>-
Skills（SKILL.md）は、AIエージェント（Claude Code、Cursor、Codexなど）に特定の能力を追加するための設定ファイルです。
詳しく見る →當使用者要求「分析資料、報表摘要、數據趨勢、建儀表板、處理 CSV/Excel、做資料視覺化」時使用。引導以結構化方式做資料分析、摘要與圖表，並可與本專案 data_analyst_agent、echarts、RAG 整合。
Helps with idea overload and prioritization. **Capture first, triage later** — keep a local backlog before promoting to GitHub. Prevents losing ideas without the friction of creating issues for half-b
Inclui uma figura estática ou gerada neste livro em mdBook. Use quando a tarefa envolver adicionar uma imagem, SVG, asset de terceiro ou ilustração gerada por scripts para algum capítulo.
Construção de dashboards Grafana orientados a operação, incidentes e acompanhamento de saúde de serviços.
'Route an approved workspace or orchestration phase into concurrent repo-targeted initiative workstreams. Use after Phase Sync when execution scope is workspace or orchestration.'
Load data for TanStack Start routes using beforeLoad and loader functions. Use when fetching data for pages, implementing route guards, or setting up route context. IMPORTANT - Loaders should call server functions for data access.
UI/UX design intelligence with searchable database
Estrategia de marca, identidade visual, brandbook, auditoria de marca
INVOKE THIS SKILL when setting up a new project or when asked about package versions, installation, or dependency management for LangChain, LangGraph, LangSmith, or Deep Agents. Covers required packages, minimum versions, environment requirements, versioning best practices, and common community tool packages for both Python and TypeScript.
INVOKE THIS SKILL when implementing human-in-the-loop patterns, pausing for approval, or handling errors in LangGraph. Covers interrupt(), Command(resume=...), approval/validation workflows, and the 4-tier error handling strategy.
Load and follow the skill at `{project-root}/_bmad/bmm/2-plan-workflows/bmad-edit-prd/SKILL.md`.
Load and follow the skill at `{project-root}/_bmad/bmm/4-implementation/bmad-sprint-status/SKILL.md`.
'Facilitate interactive brainstorming sessions using diverse creative techniques and ideation methods. Use when the user says help me brainstorm or help me ideate.'
Transform any structured CSV or Excel file into a polished React dashboard with KPI cards,
Load and follow the skill at `{project-root}/_bmad/compass/1-analysis/bmad-compass-ingest-whitepapers/SKILL.md`.
ESP32 Pro Master Skill - Engenharia de Firmware Avançada
Scene understanding and analysis. Use when users want to get a summary, overview, dependency report, or export of the current scene state. Triggers: scene summary, analyze, overview, statistics, count, export report, 场景摘要, Unity分析, Unity概览, Unity统计, 导出报告, 依赖分析.
Portable tmux-based workflow to drive one or multiple long-running Codex CLI “workers” from another process (e.g. Claude CLI) by (1) starting/reusing a tmux session running `codex`, (2) injecting prompts into the Codex pane via `tmux send-keys`/buffer paste, and (3) polling the worker’s Codex JSONL session logs to extract the next assistant reply. Each worker runs with an isolated `CODEX_HOME` (default `~/.codex-workers/<worker_id>`) to prevent log cross-talk when multiple Codex workers run concurrently. Use when you need to submit/wait/read Codex replies in tmux, manage multiple Codex workers, or troubleshoot the tmux worker and log binding.
Use when preparing a Formax code handoff: selecting files, generating repomix bundles, and writing a high-quality prompt for WebGPT or another coding agent with clear constraints and validation scope.
Meta Ads, Google Ads, campanhas, otimizacao, criativos, budget
CRITICAL: Use for ownership/borrow/lifetime issues. Triggers: E0382, E0597, E0506, E0507, E0515, E0716, E0106, value moved, borrowed value does not live long enough, cannot move out of, use of moved value, ownership, borrow, lifetime, 'a, 'static, move, clone, Copy, 所有权, 借用, 生命周期
Product Manager (Morgan). Use for PRD creation (greenfield and brownfield), epic creation and management, product strategy and vision, feature prioritization (MoSCoW, RICE), roa...
Load and follow the skill at `{project-root}/_bmad/compass/planning/bmad-compass-init-planning/SKILL.md`.
1. imageloader 的话自己怎么设计这个功能
自动化处理 Word 和 Excel 文件。使用 Python 脚本读取、写入、格式化文档和表格。支持批量处理、模板填充、数据提取和格式转换。
The universal tool adapter for AI agents. Search, install, and run packages from the anyclaw registry. Use anyclaw to access web APIs, data pipelines, CLI tools, and scripts as unified commands.
Free YouTube video downloading, transcript extraction, and metadata retrieval using yt-dlp. Use this skill for downloading YouTube videos (single or bulk), extracting transcripts/subtitles, getting video metadata, or downloading audio-only. This is FREE (no API keys) unlike Apify. Triggers on YouTube download requests, transcript extraction, video metadata, or bulk video downloads.
front_setback: 3.0
Compose multi-agent systems with SequentialAgent, ParallelAgent, and LoopAgent. Use when building agent pipelines, parallel workflows, or iterative loops.
Collaborate in Nereid Mermaid sessions via MCP using AST-first, probe-refine workflows for sequence diagrams, flowcharts, xrefs, routes, and walkthroughs. Use when exploring or editing diagrams with a human watching live in TUI, and when coordinating attention through `attention.*`, `follow_ai.*`, and `selection.*`.
Reconcile one active execution slice, optionally execute owner-chain routing, and persist checkpointed resume context for one-slice acceleration.
Use this skill when the user wants questions that make the agent first figure out *which table matters* before doing the math. Trigger it for requests such as “make it search the right sheet first,” “make it find the relevant table from a pile of files,” “make the question depend on the correct spreadsheet,” or “make it choose the right data source before answering.” Also trigger it when the task should feel like open-domain analytics over many tables, not direct computation over a table that is already handed to the agent. Plain-language examples: “Ask something where the answer is hidden in one of many datasets,” “make it pick the right table by itself,” “make it search through messy tabular data first.”
Use when user shows signs of overwhelm or frustration — repeated failed attempts, tone shifts, sudden brevity, topic abandonment. Guides gentle check-ins without being patronizing or clinical.
Archive Behance projects to Eagle DAM (Digital Asset Management) library. Use when user wants to archive or save a Behance project URL to their Eagle collection with proper metadata. Triggers include requests like '归档 https://www.behance.net/gallery/...', '保存 Behance 项目', 'archive behance project', or any request to download or save Behance gallery content to local Eagle library.
Turn user interviews into actionable insights. Advanced synthesis techniques and frameworks.
**Purpose**: Apply a structured analytical framework to any document, extracting non-obvious insights, tensions, actionable implications, and gaps — going far beyond a generic summary.
'Analyze a screen recording of a manual process and produce targeted, working automation scripts. Extracts frames and audio narration from video files, reconstructs the step-by-step workflow, and proposes automation at multiple complexity levels using tools already installed on the user machine.'
Retrieve and display GitHub Copilot usage metrics for organizations and enterprises using the GitHub CLI and REST API.
Build and scale developer-led adoption through ecosystem programs. Use when deciding open vs curated ecosystems, building developer programs, scaling platform adoption, or designing student program pipelines.
Build and scale partner ecosystems that drive revenue and platform adoption. Use when building partner programs from scratch, tiering partnerships, managing co-marketing, making build-vs-partner decisions, or structuring crawl-walk-run partner deployment.
'Skill for using the command-line tool pdftk (PDFtk Server) for working with PDF files. Use when asked to merge PDFs, split PDFs, rotate pages, encrypt or decrypt PDFs, fill PDF forms, apply watermarks, stamp overlays, extract metadata, burst documents into pages, repair corrupted PDFs, attach or extract files, or perform any PDF manipulation from the command line.'
Guides Qdrant monitoring setup including Prometheus scraping, health probes, Hybrid Cloud metrics, alerting, and log centralization. Use when someone asks 'how to set up monitoring', 'Prometheus config', 'Grafana dashboard', 'health check endpoints', 'how to scrape Hybrid Cloud', 'what alerts to set', 'how to centralize logs', or 'audit logging'.