Latest Agent Skills

Interacts with Xiaohongshu posts by posting comments, replying to comments, liking, and favoriting via a local CLI script.

Publishes image, video, and long-form posts to Xiaohongshu (Little Red Book) with scheduling, tags, and visibility options, after user confirmation.

小红书内容发现与分析技能。搜索笔记、浏览首页、查看详情、获取用户资料。 当用户要求搜索小红书、查看笔记详情、浏览首页、查看用户主页时触发。

Manages Xiaohongshu (Little Red Book) login sessions and multiple accounts via a CLI script, supporting QR code and phone verification login, account switching, and cookie clearing.

Automates Xiaohongshu (Little Red Book) operations including login, content publishing, search, and social interactions via a Python CLI.

Watches conversations continuously and compresses them into prioritized notes, consolidating and recovering missed sessions with multiple redundancy layers.

采用孙宇晨的思维框架与表达方式，基于其公开言论和著作提炼的14个核心心智模型、18条决策启发式及表达DNA，用于分析加密行业、审视商业决策并提供反馈。

Compiles SOUL.md character profiles into synthetic diploid genomes by mapping trait scores to alleles at defined loci, producing .genome.json files.

Calculates polygenic risk scores from 23andMe or AncestryDNA genotype files using PGS Catalog scoring files, then estimates population percentiles and risk categories.

Generates and burns subtitles into videos: extracts audio, transcribes via Volcano Engine, corrects errors, reviews, and burns subtitles with ffmpeg.

Generates unit tests for code changed in the current branch by comparing against origin/main and following existing test conventions.

Provides 43 prioritized best-practice rules for using Zod in TypeScript, covering schema definition, parsing, type inference, error handling, composition, refinements, and performance.

Guides creation of professional, portable, and optimized terminal recordings using VHS, covering configuration, timing, output optimization, and CI/CD integration.

Guides AI agents through Test-Driven Development with 42 prioritized rules covering the red-green-refactor cycle, test design, isolation, data management, assertions, organization, performance, and strategy.

Provides 45 best-practice rules across 8 categories for mocking APIs with MSW v2, covering setup, handler architecture, test integration, response patterns, request matching, GraphQL, advanced patterns, and debugging.

Guides WinUI 3 and Windows App SDK development with setup, scaffolding, design, and troubleshooting workflows.

Locates failing GitHub Actions checks on a pull request, fetches logs, summarizes failures, and proposes a fix plan for approval before implementing.

Refines overly bold or aggressive designs into a calmer, more sophisticated aesthetic while preserving effectiveness and usability.

Turns websites into CLI commands, reusing an existing Chrome login session for browser-backed data extraction and structured output.

Design and improve product onboarding experiences that help users understand, adopt, and succeed quickly, covering assessment, principles, and implementation patterns.

Identifies reusable UI patterns, components, and design tokens, then extracts and consolidates them into a design system for systematic reuse.

Systematically explores a web application, finds issues, and produces a report with reproduction evidence for each finding.

Simplify UI designs by removing unnecessary complexity, clarifying hierarchy, and focusing on essential elements.

Identify opportunities to add moments of joy, personality, and unexpected polish that transform functional interfaces into delightful experiences.

Identify and improve unclear, confusing, or poorly written interface text to make the product easier to understand and use.

Analyze a feature and strategically add animations and micro-interactions that enhance understanding, provide feedback, and create delight.

Automates Azure OpenAI model deployment by checking capacity across regions and deploying to the best available option.

Builds a Streamlit and FastAPI RAG application that lets users upload documents and query them with natural language through LM Studio.

Guides users through a structured interview to clarify their AI agent idea and produces an Agent Requirement Document (ARD).

Creates git commits following Sentry conventions, including conventional commit format, issue references, and AI attribution.

Summarizes URLs, local files, and YouTube links via a CLI, with options for transcript extraction and configurable models.

Query experiments, protocols, resources, and inventory in the Labstep electronic lab notebook using the labstepPy API.

Queries the ClinPGx REST API for pharmacogenomic gene-drug data, clinical annotations, CPIC guidelines, and FDA drug labels, generating markdown reports with CSV tables.

Facilitates structured sprint retrospectives, analyzing team feedback and sprint data to generate prioritized, actionable improvement items.

Interact with the X (Twitter) API through the xurl CLI, covering posting, reading, searching, engagement, and account management.

Generates or edits images for projects using the OpenAI Image API, with support for batch runs and structured prompt augmentation.

Performs a meticulous final pass on frontend work, checking visual alignment, typography, color contrast, interaction states, micro-interactions, content, icons, forms, edge cases, responsiveness, performance, and code quality to elevate work from shipped to polished.

Strengthen interfaces against edge cases, errors, internationalization issues, and real-world usage scenarios that break idealized designs.

Increases visual impact and personality in designs that are too safe, generic, or visually underwhelming, creating more engaging and memorable experiences.

Control Sonos speakers on the local network with commands for playback, grouping, favorites, queue, and Spotify search.

Automates macOS UI via a CLI: capture screens, inspect and target UI elements, drive mouse and keyboard input, and manage apps, windows, menus, and dialogs.

Checks past orders and tracks active order status for Foodora via the ordercli command-line tool.

Manage an Obsidian vault from the command line: locate active vaults, search notes and content, create, move, and delete notes using obsidian-cli.

Edits a specific page in a PDF using a natural-language instruction, with page-number handling and output verification.

Interact with MCP servers directly from the command line, including listing, calling tools, managing authentication, and generating client code.

Manage email from the terminal using IMAP, SMTP, Notmuch, or Sendmail backends, including listing, reading, composing, replying, forwarding, and organizing messages.

Controls an Eight Sleep smart bed pod from the command line, including temperature, alarms, schedules, audio, and base adjustments.

Build documentation sites with VitePress, covering configuration, Markdown, Vue components, themes, and deployment.

Guides configuring Turborepo for JavaScript/TypeScript monorepos, covering task pipelines, caching, filtering, CI optimization, and package structure.

Creates product backlog items in Why-What-Acceptance format, producing independent, valuable, testable items with strategic context.

Runs systematic quality checks across accessibility, performance, theming, and responsive design, then generates a prioritized audit report with actionable recommendations without fixing issues.

Adapt existing designs to work effectively across different contexts - different screen sizes, devices, platforms, or use cases.

Runs a Pomodoro timer with session tracking, history, and productivity analytics stored in a local SQLite database.

Fetches current weather and forecasts for any location using free, keyless APIs like wttr.in and Open-Meteo.

Generates spectrograms and multi-panel audio feature visualizations from audio files via a command-line tool.

Runs Semgrep static analysis to find bugs and security vulnerabilities, with guidance on installation, rule selection, custom rule writing, and CI/CD integration.

Sets up and runs OSS-Fuzz fuzzing harnesses locally, builds project images, and generates coverage reports.

Controls Philips Hue lights and scenes through a Hue Bridge using the OpenHue CLI, including discovery, setup, and light management commands.

Searches GIF providers (Tenor/Giphy), previews results in a TUI, downloads GIFs, and extracts stills or contact sheets.

Manages Discord messages, reactions, threads, polls, and moderation through a bot token, with configurable action groups.