Loading...
Loading...
Found 140 Skills
Removes the signs of AI generation from English text: clichés, filler, corporate jargon, sycophantic tone, emoji bullet lists, gratuitous em-dashes, fabricated sources. Use when asked to humanize, de-slop, or check English text for AI voice ('this reads like a chatbot', 'убери следы ИИ в тексте'), or when copy-paste chatbot markers are present: ':contentReference', '?utm_source=chatgpt.com', 'oai_citation', '[cite: 8]'. Do not use on text that is not English, on source code, on legal documents, or on literary prose and résumés, where rhythm and the em-dash are authorial devices.
EU AI Act (Regulation (EU) 2024/1689) compliance advisor — risk classification across all four tiers, all 9 prohibited practices (Art. 5, including the nudification/CSAM prohibition from Dec 2, 2026), all 8 Annex III high-risk use case areas, provider and deployer obligations (Arts. 9–17, 26), GPAI model obligations including the July 2025 Code of Practice (Arts. 51–55), conformity assessment and CE marking (Arts. 43–48), EU AI database registration, Art. 50 transparency (chatbots, synthetic media, AI-generated content), governance (AI Office, AI Board), penalties (Art. 99), confirmed phase-in timeline (Digital Omnibus, Reg. (EU) 2026/1744, in force July 27, 2026: Annex III deferred to Dec 2, 2027; Annex I to Aug 2, 2028), and cross-framework mapping to ISO 42001, NIST AI RMF, and GDPR. Use for any EU AI regulation, AI system classification, or AI compliance question. Current as of August 2026. GPAI enforcement powers active since August 2, 2026.
Use when building an internal admin-facing AI agent in a Medusa project. These agents are operated by merchants and store operators — not customers. Covers data models, module service, agent runtime (tools, system prompt, streamText), streaming API routes (NDJSON), and admin UI chat extensions. Load for any internal agent type: store operations assistant, product audit, cohort analysis, customer service tooling for support staff, etc. Do NOT use for customer-facing agents (storefront chatbots, buyer-side assistants).
Provides authoritative guidance on Amazon Neptune Database and Neptune Analytics for graph, knowledge-graph, and relationship-heavy workloads — fraud detection / fraud rings, agentic memory / chatbot context across sessions, recommendations, identity resolution, Gremlin / openCypher / SPARQL queries, supernode / slow traversal, Neo4j to Neptune migration / APOC compatibility, Neptune Database vs Analytics engine selection, PageRank / community detection, GraphRAG, and connectivity from Lambda / EC2 / applications. Creates and modifies Neptune Database clusters/instances and Neptune Analytics graphs on explicit user confirmation; blocks destructive operations (delete, reset-graph, failover, major upgrade) and redirects to change-control.
Writes and reviews system prompts for AI tools, agents, chatbots, and LLM products using a fixed section order and a quality checklist. Use when the user says "write a system prompt", or when drafting a system prompt or auditing one for missing stop criteria, tool rules, constraints, or examples. Not for compressing an existing prompt; use improving-prompts.
Hunt LLM/AI feature bugs — prompt injection, indirect injection, exfiltration via tool-use/markdown, ASCII smuggling, agentic AI security (OWASP Agentic Apps 2026, ASI01-ASI10). Patterns: direct injection ('ignore previous instructions'), indirect injection via documents/web pages/email the model reads, ASCII smuggling (Unicode Tags block U+E0000-U+E007F, invisible to humans, decoded by the model), tool-use exfiltration (model has fetch/browse tool, attacker injects OOB URL, model exfils chat history/secrets), markdown-image zero-click exfil, system-prompt extraction, IDOR-via-AI (cross-tenant data). Targets: chatbots, RAG, summarizers, agentic copilots, MCP tools. Detection: any LLM-backed endpoint, doc upload triggering AI processing, autonomous agent with tools. Validate: OOB/Collaborator callback for exfil, verbatim-reproducible system-prompt leak (run twice), verifiable cross-tenant leak or RCE. Confabulation is NOT a finding. Use when hunting AI features, chatbots, RAG, agentic systems, MCP.
Build or transform lightweight realtime voice-chat apps with a talking character avatar from either a user-supplied photograph or a text description. Use when Codex is asked to create a talking avatar, photo avatar, character chatbot, roleplaying voice companion, mouth-sprite animation, or reusable OpenAI Realtime avatar app in Vite/Next.js, including BYOK API-key intake, identity-consistent image generation, audio-driven lip sync, testing, and deployment.
Find an open-source, reverse-engineered tool for a closed app, API, device, protocol, file format or game, then read or fetch it. Use when a task needs to talk to something that has no official API, SDK, driver or spec, or only a limited one. Examples include "control my Tuya plug locally", "read a .psd or .dwg file", "unofficial WhatsApp, Instagram or Bilibili client", "Bambu printer protocol", "talk to my car's API", "Garmin or CGM data", "decompilation of a game" and "OpenAI-compatible proxy for a web chatbot". The skill searches a curated index of 12,000+ verified projects ranked by stars, language, license and activity.
Hunt vector-store / embedding-layer weaknesses in RAG pipelines (OWASP LLM08 Vector and Embedding Weaknesses) — persistent corpus poisoning that survives across sessions and users (distinct from one-shot indirect prompt injection, which is owned by hunt-llm-ai), cross-tenant vector-database IDOR (unauthenticated or unscoped queries against Pinecone/Weaviate/Chroma/Milvus/Qdrant/pgvector), source-text/metadata leakage in similarity-search results, and retrieval-hijack via adversarial embedding proximity ('SEO poisoning' for RAG). Targets: any app with a shared knowledge base, document upload feeding a chatbot, or a directly reachable vector-DB port. Validate: a second, clean session/account must inherit a poisoned result, or a cross-tenant artifact must be independently verifiable — confabulation is not a finding, same bar as hunt-llm-ai. Use when target is RAG-backed, exposes a vector-DB port, or lets users upload documents that other users' queries later retrieve.
Use when a product calls a language model or other AI API, embeds AI-generated content, or offers a chatbot, and you need to check provider keys and exposure, what user data reaches the provider, disclosure that users are dealing with AI, abuse and cost controls, and failure behavior. Do not use it to add a generic AI disclaimer to a product with no user-facing AI, to judge model quality, or to interpret AI regulation.
Map how customers discover, evaluate, and choose a product across Google, AI chatbots (ChatGPT, Claude, Perplexity), and social platforms, using the 5-stage awareness journey. Use when the user asks about search intent, AI SEO prompts, discoverability, buyer journeys, awareness stages, or what content to create for a brand, website, or keyword list.
One-shot user management for apps, multi-chain wallet authentication, an AI-powered assistant, and AI app introspection. Use when the user wants to let website users sign in with wallets, email/password, or social login and give each user a wallet-enabled account, then embed EmblemAI chat surfaces, connect plugins, or add Reflexive observability. Provides React components, TypeScript SDKs, session-based authentication, and pointers to the React and agent-wallet skills for specialized workflows.