Data analysis, machine learning, LLM apps, and prompt design (9.1K skills)
Guides evaluation of RAG pipeline retrieval and generation quality. Use when evaluating a retrieval-augmented generation system, measuring retrieval quality, assessing generation faithfulness or relevance, generating synthetic QA pairs for retrieval testing, or optimizing chunking strategies.
The English summary is being prepared. Showing the original description.
Build a custom browser-based annotation interface tailored to your data for reviewing LLM traces and collecting structured feedback. Use when you need to build an annotation tool, review traces, or collect human labels.
The English summary is being prepared. Showing the original description.
Create diverse synthetic test inputs for LLM pipeline evaluation using dimension-based tuple generation. Use when bootstrapping an eval dataset, when real user data is sparse, or when stress-testing specific failure hypotheses. Do NOT use when you already have 100+ representative real traces (use stratified sampling instead), or when the task is collecting production logs.
The English summary is being prepared. Showing the original description.
Design LLM-as-Judge evaluators for subjective criteria that code-based checks cannot handle. Use when a failure mode requires interpretation (tone, faithfulness, relevance, completeness). Do NOT use when the failure mode can be checked with code (regex, schema validation, execution tests); use `write-code-eval`. To validate an existing judge, use `validate-evaluator`.
The English summary is being prepared. Showing the original description.
Comprehensive diagnostic analysis of time series data. Use when users provide CSV time series data and want to understand its characteristics before forecasting - stationarity, seasonality, trend, forecastability, and transform recommendations.
The English summary is being prepared. Showing the original description.
Generate and render Mermaid diagrams for architecture docs, READMEs, PRs, terminals, chats, and CI as themed SVG, PNG, or ASCII/Unicode art. Use this skill whenever the user provides Mermaid code or .mmd files; asks for a flowchart, sequence/state/class diagram, ERD, XY chart, or architecture/workflow/data-model visualization; or wants to beautify, theme, batch-convert, or make a diagram terminal-friendly. Runs locally without a browser or DOM, with 15 built-in themes and custom colors.
The English summary is being prepared. Showing the original description.
Run /develop to build a feature, UI or backend, from an approved design, a page, component, API, service, or data slice. If something load bearing is undecided and no spec records it, it stops and routes you to /architect; otherwise it reads the spec plus AGENTS.md, builds, and advances the scope.
The English summary is being prepared. Showing the original description.
提示词分析与洞察 - 查看Prompt详情、对比差异、推荐相似提示词、元素库统计
The English summary is being prepared. Showing the original description.
智能提示词生成器 v2.0 - 支持人像/跨domain/设计三种模式，语义理解、常识推理、一致性检查
The English summary is being prepared. Showing the original description.
Gangtise (岗底斯投研) OpenAPI skill suite installer and diagnostic tool. One-click install 19 official skills (data, research, utility), configure accessKey/secretAccessKey, run health diagnostics. Trigger when user mentions Gangtise, 岗底斯, any gangtise-* skill, credential setup, or reports errors like 'token is invalid' / '接口地址错误'.
The English summary is being prepared. Showing the original description.
Collects real financial data for any US publicly traded company from free public sources (yfinance) and outputs structured JSON for downstream skills (DCF modeling, comps analysis, earnings review): market data, historical financials, WACC inputs, analyst estimates — never fabricated fallback values. Use to collect or pull financial/market data, or gather DCF inputs, for a ticker.
The English summary is being prepared. Showing the original description.
Diagnoses and repairs macOS TCC dialogs and silent denials: Full Disk Access, Screen Recording, Microphone, Camera, Accessibility, Automation. Use for recurring prompts, LaunchAgent/uv jobs that fail only in background, broken grants, or automating Full Disk Access (权限弹窗 / 授权了没用 / 完全磁盘访问). Checks requester and grants first. Not for launchd design (macos-watchdog) or app permission UX (developing-ios-apps).
The English summary is being prepared. Showing the original description.
Pulls Bigdata.com (RavenPack) financial and news data via the official bigdata-client SDK and /v1/* REST endpoints — structured financials, prices, analyst estimates, entity-sentiment series, annotated chunk search, screener. Use when the Bigdata MCP's tearsheets/search feel thin and you need the machine-readable substrate: mentions of Bigdata.com, RavenPack, a bd_v2_ key, rp_entity_id, or chunk/query_unit cost.
The English summary is being prepared. Showing the original description.
Faithfully archive public WPS/KDocs/金山文档 links, especially embedded ProcessOn .pof mind maps and canvases, as raw source data, original SVG/PNG, and Markdown. Use when a user gives a kdocs.cn or wps.processon.com link and asks to scrape, save, download, 扒下来, 归档, or 转 Markdown without logging in or saving the document to an account.
The English summary is being prepared. Showing the original description.
Finding and accessing AI/LLM model brand icons from lobe-icons library. Use when users need icon URLs, want to download brand logos for AI models/providers/applications (Claude, GPT, Gemini, etc.), or request icons in SVG/PNG/WEBP formats.
The English summary is being prepared. Showing the original description.
Produces the reader-facing HTML artifact — report, dashboard, architecture view, data browser, or review workbench — evidence-backed, browser-verified. Use when the deliverable IS a visual HTML report, or the user asks for an HTML/web presentation. Load data-visualization-discipline for chart judgment. Not for chat status or Markdown prose unless asked to become a report; not for PowerPoint (deck-creator Route C).
The English summary is being prepared. Showing the original description.
Configures and runs LLM evaluation using Promptfoo framework. Use when setting up prompt testing, creating evaluation configs (promptfooconfig.yaml), writing Python custom assertions, implementing llm-rubric for LLM-as-judge, or managing few-shot examples in prompts. Triggers on keywords like "promptfoo", "eval", "LLM evaluation", "prompt testing", or "model comparison".
The English summary is being prepared. Showing the original description.
Co-creates a personal investment-research LLM Wiki (Karpathy's pattern) by interviewing the user for THEIR OWN analysis framework, not a template — a living CLAUDE.md of pure markdown + wikilinks, no RAG in place of compilation. Use to build a compounding 投研第二大脑 / 投研知识库 / 个人投研 wiki, ingest research reports / earnings calls into an existing wiki, or run post-earnings prediction→fulfillment reviews.
The English summary is being prepared. Showing the original description.
Tests/benchmarks a third-party LLM endpoint (OpenAI- or Anthropic-compatible): availability, fidelity, speed, concurrency, protocol compliance, quality regression. Use before hand-rolling a curl loop, when onboarding a provider, or debugging "system prompt 不生效" / a tok/s claim — 测评/压测一个模型或渠道. Not for TTS/voice-clone supplier eval (use the audio skill).
The English summary is being prepared. Showing the original description.
Scans and removes sensitive data (secrets, API keys, private domains/IPs, PII) from GitHub repository history, then verifies and force-pushes safely. Use for 清理敏感数据 / 历史重写 / 泄露, "scan sensitive data", "clean git history", "remove secrets from repo", or before any force push to a public repo. Not for local-only Git recovery (use git-safety-net) or ordinary repository setup (use auto-repo-setup).
The English summary is being prepared. Showing the original description.
Verifies factual claims in documents using web search and official sources, then proposes corrections with user confirmation. Use when the user asks to fact-check, verify information, validate claims, check accuracy, or update outdated information in documents. Supports AI model specs, technical documentation, statistics, and general factual statements.
The English summary is being prepared. Showing the original description.
Fetches real, citable Bilibili (B站) video data — stats, metadata, tags, and full danmaku text — via login-free API calls, never hand-typed or estimated. Use when citing view/like/favorite counts, analyzing why a video performed, or archiving a Bilibili source into a knowledge base. Accepts BVID, av numbers, b23.tv links, or full URLs; subtitles and 收藏夹 (favorites) enumeration need the user's Bilibili login.
The English summary is being prepared. Showing the original description.
Two scopes: (1) drives Kimi.app via computer-use for Work/Agent data-plugin queries (天眼查、同花顺 iFinD、SEC、IMF etc.) and Chat's built-in 深度研究 report; (2) kimi-cu macOS desktop-automation playbook — AX set_value / keyboard / click channel selection, foregrounding, AX-tree recovery, form & dialog recipes. Use for "用 Kimi 查" / "操作 Kimi 客户端" / "Kimi 插件" / "Kimi 深度研究" / driving any macOS desktop app (Electron/webview/native) via kimi-cu. Not for kimi.com browser automation (use kimi-webbridge) or direct iFinD API access.
The English summary is being prepared. Showing the original description.
Extracts Feishu/Lark Docs, Wiki, Sheets, and Minutes (妙记) transcripts into faithful local Markdown via the lark-cli API — no LLM paraphrasing, browser-DOM fallback when lark-cli can't reach content. Use whenever the source is a Feishu/Lark URL and fidelity matters — 导出飞书文档/合集/妙记转写, 把飞书 wiki 转 markdown, or archiving a collection — even if the user just says "save this". Also covers owner-exported .docx → Markdown.
The English summary is being prepared. Showing the original description.