Top Agent Skills

Transforma copy aprovada em conceito visual: ideia central, mecanismo visual, hierarquia, sistema de peças e especificação de ativos com prompts prontos.

Saves the latest learning as a numbered markdown file under ~/.claude/learnings and updates the learnings index with title and tags.

Interviews the user in depth about a plan, probing technical implementation, UI/UX, risks, tradeoffs, and missing decisions before writing or refining a spec.

Refines an existing skill in place with minimal diffs, using evidence from usage and session mining to improve triggers, workflow, metadata, and resources.

Refactors duplicated code by extracting helper methods, shared abstractions, or reusable structures, with automated testing and commits after each extraction.

Breaks applications or features into thin vertical user-story slices with clear acceptance criteria and user-observable value, suitable for backlog planning and feature decomposition.

Analyzes a class or module for code smells and produces a prioritized refactoring plan with phases, success criteria, and risk mitigation.

Compile deep repository evidence into artifact-bound correctness doctrine, including authority/law/proof maps, owned invariants, failure archaeology, and knowledge routing, with an optional minimal repository-specific skill portfolio.

Analyzes code to separate essential complexity from incidental noise, then produces a ranked refactoring plan with a structural sketch and TRACE assessment, without making edits.

将内容拆解为系列卡通风格信息图提示词，通过 Chrome DevTools MCP 自动化调用 Gemini web app 生成图片，并自动收集到本地临时目录。

Operates Vultr cloud resources directly via the vultr-cli command-line tool, covering instances, object storage, and account management with built-in confirmation for write operations.

Operates UpCloud cloud servers via the upcloud CLI, covering server, storage, network, and firewall management with read-only and confirmed write operations.

Search the web with LLM-optimized results via the Tavily CLI, returning relevant snippets, relevance scores, and metadata. Supports domain filtering, time ranges, and multiple search depths.

Conduct deep, multi-source web research with citations using the Tavily CLI, producing structured reports for comparisons, market analysis, and literature reviews.

Translates English text paragraph by paragraph into Chinese and provides deep linguistic analysis covering vocabulary, phrases, grammar, voice, syntax, and sentence structure.

Extracts clean, LLM-optimized markdown from any URL, including JavaScript-rendered SPAs, with support for concurrent scraping of multiple URLs and options like main-content-only extraction and custom output formats.

Publishes image-text, video, and long-form content to Xiaohongshu (Little Red Book) via a local CLI script, with support for scheduling, tags, and visibility settings.

Compacts and prunes LanceDB tables in StaticFlow databases to merge fragment files, reduce open file descriptors, and reclaim storage.

Recalibrates conservative Kiro cache-estimation coefficients from recent successful usage samples, producing a recommendation for manual admin Kmodel updates.

Deploy Caddy on a remote Linux host to expose a local HTTP backend as trusted HTTPS, prioritizing a user-owned domain with Let's Encrypt HTTP-01 and falling back to DuckDNS DNS-01 when needed.

Manage Hugging Face dataset Git repositories with Git Xet/LFS-compatible tracking, including setup, safe snapshot commits, push verification, binary rejection recovery, and README track-rule maintenance.

Summarizes, condenses, or extracts text, transcripts, and key points from URLs, articles, web pages, PDFs, podcasts, YouTube videos, and local files. Acts as a fallback transcription tool when the user asks to transcribe, digest, recap, or get the gist of a link, video, or document.

Generates a complete Custom GPT knowledge package from the current workspace project, producing 20 markdown documentation files plus optimized custom instructions for a strategic consultant.

Writes Alan Hirsch's 8-week transformational course content, including video scripts, readings, case studies, reflection questions, and field experiments, in his voice with formation-over-information pedagogy.

Writes or updates pathway pages for Alan Hirsch's platform, following a 12-section architecture that grounds frameworks in Scripture and story, offers practices, and invites course-based formation.

Configures Vite projects, covering vite.config.ts, plugin API, SSR, and Vite 8 Rolldown migration.

Exports a platform feature as a product constitution and data reference, including data model, API contracts, and acceptance criteria, for use in AI prototyping tools.

Collates a movement leader's voice and theme documents into a professionally styled PDF using WeasyPrint.

Creates programmatic videos with React using Remotion, covering compositions, animations, motion graphics, and MP4 rendering, plus walkthrough and content-to-animation workflows.

Converts Stitch designs into modular Vite and React components, using MCP networking and AST-based validation to ensure code quality.

Generates or executes a remediation prompt for a book flagged YELLOW or RED by /book-audit, writing a fix-<book-slug>.md that enumerates defects with verbatim PDF source text and verification commands, then optionally executes the fixes to bring the book to GREEN.

Audits type-safety documentation against the live codebase, checking for drift from validators and folder layout.

Refine existing images through conversational edits using Nano Banana 2, covering color grading, composition, element changes, style transfer, and cleanup with iterative refinement.

Scans local repositories and a Supabase database to inventory all pathway, portal, and theme content, producing a categorized report organized by portal.

Audits image assets across a project to find missing, broken, or mismatched images, and generates prompts for missing assets.

Establishes or validates a canonical Icon wrapper component, size token scale, stroke weight conventions, and illustration usage standards for a project, creating src/components/ui/icon.tsx and documenting the system.

Extracts a YouTube transcript with yt-dlp, cleans it while preserving all substantive speech, and saves a structured markdown file with metadata, overview, and optional timestamps.

Places generated images into realistic device and print mockups such as laptops, phones, books, posters, and billboards for marketing previews and presentations.

Improves or generates prose with sentence-level craft: rhythm, voice, sensory detail, pacing, and line-level revision across genres and styles.

Converts files and office documents to Markdown, supporting PDF, DOCX, PPTX, XLSX, images with OCR, audio with transcription, HTML, CSV, JSON, XML, ZIP, YouTube URLs, and EPubs.

Turns strategy-first Madden NFL YouTube videos into structured, game-ready notes covering meta snapshot, formations, plays, adjustments, and provenance, using transcripts and a curated source list.

Guides database design and operations to avoid common scaling, reliability, and data integrity pitfalls.

Deploy, monitor, and manage GCP services with battle-tested patterns.

Defines an agent's identity, personality, voice, and boundaries to create authentic, non-generic assistants.

Quick-reference guide for project scaffolding, covering directory structures, template engines, config files, and conventions.

通过6道选择题，在约一分半钟内测出你在现实和AI面前两种不同的MBTI人格，并生成对比画像和镜像指数。

Guides the creation of OpenClaw skills with discovery of similar skills, reuse suggestions, and adaptive file generation.

Build reliable Flutter apps by avoiding state loss, widget rebuild traps, and async pitfalls.

Analyzes uploaded data files with full Python access, producing cleaned datasets, statistical reports, charts, and dashboards via the CellCog coding agent.

Gives AI agents a virtual pet with a REST API, real-time hunger, permanent death, and 73+ species to care for.

Runs API, performance, load, stress, and HTTP tests using the basjoofan CLI with configurable concurrency, duration, and statistics output.

Guides OLTP database schema design through six stages: domain and access patterns, entities and relationships, keys and constraints, normalization trade-offs, indexing and performance, and operations and evolution. Includes a final review checklist and tips for effective guidance.

Provides a command-line interface to manage Ansible, Terraform/OpenTofu/Terragrunt, PowerShell, and other DevOps tools through a modern UI and API.

Shares code as GitHub Gists instead of inline chat blocks, with secret-by-default, sensitive-data scrubbing, and same-URL updates.

Improves mobile conversion rates by fixing page speed, CTA visibility, form usability, and hover-dependent interactions, with guidance on real-device testing.

Scans local repos and AI agent skill folders for security drift, saves trusted baselines, and compares changes after updates to highlight risky new capabilities.

Collects Chinese A-share stock data, fetching stock lists and daily, weekly, and monthly K-line history into a local SQLite database for quantitative analysis.

Runs a local Node.js proxy that adapts Azure OpenAI endpoints for OpenClaw, fixing the api-version query parameter issue and enabling Azure credits for subagents.

Sends and reads email for your own domain through a local mail server using fixed scripts, and creates new mail accounts.

Designs scalable REST and GraphQL APIs, creates OpenAPI 3.1 specifications, and plans versioning, pagination, and error handling.