AI & ML

amzscout-corp Skill

Amazon-seller research using AMZScout tools — analyze a product by ASIN, evaluate a niche / category, pull keyword & PPC data, and explore a brand's Amazon catalog. Use whenever the user asks whether an Amazon product is worth selling, to analyze a niche or its competition, find/discover products, check a listing's keywords or ads, or research a brand on Amazon. Requires the `amzscout` MCP server connected (its default exposes both the granular `amzscout_*` tools and the all-in-one `amzscout-agent` tool).

ancrz Bundle

This skill should be used when the agent needs to "find a skill", "install a skill", "search for tools", "what skills do I have", "cherry-pick context from a skill", "extract a section from a skill", "manage agent skills", or when a task requires capabilities not currently available and the agent considers searching for a pre-built skill instead of building from scratch. Acts as the decision protocol for the skill-swarm MCP server tools.

andreahaku Bundle

Programmatic 3D CAD with OpenSCAD. Fast path for simple printable parts (Quick mode) and for editing an existing STL without reconstructing it (Modify mode), plus full design, STL-to- parametric reconstruction, and export. Triggers on: 3D model, STL, 3D print, parametric design, openscad, CAD, enclosure, bracket, spacer, adapter, holder, "modifica questo STL", or any 3D modeling task.

anthony-at-pieces Bundle

Connect to the Pieces MCP server (StreamableHTTP or SSE) and interact with the full Pieces data plane -- work-history retrieval via search_memory/ask_memory/ask_pieces_ltm, targeted full-text and vector search across workstream events/summaries/conversations/annotations/tags/websites, batch snapshot retrieval, browser history, filesystem search, Google Calendar, and memory creation. Also covers the remote Pieces Docs MCP for querying official documentation. Verified against PiecesOS 12.5.0 (69 tools).

aplaceforallmystuff Skill

Mandatory pre-creation analysis for new skills, agents, commands, or CLI tools. Searches existing ecosystem for overlap and recommends PROCEED/EXTEND/COMPOSE/ITERATE/BLOCK. Must be invoked BEFORE writing any new artifact definition. Trigger whenever the user says "create a skill", "build an agent", "make a command", "add a CLI tool", or any variation of creating new Claude Code capabilities. Also trigger when the user describes a workflow they want to automate as a new skill or agent, even if they don't use the word "create".

aplaceforallmystuff Skill

Enforces mental model application before major decisions. Use when facing architectural choices, business decisions, feature prioritization, or trade-off analysis. Ensures structured thinking before implementation.

ardiannurcahya Skill

OpenGraphMemory (OGM) Hybrid RAG, Codebase AST Search, Knowledge Graph, and Persistent Agent Operational Memory. Trigger whenever investigating bugs, researching architecture, navigating code symbols/call-graphs, querying hybrid RAG evidence, syncing code files, or persisting verified bug fixes and operational lessons.

lovstudio Bundle

将已验收结果整理成官网案例，普通用户登录即可手动导入或由 Agent 投稿，无需 GitHub 权限。Use when the user asks to add or publish an accepted Skill case.

lovstudio Bundle

Audit and optimize one or more existing Agent Skills from a canonical source path, then bump semver, update README/SKILL.md/skill.yaml/CHANGELOG.md, and verify installed copies and catalog synchronization. Checks frontmatter, trigger quality, CLI hygiene, naming, portability, version drift, dirty worktrees, shared Skill feedback policy, and compatibility contracts. Use when the user asks to optimize, refine, audit, polish, or update a Skill, or mentions "优化 skill", "skill 审计", "刷一遍 skill", "skill-optimizer", or "update skill changelog".

lovstudio Bundle

为一个或多个 Agent Skill 生成可解释的 Skill Pricing Card：结合创作者时间与维护成本、用户价值、稀缺性、购买信心和生态潜力，输出建议价、价格区间、渠道策略及证据缺口；触发语包括“给这个 Skill 定价”和 “price this Skill”。

ltdigor-review Skill

Use when questions should be answered from Docmost content, including when the answer depends on screenshots, images, or attached files.

lucas-saldanha-werneck Skill

Use 1Password with Claude Code without secrets ever entering the chat, the transcript, the command line or shell history. Trigger when the user wants to store an API key, token, password or credential; when a tool, MCP server, hook or script needs a secret; when the user mentions 1Password, `op`, `op://`, secret references, .env files with secrets, "where do I put my key", or asks how to launch Claude Code with secrets loaded. Provides: `op-store` (native hidden dialog with an eye/reveal toggle → straight into 1Password), `op-env` (launch any command with secrets injected, TTY preserved, one biometric prompt) and `secret-dialog`.

lukethecat Bundle

A skill for AI agents that want to produce better daily reports and discover more of what their users actually want. Scans source front pages, diffs them against yesterday, prescreens with a weighted profile, reviews with an LLM, deduplicates, publishes, and evolves the profile from user feedback. All decisions go to an append-only tape for audit and replay.

mahsan07 Bundle

Create focused Hermes SKILL.md packages with valid metadata and reusable workflows. Use when a user asks for this workflow or a closely related task.

malkreide Bundle

Erstelle, prüfe und publiziere professionelle GitHub Repositories für technische Projekte (MCP-Server, Claude SKILLs, Raspberry Pi, Python). Verwende diesen Skill immer wenn der User (1) ein Repo erstellen, publizieren oder GitHub-ready machen will, (2) bilinguale READMEs (EN/DE) oder Standard-Dateien (LICENSE, .gitignore, CHANGELOG, SECURITY, CONTRIBUTING) braucht, (3) Repo-Metadaten wie Name, Description oder Topics definiert, (4) ein bestehendes Repo prüfen, aktualisieren oder aufräumen will, (5) einen Release oder Git-Tag erstellt, (6) ein Python-Paket oder einen MCP-Server auf PyPI bzw. in die MCP-Registry publiziert, (7) den GitHub-Workflow per gh-CLI oder MCP-Tools nutzt, (8) vor einem Push einen Secrets-, Datenschutz- oder Sicherheitscheck braucht, (9) CI-Fehler debuggt, die ohne Codeänderung auftreten. Auch bei Fragen wie «Wie stelle ich das auf GitHub?», «Kannst du das GitHub-ready machen?», «Warum ist die CI rot?» oder «Warum schlägt der Publish fehl?» diesen Skill verwenden.

mattiasgeniar Bundle

Rules for building offline-first Progressive Web Apps that launch instantly from the home screen. Use when building, reviewing or debugging a PWA, or anything touching a service worker, a web app manifest, precaching, an in-app update prompt, iOS home screen behaviour, or safe-area/notch layout.

mcpjam Bundle

Interpret `mcpjam-cli` probe, doctor, OAuth, tools, resources, and prompts output conservatively against MCP 2025-11-25. Use when triaging MCP server findings, performing security reviews, deciding whether a CLI finding is real or overstated, or turning inspection output into an engineer-facing report with severity and confidence.

mikerrr Bundle

Designs, reviews, and recommends security controls for AI agents across models, context, memory, RAG, tools, identities, execution, infrastructure, and operations. Use when a user says “secure this AI agent,” “review my agent architecture,” “create an AI agent threat model,” “recommend controls for an agent with tool access,” or “prepare an AI agent security release checklist.”

minghinmatthewlam Bundle

Audit agent skills in a repo against best practices — checks .claude/skills/ and .agents/skills/ for quality, structure, and coverage gaps. Use when the user wants to review, improve, or evaluate their skills, or when they mention skill quality, skill audit, or skill best practices.

mintlify Bundle

Comprehensive reference for building Mintlify documentation sites. Use when creating pages, configuring docs.json, adding components, setting up navigation, or working with API references. Routes to detailed reference files for all components and configuration options.

nvidia Bundle

Guides human users' AI agents to the NemoClaw docs MCP server and canonical Fern documentation in Markdown form. Use when users ask how to install, configure, operate, troubleshoot, secure, or learn NemoClaw with an AI coding assistant. Trigger keywords - nemoclaw docs, use nemoclaw with ai agent, nemoclaw mcp docs, nemoclaw install help, nemoclaw quickstart, nemoclaw markdown docs, llms.txt, agent skills.

criptogus Skill

Automatic agent selection and intelligent task routing. Analyzes user requests and automatically selects the best specialist agent(s) without requiring explicit user mentions.

tonone-ai Skill

SKILL_DESCRIPTION

miuav Skill

瑞芯微RKNN模型转换 - ONNX PyTorch TensorFlow转RKNN

golemcloud Skill

Scheduling a future agent invocation in a Rust Golem project. Use when the user asks about delayed invocations, scheduling calls for later, or timed agent execution.

userinner Bundle

Share durable, inspectable context and handoffs between Claude, Codex, Hermes, Cursor, OpenCode, and other agents through the local ECC Memory Vault. Use when an agent must save work state, transfer context, resume another agent's task, or search shared project knowledge.

agsqaintern Skill

Operate Open Design daemon memory — the durable markdown fact store under the daemon data root that is injected into future agent prompts. Use when the user mentions od memory, daemon memory, memory tree, MEMORY.md, user profile, memory rules, memory extraction, or wants to list/edit/move memory entries, set profile, add rules, or toggle memory config via CLI or /api/memory.

sendralt Skill

Compiled CLI covering all 52 endpoints of the Anytype local API — objects, properties, tags, search, chat, files — one binary, no MCP server needed.

doriangallo Bundle

Run protected AAS maintainer sweeps, PR merge batches, canonical sync, Core preview checks, and scripted releases. Use for repository maintenance, main alignment, CLI/MCP/Workbench changes, or release work; not ordinary contribution tasks.

24601 Skill

Expert SurrealDB 3 skill. Use when working with SurrealDB, SurrealQL queries, multi-model data modeling (document, graph, vector, time-series, geospatial), schema design, graph traversal, vector search, security and permissions, deployment and operations, performance tuning, SDK integration, Surrealism WASM extensions, SurrealMCP, Surrealist IDE, Surreal-Sync migrations, SurrealFS, SurrealKit, or ecosystem integrations such as n8n and CodeMirror.

globalize-now Bundle

Add multi-language support (i18n) to this Lovable app using Lingui. Use when the user asks to add i18n, internationalization, localization, or translations — "translate my app", "make my app multilingual", "add Spanish/French/German support", "add a language switcher", "support multiple languages", or "connect Globalize". Covers setup (Vite SPA and TanStack Start), wrapping hardcoded text, PO catalogs, a GitHub Action that keeps catalogs in sync, coding rules in AGENTS.md, and connecting the Globalize.now translation platform (via its MCP connector).

goingli0324 Bundle

Turns a vague, underspecified request into a clearly structured Goal / Constraints / Obstacle breakdown, then produces a ready-to-use structured prompt. Use this whenever the user brings a fuzzy ask ("幫我想辦法...", "有什麼方法可以...", "我不知道怎麼處理..."), asks explicitly to help them "問對問題" or structure their request, or describes a real-world problem/decision they want AI help with but haven't yet specified what success looks like, what can't change, or what the actual blocker is. Trigger this proactively — even without the user naming the skill — any time answering directly would likely produce a generic, "technically correct but not actually usable" answer rather than something tailored to their real situation.

goldmar Skill

Skill for orchestrating coding agent sessions from OpenClaw, including OCA requests such as "let oca do...", "ask oca to...", or "have oca handle...". Covers launching, monitoring, plan approval, lifecycle management, and worktree decisions.

green-dalii Bundle

指导任何 Agent 正确、高效、符合规范地开发 DeepSeek Harness（DSH）插件。涵盖 Tool（defineTool）、LLM 适配器、服务与依赖、事件系统、配置、打包发布，以及 Cordis 框架的心智模型、代码模板与验证清单。

hamid-bhz Skill

Kill stale/orphaned MCP server processes leaked by ended sessions — npx-launched servers (chrome-devtools-mcp, sentry-mcp, any npm exec *mcp*), their wrappers and watchdogs — while keeping the ones live sessions are using. Use when MCP processes pile up across sessions and eat memory.

hanzoskill Bundle

AI-optimized web search using Tavily Search API. Use when you need comprehensive web research, current events lookup, domain-specific search, or AI-generated answer summaries. Tavily is optimized for LLM consumption with clean structured results, answer generation, and raw content extraction. Best for research tasks, news queries, fact-checking, and gathering authoritative sources.