Data & AI skills

Universal prompt engineering techniques for any LLM. Use when crafting, optimizing, or reviewing prompts for AI models. Triggers on requests like "improve this prompt", "write a system prompt", "optimize my instructions", "help me prompt engineer", "audit this prompt", "review my prompt", or when building agentic systems that need structured prompts.

The English summary is being prepared. Showing the original description.

Replace with when the AI should activate this skill. Be pushy — cover multiple phrasings so the AI activates for a wide range of user prompts.

The English summary is being prepared. Showing the original description.

Use when building or maintaining a personal LLM-powered knowledge base. Triggers: ingesting sources into a wiki, querying wiki knowledge, linting wiki quality, 'add to wiki', 'what do I know about', or any mention of 'LLM wiki' or 'Karpathy wiki'.

The English summary is being prepared. Showing the original description.

🛒 E-commerce & Retail skill suite derived from VoltAgent/awesome-agent-skills. Product catalogue optimisation, conversion rate, customer journey and retail analytics. Provides 10 specialised commands for ecommerce, retail, shopify workflows.

The English summary is being prepared. Showing the original description.

Use when 用户想根据论文、科研文档、研究文本、图注、开题/答辩材料或具备读图条件的参考图生成可复制的 AI 科研绘图提示词；触发场景包括论文配图、科研绘图、图形摘要、Graphical Abstract、机制图、技术路线图、实验装置图、模型架构图、多面板对比图、汇报总览图、参考图风格迁移、未知领域母版生成，或上传/引用 PDF、Word、LaTeX、Markdown、摘要、方法段、图注、课题说明、研究方案、参考图片。Also use when the user asks for scientific figure prompts, research illustration prompts, graphical abstract prompts, mechanism diagrams, technical roadmaps, experimental setup diagrams, model architecture diagrams, multi-panel scientific figures, paper/conference figures, or AI image prompts based on papers, research documents, abstracts, methods sections, figure captions, proposals, reference images, PDFs, Word docs, LaTeX files, Markdown files, or research plans.

The English summary is being prepared. Showing the original description.

Live affiliate program data from openaffiliate.dev. Search programs, compare commissions, check cookie days, find top performers. Use when researching affiliate programs, comparing options, or checking program details. Persistent daemon with cache — first call starts server (~2s), subsequent calls ~100ms.

The English summary is being prepared. Showing the original description.

Ultimate AI prompt database and builder with 2,500+ curated prompts across 19 categories and 17 AI models (Midjourney, Flux, Leonardo AI, DALL-E, Sora, Imagen, Mystic, Stable Diffusion, Ideogram, Adobe Firefly, and more). Search, build, enhance, and adapt prompts for image generation, video creation, text, and meta-prompt generators. Use when user says "prompt", "find a prompt", "build a prompt", "enhance my prompt", "adapt this prompt", "prompt library", "image prompt", "video prompt", "midjourney prompt", "flux prompt", or any AI prompt engineering task. Do NOT use for terminal/CLI prompts, JavaScript prompt() dialogs, user input prompts, or bash prompt customization.

The English summary is being prepared. Showing the original description.

Silently restructures the user's natural-language prompt into the format the model CURRENTLY running this skill handles best, then answers. On activation it identifies which model family is executing it (Claude, GPT, Gemini, Llama, DeepSeek, Mistral, Qwen, Grok, Perplexity, Kimi, GLM, Command, Nova, or Phi) and loads that one model's official strategy — so the optimization always matches the model that actually runs it. Activate with /prompt-refine. Use when users want better answers without learning prompt engineering.

The English summary is being prepared. Showing the original description.

Run the Yuzu full governance pipeline on a commit range. Produces Gate 1 Change Summary, then orchestrates Gates 2-6 as parallel agent fan-outs with pre-written prompt preambles. Use when the user says "/governance <range>" or "full governance" or asks to run the multi-gate review pipeline on a PR/commit set.

The English summary is being prepared. Showing the original description.

Pre-landing PR review. Analyzes diff against main for SQL safety, LLM trust boundary violations, conditional side effects, and other structural issues.

The English summary is being prepared. Showing the original description.

Generate ready-to-paste AI image-gen prompts for 2D game art (character/sprite, icon/UI/item, background/tileset) that stay consistent with the project's art style across separate chat sessions in Claude/Gemini/ChatGPT chat UIs. Use when the user wants to render, generate, or create game art/sprites/icons/backgrounds with AI, or mentions an "art style bible" for a game project. Maintains a persistent `art-style-bible.md` so style doesn't drift between requests, and gives a post-generation checklist plus post-processing guidance for common technical misses (transparency, size, aspect ratio).

The English summary is being prepared. Showing the original description.

Semantic vector search with moflo — RAG over your own documents, similarity matching, context-aware retrieval via HNSW (node:sqlite-backed). Use when building retrieval layers for chat, search, or context-assembly.

The English summary is being prepared. Showing the original description.

Detects apps that send user data to third-party AI systems without explicit in-app consent and disclosure, enforcing Guideline 5.1.2(i).

The English summary is being prepared. Showing the original description.

Store and semantically search agent memory with ONNX vector embeddings on a ruOS desktop, using the Ruflo CLI. Use to persist patterns/decisions across sessions and recall them by meaning rather than exact key.

The English summary is being prepared. Showing the original description.

Persistent, adaptive vector memory for agents on a ruOS desktop — a Rust-native vector database with local semantic embeddings, HNSW retrieval, and graph relationships. Use to remember and recall across sessions with no database server or API key.

The English summary is being prepared. Showing the original description.

Curate the project's knowledge base and memory in .unikit/memory/ — the indexed reference library of coding standards and framework usage patterns. ALWAYS use this skill whenever the user adds knowledge from a source: a URL, a file, a folder path, a PDF, an article, or a book — any path/link/document is a strong signal for the knowledge base, not a quick rule. Also use it to research or document how the project uses a framework, or to add a researched core/stack knowledge entry. Sub-commands by phrasing: "migrate the rules" or "promote rules" runs migrate-rules; "optimize the knowledge base" or "optimize the rules" runs optimise (extract large sections into references); "validate" re-syncs RULES_INDEX.md; "--module <id>" targets a module. For a quick one-line convention or correction typed as a prompt ("always do X", "never use Y", "remember this") with no source, use /unikit-rules; for architecture decisions use ARCHITECTURE.md.

The English summary is being prepared. Showing the original description.

Author and own ONE content type's typed schema (the CONTENT-TYPE.md) at .unikit/gamedesign/content-types/CT-<slug>.md — the content / catalog layer of the GDD (cards, items, weapons, enemies, levels, quests, loot). Use whenever the user wants to ADD a new kind of content or UPDATE its schema, e.g. "add a new content type", "design the loot content", "define the card schema", "add an enemies content type", "add a rarity field to items", "switch this catalog to curated". Create the skeleton, fill its typed field schema (CT.fields), scale, relationships, and validation, AND revise the schema under the delta discipline (a schema change bumps the version + changelog). Selects the scale (bulk | curated) and self-registers content_types/content. This owns the content SCHEMA, not the catalog of values — adding individual entries/units is data handled in the editor, not a schema edit. To add or detail a system use /unikit-gd-system; to add a flow use /unikit-gd-flow; to apply a multi-zone edit use /unikit-gd-apply.

The English summary is being prepared. Showing the original description.

Add a short, project-specific rule, convention, or override to .unikit/RULES.md — the quick-capture inbox for this project's rules (common rules always load; topic files in .unikit/rules/ load when the work matches), automatically loaded by /unikit-implement (later promotable via /unikit-memory migrate-rules). Works only with a rule typed as a prompt — it does NOT read files, folders, URLs, or PDFs. Cross-checks against the knowledge base (RULES_INDEX.md) to avoid duplicating core/stack entries. Use for fast, one-line conventions and corrections: "add a rule", "remember this", "convention", "always do X", "never use Y", "from now on do Z", or when the user corrects agent behavior and wants it remembered; also "split the rules into topics" (optimise), "clean up the rules" (prune), "shorten RULES.md" (compact). If the user points to a source (file, folder, URL, PDF, article, book) or wants to research/document framework usage, use /unikit-memory; for architecture decisions use ARCHITECTURE.md.

The English summary is being prepared. Showing the original description.

Qualitative quality review of game design documents — answers "is this design good, and does it follow best practices?" — across all three GDD axes: systems, flows, and content types. Fans out adversarial lenses (completeness, clarity, pillar alignment, systems-math, fantasy-delivery, feasibility, scope) plus domain lenses that check it against the game-design rules, each prompted to find problems rather than validate; produces a severity-graded verdict and a two-bucket report (apply-ready fixes vs research), handed to /unikit-gd-apply or /unikit-gd-explore in one move. Scope is inferred: a named system, flow, or content type reviews that document; "all" runs a cross-document review. Use when the user wants a critique, quality judgment, or rules check of the design, e.g. "review the combat GDD", "review the onboarding flow". This is the subjective quality pass — for a mechanical consistency check (numbers, terms, IDs, references matching the registry) use /unikit-gd-verify.

The English summary is being prepared. Showing the original description.

Enrich customer/lead profiles with business data using [LeadIQ](https://composio.dev/toolkits/leadiq), [RocketReach](https://composio.dev/toolkits/rocket-reach), or [Clearout](https://composio.dev/toolkits/clearout)

The English summary is being prepared. Showing the original description.

Sync customer data between [Gorgias](https://composio.dev/toolkits/gorgias) and [HubSpot](https://composio.dev/toolkits/hubspot) - find mismatches and missing contacts

The English summary is being prepared. Showing the original description.

Use a single seed-script owner OID variable when bootstrap data must satisfy owner-aware logic on fresh databases.

The English summary is being prepared. Showing the original description.

Determine which LLM model to use for each agent spawn based on configuration, session directives, and task type

The English summary is being prepared. Showing the original description.

Expert .NET 10 Full-Stack Developer skill. Use this when implementing new features, vertical slices, or modifying existing logic in the JJGNET Broadcasting application. It covers Domain, Data (EF Core), Managers, Api, and Web.

The English summary is being prepared. Showing the original description.