Prompts
Prompt engineering and templates
clarify-spec
by Svenja-dev
AKTIVIERT SICH AUTOMATISCH bei vagen Auftraegen. LIEBER EINMAL ZU OFT NACHFRAGEN als falsch implementieren. Erkennungsmerkmale (EINES genuegt!): - Auftrag <25 Woerter - Keine konkreten Dateinamen/Pfade - Vage Verben: besser, optimieren, fixen, machen, aendern, verbessern, anpassen, erweitern, refactoren, aufraumen, ueberarbeiten - Unsichere Sprache: irgendwie, vielleicht, mal eben, schnell, einfach, bisschen, koennte, sollte - Fehlende Erfolgskriterien: Kein damit, sodass, weil, um zu - Relative Begriffe ohne Kontext: schneller, besser, schoener, einfacher Output ist STRUKTURIERTES JSON fuer prompt-architect Skill. Escape: mach einfach, keine Rueckfragen, entscheide selbst ueberspringt Klaerung.
knowledge-pipline
by YesIamGodt
"多模态知识管道技能 — 摄入文档(PDF/图片/视频/Office)到持久化知识维基，支持知识融合、跨源矛盾检测、多源聚合查询、知识图谱构建。当用户提到摄入文档、构建知识库、查询维基、检查一致性、构建知识图谱、文档分析、多模态理解、数据管道等需求时触发此技能。即使用户没有明确说 pipeline 或 knowledge-pipline，只要涉及将文档转化为结构化知识、跨文档分析对比、或知识图谱可视化，都应触发此技能。"
linkedin-engagement
by Svenja-dev
LinkedIn Content-Erstellung, Engagement und Monitoring für B2B/Manufacturing. Regionale Anpassung (US/EU/Asien), Artikel mit Teasern, Bildgenerierung via Gemini, Kommentar-Monitoring.
prompt-architect
by Svenja-dev
Transformiert Anforderungen in Best-Practice Prompts nach Claude 4.x Standards (Dezember 2025). Basiert auf: - Nate B. Jones 4 Beginner Moves: Shape, Context, Silent Plan, Self-Check - Anthropic Claude 4.x Best Practices: Explizitheit, Contract-Style, Examples beat Adjectives - Pipelines over Prompts Philosophie AKTIVIERT SICH AUTOMATISCH nach clarify-spec oder bei /prompt-architect. Produziert strukturierten, ausfuehrbaren Prompt mit allen Best Practices.
multi-llm-advisor
by Svenja-dev
Fetches additional perspectives from OpenAI Codex and Google Gemini for architecture, review, and debugging. Transparently displays all LLM calls.
prompt-architect
by Svenja-dev
Transformiert Anforderungen in Best-Practice Prompts nach Claude 4.x Standards (Dezember 2025). Basiert auf: - Nate B. Jones 4 Beginner Moves: Shape, Context, Silent Plan, Self-Check - Anthropic Claude 4.x Best Practices: Explizitheit, Contract-Style, Examples beat Adjectives - Pipelines over Prompts Philosophie AKTIVIERT SICH AUTOMATISCH nach clarify-spec oder bei /prompt-architect. Produziert strukturierten, ausfuehrbaren Prompt mit allen Best Practices.
learning-capture
by Svenja-dev
Recognize and capture reusable patterns, workflows, and domain knowledge from work sessions into new skills. Use when completing tasks that involve novel approaches repeated 2+ times, synthesizing complex domain knowledge across conversations, discovering effective reasoning patterns, or developing workflow optimizations. Optimizes for high context window ROI by identifying patterns that will save 500+ tokens per reuse across 10+ future uses.
design-system-analyzer
by NakanoSanku
Analyze any website's UI style using ChromeDevTools to extract precise CSS tokens, animations, and interaction states. Handles complex sites and anti-bot measures by guiding the user. Triggers on "analyze this site", "extract UI style", "create design system from [URL]", or "learn visual style".
Design Style Skill
by NakanoSanku
useful anthropic skills
skill-evolve
by OrangeViolin
用演进式方法论改进任何 skill 的质量。当用户说"改进这个 skill"、"这个 skill 效果不好"、"优化 skill"、"skill 不够好"、"迭代 skill"、"skill-evolve"、"/evolve"时触发。也适用于用户拿着一个 skill 的输出结果说"不满意"、"有问题"、"效果差"的场景。不要等用户明确说"演进"——只要他们在讨论一个 skill 的质量问题，就应该启用。
gemini-image-generator
by mkdev-me
Generate images using Google Gemini with customizable options
second-opinion
by runkids
"Runs external LLM code reviews (OpenAI Codex or Google Gemini CLI) on uncommitted changes, branch diffs, or specific commits. Use when the user asks for a second opinion, external review, codex review, gemini review, or mentions /second-opinion."
claude-in-chrome-troubleshooting
by runkids
Diagnose and fix Claude in Chrome MCP extension connectivity issues. Use when mcp__claude-in-chrome__* tools fail, return "Browser extension is not connected", or behave erratically.
claude-code-analyzer
by pratos
Analyzes Claude Code usage patterns and provides comprehensive recommendations. Runs usage analysis, discovers GitHub community resources, suggests CLAUDE.md improvements, and fetches latest docs on-demand. Use when user wants to optimize their Claude Code workflow, create configurations (agents/skills/commands), or set up project documentation.
langsmith-evaluator
by jackjin1997
Use this skill for ANY question about CREATING evaluators. Covers creating custom metrics, LLM as Judge evaluators, code-based evaluators, and uploading evaluation logic to LangSmith. Does NOT cover RUNNING evaluations.
audit-context-building
by runkids
Enables ultra-granular, line-by-line code analysis to build deep architectural context before vulnerability or bug finding.
multiversx-factory-manager
by multiversx
Factory pattern for deploying and managing child contracts from a parent manager. Use when building marketplaces, launchpads, multi-tenant systems, or any protocol that deploys child contracts from a template.
news-extractor
by jackjin1997
新闻站点内容提取。支持微信公众号、今日头条、网易新闻、搜狐新闻、腾讯新闻。当用户需要提取新闻内容、抓取公众号文章、爬取新闻、或获取新闻JSON/Markdown时激活。
smart-commit
by jackjin1997
"AI-powered git commit message generation. Uses LLM to summarize changes and create meaningful commit messages. Triggers when user wants to commit changes, amend/squash commits, or needs LLM to summarize changes for commit messages. Chinese triggers: 提交, 提交代码, 提交更改, 提交修改, 要提交, commit, 提交信息, git 提交, 生成提交信息."
mvx_factory_manager
by multiversx
Factory pattern for deploying and managing child contracts from a template.
openai-image-gen
by malue-ai
Batch-generate images via OpenAI Images API. Random prompt sampler + index.html gallery.
oracle
by malue-ai
Best practices for using the oracle CLI (prompt + file bundling, engines, sessions, and file attachment patterns).
craft-companion
by qcx1919788736-collab
基于结构化知识库的AI协作小说创作框架。支持章纲→初稿→自查→修订→终版完整流程，适用于都市异能/任何长篇小说。
nse-trading-toolkit
by Bhala-Srinivash
Master orchestrator for Indian NSE/BSE equity trading analysis via Groww broker. Routes to specialized framework skills: technical analysis, position sizing, stop-loss, trailing stops, risk-reward, multi-timeframe, RSI divergence, and Fibonacci trading. Use this skill whenever the user asks to: analyze a stock, check a position, decide buy/sell/hold, plan entries/exits, or do any comprehensive trading analysis for Indian equities. Triggers on: "analyze [stock]", "should I buy/sell [stock]", "check [stock]", "what's the setup on [stock]", or any broad market analysis request involving NSE/BSE stocks. This is the go-to skill for full stock analysis — it pulls together all the individual framework skills into one workflow.