant automatically captures interesting Bash commands executed by Claude Code (via `cchistory`) and transforms them into well-documented, categorized Makefile targets. This eliminates ma

malware-forensics

This skill should be used when implementing stateless conversation persistence, creating/loading conversations by ID, saving user/assistant messages, fetching history for agent input, and handling async database queries.

Manage delayed request queues including workload, system, and utility queues to release blocked requests or abort unnecessary items

Manage solution outline documents - standards, examples, validation, and deliverable extraction