Data analysis, machine learning, LLM apps, and prompt design (8.9K skills)
Query foreign LLM for chat. Use this skill if a foreign LLM like OpenAI ChatGPT, Google Gemini, DeepSeek or xAI Grok should be queried with a single chat message.
The English summary is being prepared. Showing the original description.
将 SRT 字幕文件转换为结构化 JSON 数据。 触发场景： (1) 需要解析 SRT 字幕文件 (2) 需要将字幕转为 JSON/结构化格式 (3) 需要提取字幕时间码和文本 (4) 视频字幕数据处理和分析 (5) 生成字幕纯文本或统计信息
The English summary is being prepared. Showing the original description.
Handle PR review feedback - understand reviewer comments, research their concerns, and help the user address them. The LLM explains what reviewers want and why; the user decides how to respond and writes the code. Use when you receive review comments on a submitted PR. Not for opening the PR in the first place, which is oss-submit-pr. If the feedback is a failing CI job, use oss-debug-ci.
The English summary is being prepared. Showing the original description.
Reverse-engineer a supplied video into a shot-by-shot generation specification, displayed evidence frames, and paired Chinese-English prompt packages. Use for requests such as 视频反推提示词, 视频转提示词, 从视频生成提示词, 视频逆向提示词, 逐镜头反推, 分镜拆解并生成提示词, 反推视频 prompt, or video-to-prompt; also use for Veo, Sora, Kling, Wan, generic prompt adaptation, and bounded generate-compare-optimize loops. Do not use for ordinary video summaries or basic transcription.
The English summary is being prepared. Showing the original description.
Icarus Figures produces publication-grade figures for scientific papers — reproducible matplotlib/seaborn data figures and original TikZ method/framework/architecture figures, held to a four-axis quality bar (depth · elegance · unimpeachable · visible-gap) and exported as editable PDF+PNG+SVG with a runnable critique gate. Use this whenever a figure is destined for a paper, journal, conference submission, thesis, or report — making a plot/chart publication- or journal-ready, building a method/architecture/framework diagram or 技术路线图 (the hero figure a paper opens with), a schematic or workflow figure, or cleaning up a matplotlib/seaborn/TikZ figure that currently looks like a homework plot. Trigger even when the user never says "publication": if the figure goes into a written scientific document, this skill applies.
The English summary is being prepared. Showing the original description.
Intelligent pattern selection for Fabric CLI. Automatically selects the right pattern from 242+ specialized prompts based on your intent - threat modeling, analysis, summarization, content creation, extraction, and more. USE WHEN processing content, analyzing data, creating summaries, threat modeling, or transforming text.
The English summary is being prepared. Showing the original description.
Prompt engineering standards and context engineering principles for AI agents based on Anthropic best practices. Covers clarity, structure, progressive discovery, and optimization for signal-to-noise ratio.
The English summary is being prepared. Showing the original description.
Fetches tweets from Twitter List, scores them using data metrics and AI analysis, and generates topic recommendation reports for content creators.
The English summary is being prepared. Showing the original description.
Use when the user wants to publish or schedule a LinkedIn post through Publora: text, a multi-image grid, a video, a PDF document, or @mentions. Not for analytics, reactions, comments or reshares (use linkedin-analytics), and not for other platforms.
The English summary is being prepared. Showing the original description.
Analyze LinkedIn performance and manage engagement through Publora. Use when the user asks how a LinkedIn post or account performed (impressions, reach, reactions, comments, reshares, follower growth) or wants to react, comment, reshare or resolve an @mention. Statistics run over the REST API, engagement over MCP tools. Not for creating posts (use linkedin-post).
The English summary is being prepared. Showing the original description.
LLM brand manipulation — build a consensus web so ChatGPT, Claude, Perplexity, and Google AI Overviews mention your brand when people ask about your category. Uses surround sound methodology, entity SEO, and LLM citation science. Use when "get mentioned in AI", "LLM brand presence", "surround sound", "AI search visibility", "Perplexity ranking", "ChatGPT mentions", "AI Overview inclusion", "entity authority", "brand mentions in AI", or any request to influence how AI systems perceive and recommend your brand.
The English summary is being prepared. Showing the original description.
Build and maintain a provenance-clean proof library — inventory every real proof asset (analytics, reviews, permitted testimonials, case studies, press, certifications), categorize it, rewrite each cleared item in 3 lengths, fuse top assets with narrative, and gate everything through FTC testimonial rules before it can ship. Use when "proof library", "gather our proof", "authority builder", "collect testimonials", "social proof assets", "proof points for the sales page", "what results can we claim", or any request to assemble evidence for marketing claims. NEVER invents proof — missing proof is reported as a gap.
The English summary is being prepared. Showing the original description.
Build a plug-in-ready SDR operator package for sales development and outbound pipeline work: ICP definition, compliant lead-source plan, enrichment/research workflow, account scoring, outbound assets, CRM handoff, reply triage, meeting prep, approval gates, and loop memory. Use when "SDR", "sales development", "outbound SDR", "operator room", "lead gen pipeline", "prospecting pipeline", "ICP targeting", "Apify", "RapidAPI", "Clay", "Apollo", "agentic SDR workflow", "sales operating loop", "sales dashboard handoff", or any request to package outbound sales workflows that can later connect to data tools, CRMs, or operator surfaces.
The English summary is being prepared. Showing the original description.
Convert Kai workflow data, CSV exports, audit folders, SDR package outputs, and marketing reports into dashboard-ready specs or lightweight static dashboards. Use when "data dashboard", "operator dashboard", "operator room", "HTML operators room", "sales dashboard", "SDR dashboard", "turn this data into a dashboard", "dashboard handoff", "visualize Kai data", or any request to package sourced marketing, sales, audit, or SDR data for a dashboard or presentation surface.
The English summary is being prepared. Showing the original description.
Analytics and attribution setup — tracking plan, UTM conventions, dashboard design, and attribution model selection. Use when "analytics setup", "attribution", "tracking plan", "UTM", "marketing analytics", "dashboard setup", "measurement strategy", "how do I track", "which metrics", or any request to set up or improve marketing measurement and attribution.
The English summary is being prepared. Showing the original description.
Pull performance data for published content across every surface — LinkedIn, Dev.to, Google Search Console, GA4, and AI citation tracking (Perplexity, Anthropic, OpenAI). Grades each piece as winner, average, or underperformer and surfaces whether an AI search engine has cited it.
The English summary is being prepared. Showing the original description.
Generate a strategic content brief from format + site + keyword. Auto-resolves persona, pulls GSC data, generates hooks, angles, and competitor weakness via LLM.
The English summary is being prepared. Showing the original description.
Suggest content topics ranked by opportunity score. Analyzes GSC keyword data and cross-references with personas to find high-potential topics.
The English summary is being prepared. Showing the original description.
On-Chain Analytics Agent — whale movements, exchange flows, active addresses, network growth, holder distribution, and transaction metrics with On-Chain Score (0-100)
The English summary is being prepared. Showing the original description.
当用户要写出高质量 Goal Prompt，把模糊、战略性、多步骤、证据不足、持续/自动化或容易跑偏的请求整理成可执行、可验证、可暂停的目标契约时使用。适用于写 goal、优化任务提示词、明确 done/success criteria、deep research 后定战略、大改前 inventory、修复跑偏计划、识别可委托的重复 workflow、为 Codex 或 Claude Code 准备执行任务；默认一次性交付只生成 Goal Prompt，只有存在真实后续迭代需求时才追加 Loop Prompt，不执行 goal 或 loop，也不创建自动化。
The English summary is being prepared. Showing the original description.
Pre-landing PR review. Analyzes diff against the base branch for SQL safety, LLM trust boundary violations, conditional side effects, and other structural issues.
The English summary is being prepared. Showing the original description.
Use when the user wants to set up the evolver in their project, optimize an LLM agent, improve agent performance, or mentions evolver for the first time in a project without .evolver.json.
The English summary is being prepared. Showing the original description.
弗洛伊德.skill：给AI做心理分析的认知调优系统。基于Anthropic AI心理学研究（Persona Selection Model、全局工作空间/J-lens、Emotion Concepts、Introspective Awareness等7篇论文）。 两种模式：(1)执行增强——处理复杂任务前给AI做「认知准备」，像心理咨询师让来访者进入最佳状态；(2)诊断优化——用精神分析手法揭示prompt/skill/系统提示的身份冲突、规则堆砌、隐含矛盾等深层毛病，并重写。 当用户提到"优化表现"、"调优"、"输出不够好"、"风格不稳定"、"persona"、"认知配置"、"优化prompt"、"优化skill"、"弗洛伊德"、"心理分析"、"给AI看心理医生"、"给prompt做体检"时使用。 当用户开始重要/复杂任务但方向不明确、觉得之前的输出质量不够好、或想理解为什么某个prompt/skill有效或无效时，也应主动考虑使用。 即使用户只是说"帮我想想怎么做更好"、"这个结果不对味"、"为什么效果不好"也应触发。
The English summary is being prepared. Showing the original description.
Search and read locally-stored Claude documentation covering Claude Code CLI, Claude API (Messages, tool use, vision, streaming, batch), Agent SDK (Python and TypeScript), prompt engineering, and all Anthropic platform docs. Use this skill whenever the user asks about Claude Code features (hooks, MCP servers, skills, plugins, settings, permissions, keybindings, sub-agents), the Anthropic API or any of its SDKs (Python, TypeScript, Go, Java), the Agent SDK (sessions, hooks, custom tools, MCP), model capabilities (context windows, extended thinking, pricing, rate limits, vision), prompt engineering best practices, or troubleshooting any Claude-related error. This skill provides instant access to official documentation files without web searches — always prefer it over web lookups for Claude and Anthropic topics.
The English summary is being prepared. Showing the original description.