数据与 AI技能

Exploratory data analysis. Use when users upload .csv/.xlsx/.json/.parquet files or request "explore data", "analyze dataset", "EDA", "profile data". Small files get ydata-profiling HTML/JSON reports; large files (over 200MB or 5M rows) get fixed-memory DuckDB/sketch profiling. Also covers near-duplicate row detection, cross-file key overlap ("can these join?"), dataset drift vs a stored baseline, and time-series profiling.

中文简介正在准备中。当前显示原文说明。

Select the right Python charting library (seaborn, matplotlib, graphviz) and produce publication-quality static visualizations. Use when creating charts, plots, graphs, diagrams, heatmaps, visualizations from data, or when choosing between matplotlib/seaborn/graphviz. Also triggers for network diagrams, flowcharts, dependency trees, state machines, and entity-relationship diagrams. For interactive browser-rendered charts or uploaded data exploration, defer to charting-vega-lite instead.

中文简介正在准备中。当前显示原文说明。

Composes single-file HTML artifacts (PR review writeups, status reports, incident postmortems, slide decks, design systems, prototypes, flowcharts, module maps, feature explainers, kanban boards, prompt tuners) from a small JSON spec instead of hand-written HTML/CSS/JS. Use when the user asks to "compare options side-by-side", requests an HTML version of a report or review or deck, asks for a flowchart, status update, postmortem, design system reference, interactive prototype, custom editor — or explicitly says "HTML artifact", "single HTML file", "self-contained HTML". Skip for ad-hoc HTML snippets (forms, emails, embedded widgets) where there's no template fit.

中文简介正在准备中。当前显示原文说明。

Builds a portable, embedding-free knowledgebase from a set of files and delivers it as a self-contained `.skill` bundle (BM25 index + bundled searcher + query protocol). Use when a user wants to turn uploaded files, a folder, or a corpus into a searchable knowledgebase they can hand to any agent — phrased as "make a knowledgebase", "build a KB skill", "package these docs for retrieval", "create a searchable bundle", or references to a `.skill` KB. The output runs anywhere with Node or Python — no model, no install, no network. Distinct from `bm25` (ephemeral in-session search) and `building-github-index` (markdown project-knowledge index).

中文简介正在准备中。当前显示原文说明。

Builds and revises a complete skill DIRECTORY — SKILL.md, scripts, references, assets — and packages it. Use for "create a skill for X", "turn this into a skill", "update/improve this skill", "why doesn't my skill trigger", "review this SKILL.md", "package this skill", or when a repeated procedure should become a reusable artifact. Enforces the structure that makes skills work — a concrete procedure rather than a goal statement, an explicit applicability boundary, failure modes with their signals, a runtime verification step, and a description checked against the existing catalogue for confusability. For choosing whether the instruction should be a skill at all rather than project instructions or a prompt, use crafting-instructions. For writing quality inside the prose, use writing-instructions.

中文简介正在准备中。当前显示原文说明。

Delegates work to a subagent or spawned session by writing only the task, while a PreToolUse hook pages the parent transcript through Jev and appends the chunks that task needs. Use before writing any Agent tool prompt or create_session prompt, and when asked to delegate this, hand this off, use a subagent, spawn an agent, run agents in parallel, or brief a subagent on what we have done so far.

中文简介正在准备中。当前显示原文说明。

Text-prompted image zone detection using TIPSv2 B/14 on CPU. Produces `focus_targets` / `focus_edges` bbox lists from natural-language labels, ready to feed into `svg-portrait-mode`. Use when you want automatic foreground/background separation from prompts like "dog face" + "wooden floor" instead of hand-annotating bboxes.

中文简介正在准备中。当前显示原文说明。

Zero-shot univariate time series forecasting using the Reverso foundation model (NumPy/Numba CPU-only inference). Activate when users provide time series data and request forecasts, predictions, or extrapolations. Supports Reverso Small (550K params). Triggers on "forecast", "predict", "time series", "Reverso", or when tabular data with a temporal dimension needs future-value estimation.

中文简介正在准备中。当前显示原文说明。

Create interactive data visualizations using Vega-Lite declarative JSON grammar. Supports 20+ chart types (bar, line, scatter, histogram, boxplot, grouped/stacked variations, etc.) via templates and programmatic builders. Use when users upload data for charting, request specific chart types, or mention visualizations. Produces portable JSON specs with inline data islands that work in Claude artifacts and can be adapted for production.

中文简介正在准备中。当前显示原文说明。

Practical prompt patterns and techniques for effective Claude Code usage. Reference when crafting prompts, planning workflows, or debugging interactions.

中文简介正在准备中。当前显示原文说明。

ClickHouse database patterns, query optimization, analytics, and data engineering best practices for high-performance analytical workloads.

中文简介正在准备中。当前显示原文说明。

Use when operating peky from the CLI or TUI, especially for AI agents who need reliable, low-error procedures. Covers how to target sessions/panes correctly, use scopes, avoid confirmation prompts, and keep CLI/TUI/daemon in sync.

中文简介正在准备中。当前显示原文说明。

Judges whether a user's input suits the Vibe Creating style of video-prompt writing, and when it does, distills single-scene prompts, multi-shot descriptions, emotional imagery, or mixed input into prompts that are easier for a video model to generate from — while preserving any user-specified dialogue, voiceover, music, sound effects, and other hard constraints. Use when a user wants to turn an idea, story, feeling, or rough/over-specified prompt into a strong text-to-video prompt (Seedance, Sora, Kling, Veo, Runway, etc.), or asks to "rewrite", "improve", "clean up", or "vibe-ify" a video prompt. Do NOT use for long narrative films that need precise word-for-word dialogue sync, industrial shot lists meant to be executed verbatim, or functional/UI demos and step-by-step tutorials.

中文简介正在准备中。当前显示原文说明。

Decide and implement how to support a new LLM provider or agent engine in AWF - either as a proxied provider (api-proxy adapter) or a direct-API engine (domain allowlist only), e.g. Cursor, Aider, or any tool that calls its own endpoint.

中文简介正在准备中。当前显示原文说明。

Stream-JSON chaining for multi-agent pipelines, data transformation, and sequential workflows

中文简介正在准备中。当前显示原文说明。

Implement semantic vector search with AgentDB for intelligent document retrieval, similarity matching, and context-aware querying. Use when building RAG systems, semantic search engines, or intelligent knowledge bases.

中文简介正在准备中。当前显示原文说明。

Read your X (Twitter) audience and niche from real data. Pull a handle's recent tweets (yours or a competitor's) with likes, replies, and views, see which formats and hooks are working, read the repliers on a tweet (X gates likers, so repliers are the signal), and scan a niche query for top tweets. Powered by Apify, no login. Triggers on "analyze my tweets", "what is working on X", "read the replies", "competitor tweets", "who is engaging". Not for writing a tweet (use x-post-writer).

中文简介正在准备中。当前显示原文说明。

使用 ArkCLI 创建、查询和管理模型精调训练任务，并从训练指标选择最佳 step、导出训练产物为 custom model、衔接模型仓库与推理部署。任何包含精调任务 ID（`mcj-*`）的查询、查不到原因诊断、日志、trajectory、状态或生命周期操作都应使用本 skill；也适用于选择训练方法、查询精调价格和超参数、校验精调训练/验证数据、匹配精调资源组、创建任务及导出部署。本 skill 不负责独立 Dataset 生命周期管理；精调工作流中的数据校验和 Dataset 引用仍由本 skill 编排。

中文简介正在准备中。当前显示原文说明。

使用 ArkCLI 创建、校验、查询、更新、删除、版本化和下载 Dataset。用户提到 Dataset、数据集、ds-*、dsv-*、训练集/验证集复用、数据格式校验或把 Dataset 接入精调任务时使用。

中文简介正在准备中。当前显示原文说明。

Route HugeGraph MCP graph data extraction and controlled import/delete tasks to stable public tools. Use when the user asks to extract graph data from text, import structured vertices or edges, verify an import, or asks whether table, SQL, update, or delete graph writes are available.

中文简介正在准备中。当前显示原文说明。

Use when code needs a judgment about natural language that rules or regex cannot make (classify, route, triage, moderate, score, rank, match, dedupe, filter, extract, verify, or gate an action), when brainstorming where AI could fit in an app, when an LLM call exists only to pick a label, score, or yes/no, or when code uses TypeSafe AI, Jev, System One, typesafe-sdk, or @typesafe-ai/sdk.

中文简介正在准备中。当前显示原文说明。

Use when you need GA4 + GTM tracking delivery from site discovery through publish, or when the right phase entry point is still unclear.

中文简介正在准备中。当前显示原文说明。

コミュニケーション診断ツール（commu-checker）の各タイプ向け、90日トレーニングコンテンツを生成するスキル。 ユーザーが「D1型のトレーニングを作って」「〇〇型の90日プランを作りたい」「training-data.jsに追加したい」 「コミュ診断のトレーニングページ」などと言ったときに必ず使う。 タイプ定義・観察メモを受け取り、既存サイト（M PLUS Rounded 1c・グリーン基調・Material Icons）に合わせた インタラクティブなチェックリスト用HTMLコンテンツを training-data.js の TRAINING_PAGES オブジェクトに追加する形で出力する。 トレーニングは trainings/index.html + trainings/training-app.js + trainings/training-data.js の3ファイル構成。 個別の <type>.html は存在せず、URL の ?type=d1 などのパラメータで表示タイプを切り替える。

中文简介正在准备中。当前显示原文说明。

Tabs swap views under a shared context. Use when designing tabbed layouts, settings pages, detail views or dashboards with several data views.

中文简介正在准备中。当前显示原文说明。