发现 Skills

Incrementally fix build and type errors with minimal, safe changes. Use when build fails, type errors appear, or user says "fix build", "build broken", "build-fix".

Generate Excalidraw JSON for architecture diagrams, flowcharts, sequence diagrams. Use when user asks for "диаграмма", "flowchart", "excalidraw", "архитектурная схема".

Plan, launch, and operate a LinkedIn employee advocacy program for a marketing team. Covers 14-day launch playbook, authentic-voice posting at scale, brand guideline governance with optional review, per-post time budgeting, team posting cadence benchmarks, and ROI measurement (team reach, engagement, pipeline impact). Triggers on "employee advocacy", "team posting program", "scale LinkedIn across marketing team", "brand amplification", "advocacy ROI", "get the team posting", "employee-generated content".

Распаковать PPTX как zip, прочитать XML слайдов, извлечь текст/картинки/координаты. Чтобы редактировать чужой дек как HTML.

Prepare a pub.dev release with version bump, changelog update, and publish dry-run

ClawHub 技能市场工具。使用 ClawHub CLI 从 clawhub.com 搜索、安装、更新和发布 agent 技能。支持技能搜索、安装指定版本、更新到最新版本、批量更新、发布新技能。适用于"安装XX技能"、"更新技能"、"搜索技能"、"发布技能"等查询。需要安装 clawhub CLI（npm global）。

文本摘要工具。从长文本中提取关键要点，生成结构化摘要。支持自定义要点数量（默认5个）。适用于"总结XX"、"提取要点"、"归纳XX内容"、"概括XX文章"、"关键信息"等查询。返回 JSON 格式的要点列表。

技能创建指南工具。帮助用户创建有效的 JPClaw skills，提供最佳实践、模板、工作流和集成建议。适用于"创建技能"、"新建skill"、"技能开发"、"skill模板"等查询。生成完整的 SKILL.md 文件和实现代码框架。

Extracts and analyzes competitors' ads from ad libraries (Facebook, LinkedIn, etc.) to understand what messaging, problems, and creative approaches are working. Helps inspire and improve your own ad campaigns.

Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.

Send messages to Feishu webhook. Triggers: notify feishu, feishu alert, feishu card.

Java 21 LTS development specialist covering Spring Boot 3.3, virtual threads, pattern matching, and enterprise patterns. Use when building enterprise applications, microservices, or Spring projects.

SPEC workflow orchestration using the EARS format, requirement clarification process, and Plan-Run-Sync integration for the JikiME-ADK development methodology

Fetch additional context from the platform, including recent messages, search through conversation history, or get user information. Use when you need more context than what's provided initially.

List all active reminders for the current user

For pathfinding and search: shortest path, maze solving, game AI, route planning, graph traversal, BFS/DFS, Dijkstra, A* problems.

For tree/maze generation: spanning trees, random mazes, graph coverage. Uses frontier-based exploration with configurable traversal order.

For interpreters: separate lexing from parsing, token stream to AST, structured text processing in stages.

Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like "the xlsx in my downloads") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved.

Apply targeted corrections for CRITICAL and MAJOR code review issues

Full pipeline orchestrator — executes tasks, validates, reviews, fixes, and generates a summary report

Deploys and manages NVIDIA Triton Inference Server containers. Automates model repository setup, config generation, and health checks. Use for "triton server", "triton run", "model serving", "inference server" requests.

Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.

Serves LLMs with high throughput using vLLM's PagedAttention and continuous batching. Use when deploying production LLM APIs, optimizing inference latency/throughput, or serving models with limited GPU memory. Supports OpenAI-compatible endpoints, quantization (GPTQ/AWQ/FP8), and tensor parallelism.