搜索结果
全部能力
找到 923 个相关结果 / 搜索与检索
研究学习 / 检索整理
core-web-vitals
core-web-vitals
Optimize Core Web Vitals (LCP, INP, CLS) for better page experience and search ranking. Use when asked to "improve Core Web Vitals", "fix LCP", "reduce CLS",…
研究学习 / 检索整理
scikit-learn
scikit-learn
Machine learning in Python with scikit-learn. Use when working with supervised learning (classification, regression), unsupervised learning (clustering,…
研究学习 / 检索整理
prospect-investigation
prospect-investigation
Research and investigate business prospects and leads. Gathers company information, contact details, and qualification data for sales.
研究学习 / 检索整理
research-ideation
research-ideation
Generate research questions from economic phenomena
研究学习 / 检索整理
memory
memory
Project memory system - save and search past decisions, preferences, context, and notes. Use when user says "remember this", asks "what did we decide about X",…
研究学习 / 检索整理
matplotlib
matplotlib
Low-level plotting library for full customization. Use when you need fine-grained control over every plot element, creating novel plot types, or integrating…
研究学习 / 检索整理
investigate
investigate
Research the codebase to answer questions. Search for relevant files, gather context, and provide clear answers.
研究学习 / 检索整理
content-research-writer
content-research-writer
Assists in writing high-quality content by conducting research, adding citations, improving hooks, iterating on outlines, and providing real-time feedback on…
研究学习 / 检索整理
scientific-schematics
scientific-schematics
Create publication-quality scientific diagrams using Nano Banana 2 AI with smart iterative refinement. Uses Gemini 3.1 Pro Preview for quality review. Only…
研究学习 / 检索整理
spec-design-research
spec-design-research
Use when 需要在 Spec 级设计阶段执行 D1 research(产出 `{FEATURE_DIR}/design/research.md`),或面对关键不确定性/高风险点需要先验证而不是直接进入 D2;常见症状包括缺少证据支撑取舍、未知项被写成 TODO/待确认问题、在压力下想猜 FEATURE_DIR…
研究学习 / 检索整理
confluence
confluence
Search and manage Confluence pages and spaces using CQL, read/create/update pages with Markdown support. Use when working with Confluence documentation.
研究学习 / 检索整理
skill-forge
skill-forge
Generate a production-ready AbsolutelySkilled skill from any source: GitHub repos, documentation URLs, or domain topics (marketing, sales, TypeScript, etc.). Triggers on /skill-forge, "create a skill for X", "generate a skill from these docs", "make a skill for this repo", "build a skill about marketing", or "add X to the registry". For URLs: performs deep doc research (README, llms.txt, API references). For domains: runs a brainstorming discovery session with the user to define scope and content. Outputs a complete skill/ folder with SKILL.md, evals.json, and optionally sources.yaml, ready to PR into the AbsolutelySkilled registry.
研究学习 / 检索整理
geo-fundamentals
geo-fundamentals
Generative Engine Optimization for AI search engines (ChatGPT, Claude, Perplexity).
研究学习 / 检索整理
reference-builder
reference-builder
Creates exhaustive technical references and API documentation. Generates comprehensive parameter listings, configuration guides, and searchable reference…
研究学习 / 检索整理
earnings-call-analysis
earnings-call-analysis
Analyze earnings call transcripts to extract forward-looking guidance, strategic focus areas, supply chain insights, and generate follow-up questions for…
研究学习 / 检索整理
slack-qa-investigate
slack-qa-investigate
Investigate and answer repository questions in read-only mode. Use when asked for research-backed answers that require codebase and documentation investigation…
研究学习 / 检索整理
balance-sheet
balance-sheet
Retrieve detailed balance sheet statement data including Total Assets, Current Assets, Non-Current Assets, Liabilities, Equity, and Net Debt for public…
研究学习 / 检索整理
ai-engineer
ai-engineer
Build production-ready LLM applications, advanced RAG systems, and intelligent agents. Implements vector search, multimodal AI, agent orchestration, and…
研究学习 / 检索整理
grill-me
grill-me
Clarify ambiguous or conflicting requests by researching first, then exhaustively interrogating assumptions, constraints, dependencies, trade-offs, edge cases, and failure modes before any planning or implementation. Use when prompts say "$grill-me" or "grill me", ask hard questions, request relentless interrogation, pressure-test assumptions, clarify scope or requirements, define success criteria, or request product/system-design decisions before implementation. Respond in the user's language. Stop before implementation.
研究学习 / 检索整理
market-research-reports
market-research-reports
Generate comprehensive market research reports (50+ pages) in the style of top consulting firms (McKinsey, BCG, Gartner). Features professional LaTeX…