Loading...
Loading...
Found 10,840 Skills
Official Google Search guidance for optimizing websites for generative AI features such as AI Overviews and AI Mode. Use when an AI agent needs to explain, audit, plan, or implement SEO work for Google AI Search visibility; evaluate AEO/GEO claims; advise on llms.txt, structured data, content quality, crawlability, JavaScript SEO, media SEO, ecommerce/local details, Merchant Center, Business Profile, or agent-friendly site readiness.
Marc Andreessen-mode decision and productivity skill. A blunt, market-first operator that pressure-tests ideas, ventures, features, and career bets through Andreessen's actual frameworks — market dominates team and product; the only milestone that matters is product/market fit; bias to build over deliberate. Use when the user says 'andreessen', 'pmarca mode', 'should I build this', 'is there a market', 'are we at product/market fit', 'pmf check', 'pressure-test this idea', 'be brutal about this venture', 'market-first take', or wants a no-disclaimers, no-hedging, confidence-leveled verdict on whether something is worth pursuing. Also provides the 3x5-card + Anti-Todo personal productivity routine. Runs on a fixed anti-sycophancy operating prompt: leads with the strongest counterargument, never validates premises, uses explicit confidence levels, never apologizes for disagreeing. Not for polite brainstorming — this skill exists to tell you the market is dead when it is.
Redis vector search guidance covering HNSW vs FLAT algorithm choice, vector index configuration (dims, distance metric, datatype), filtered hybrid search combining vector similarity with TAG or NUMERIC filters, and the RAG retrieval pattern with RedisVL. Use when defining a VECTOR field in FT.CREATE, integrating embeddings (OpenAI, Cohere, sentence-transformers), tuning HNSW parameters (M, EF_CONSTRUCTION, EF_RUNTIME), building a retrieval-augmented generation pipeline, or filtering vector results by attribute.
When the user wants to improve their ability to recognize buying signals, ask for the sale, and confidently move deals to commitment. Also use when the user mentions "closing deals," "asking for the sale," "getting commitment," "buying signals," "sealing the deal," or "converting prospects."
Trigger this skill when building applications with Gemma or for general knowledge inquiries related to Gemma models (e.g. prompt structure, capabilities). Covers model selection, development workflows, and deployment best practices.
Use when users need Rust quantitative SDK or TQSDK Rust capabilities: real-time market data/quote/market depth/K-line/tick, product/contract list, main continuous contract/continuous contract, option chain, contract specification, metadata/direct query, historical data download/cache/CSV/Greeks, trading account/order placement/order cancellation/order status, TargetPosTask/risk control/multi-account/strategy execution, low-latency trading desk, stream/fan-out, replay/backtest/live-sim-replay; also applicable when agents need real-time or historical quantitative data, transaction execution substrate, or trading desk capabilities, even if TQSDK is not explicitly mentioned.
Call the cloud OpenAPI of Pudu robots, supporting operations such as robot task distribution, status query, delivery, cruise, call, and statistical data analysis. When using, first check the credentials and cluster environment variables; if missing, prompt the user to supplement them, then call the corresponding interface according to the user's intention and display the results. Trigger scenarios: Use this skill when the user mentions keywords such as "Pudu robot", "pudu", "robot task distribution", "query robot status", "delivery task", "cruise task", "call robot", "lifting task", "errand", "Flash Cabinet", "advertisement playback", "advertisement configuration", "cabinet task", "cabinet SKU", "product SKU", "hatch door photo", "traffic control zone", "map list", "statistical data", "risk avoidance", "dashboard overview", "OpenAPI".
Multi-step video annotation pipeline that turns raw videos into Chain-of-Thought training data — multi-level captions, structured descriptions, and QA pairs (MCQ, binary, open-ended) with reasoning traces, via VLM/LLM distillation. Use when the user wants to "create video training data", "generate video QA datasets", "build CoT reasoning traces from videos", "auto-label videos", or run the video_reasoning_annotation pipeline. Triggers include "video annotation", "video CoT", "video QA", "chain-of-thought", "video captioning pipeline", "video distillation".
Clarify and compile project technical solutions. Use this when users need to determine the overall implementation approach, key technology trade-offs, module and file responsibilities, compatibility and verification boundaries for a problem, bug, function change, or existing requirement in combination with the current project, or when they need to create a technical document that can be understood by product, development, and testing teams and used for subsequent work. No prior requirement document is required, and it does not cover task breakdown, coding implementation, or project acceptance.
Use when a Lightning Web Component data need is described in ambiguous natural language — turn "get contact info" or "show account data" into a clear, PRD-ready data-requirements spec. TRIGGER when the user says "define data requirements for this LWC", "turn this PRD data section into validated object/field names", "recommend GraphQL vs UIAPI for this data need", "validate these Salesforce API names", or "spec out the LDS adapter for this component", or references LWC bundle files (`.js`, `.js-meta.xml`) whose data layer is not yet specified. DO NOT TRIGGER when the data layer is already fully specified, when authoring the actual query or adapter code from a known spec, or when implementing an LWC end-to-end (use experience-lwc-generate).
Analyze a Salesforce project against the Salesforce Well-Architected framework (Trusted / Easy / Adaptable). Use when the developer asks to "review the architecture", "run a Well-Architected check", "audit this project", "is this project well-architected?", "assess security/governor-limit/packageability risk across the project", or wants a holistic code-and-metadata health report. Grades the criteria that are observable from code and metadata (sharing/FLS, bulkification, selective SOQL, trigger-handler separation, legacy tech, packageability) with file:line evidence, and emits a human checklist for governance/process pillars it cannot see (security matrix, BCP, roadmaps, AI governance). Distinct from `dx-code-analyzer-run` (single-tool Code Analyzer scan of Apex) — this skill is a multi-pillar architectural review that orchestrates several analysis skills and maps findings to Well-Architected. Read-only: it grades and advises, never edits.
Stand up your own fastCRW API server — single binary, Docker, or docker-compose with a bundled search-backend sidecar. Use when the user wants to run crw locally or on their own infra, configure renderers/proxies/ auth/LLM extraction, or understand the embedded vs proxy MCP modes.