AI & ML

cognigy Skill

Use when a Cognigy agent returns empty responses, a tool call or create_ai_agent fails, a resource is not found, setup_llm fails, or you need to diagnose a Cognigy MCP problem.

cognigy Skill

Use when backing up a Cognigy project before changing an existing AI Agent, rolling a project back to a previous state, undoing agent changes, or working with Cognigy Snapshots — create, restore, list, delete.

cognigy Skill

Use when exporting, importing, uploading, inspecting, or downloading Cognigy package zip files — including reusing an LLM plus its connection across projects.

cognigy Skill

Use when the user wants to set up a voice agent or a Voice Gateway endpoint with WebRTC for browser-based voice interaction.

cognigy Skill

Use when the user wants to audit, validate, or make a Cognigy voice agent production-ready against the Voice Go-Live Checklist, or asks what audit_voice_agent checks and which items are auto-fixable vs manual.

xjccc-skills Bundle

Narrow a large candidate set — files, search hits, document sections, records, rows — down to the few that matter before they enter the model's context, using TypeSafe/Jev for the typed judgment (select, rank, verify). Use when a task would otherwise mean reading everything to find the relevant part, and the token cost of that matters. Do not use when there are fewer than ~30 candidates, when judging them requires their full text anyway, or to generate, rewrite or summarize content.

sprintberlin Bundle

Zoho People via MCP: setup, action catalog, profiles, HR helpers, verified workflows, limits, and REST fallbacks.

rogue-dev-studio Bundle

Canonical guide for authoring and validating portable agent skills (SKILL.md packs) for the agent house catalog and team local skills.

zilliztech Bundle

Diagnose and configure MemSearch memory behavior. Use when the user asks about MemSearch configuration, plugin summarization, PROJECT.md/USER.md maintenance, memory directories, index health, provider routing, prompt files, or migration/compatibility questions.

zilliztech Bundle

Turn workflows from your MemSearch memory into reusable skills. Use when the user asks to make/create/extract/distill a skill from what they just did or from past work, review skill candidates, install a distilled skill, or 'turn this into a skill'. Manages MemSearch procedural-memory candidates under .memsearch/skill-candidates/, not the host agent's own skills system.

pixeltable Bundle

Build multimodal AI applications with Pixeltable. One application file declares TableModel tables, computed columns, embedding indexes, and FastAPI routes; inserting a row runs the transforms. Use when building RAG, processing images, video, audio, or documents, or serving an API over that data. Do not use for general Python or direct PostgreSQL administration.

agentscope-ai Skill

指导外部自动化 agent 使用 QwenPaw Data CLI 发现 Data Bridge 数据源、通过自然语言规划与执行数据分析任务、复用 SOP YAML，并根据流式输出、执行摘要和错误信息验收结果。用于需要调用本地 `qwenpaw-data` 命令完成数据任务、选择 `run` 或 `plan`/`execute`、传入 `--datasource-id`、处理长任务输出或排查 CLI 失败的场景。

lifeparticle Bundle

Agent skills

agentscope-ai Skill

Builds end-to-end predictive modeling pipelines on tabular datasets—data exploration, preprocessing, baseline modeling, and mandatory optimization—producing valid saved predictions in the required output format. Use for any supervised machine learning or data modeling task, including classification and regression on tabular data, Kaggle-style competitions or submission-file challenges, training a model to predict a target from features, or requests to fit/tune/evaluate models with scikit-learn, XGBoost, Random Forest, Logistic Regression, and similar non-deep-learning methods. Runs fully automated end-to-end without asking the user for intermediate decisions.

langbot-app Skill

Browse and search the LangBot Space marketplaces (plugins, MCP servers, skills) through the Space MCP server. Use when an AI agent needs to discover LangBot extensions on space.langbot.app over MCP. Covers the /mcp endpoint, Personal Access Token (PAT) auth, the tool surface, and client configuration. Triggers on "langbot space mcp", "search langbot plugins", "langbot marketplace mcp", "space.langbot.app mcp".

daya-gagas-internasional Bundle

Auto-reply comment, chat & thread di TaskGlory. SSE listener → Hermes CLI (PTY) → MCP tools. Real-time, tanpa queue/cron.

daya-gagas-internasional Skill

Operasikan TaskGlory via MCP — query task, space, list, member, comment, channel, file. Auto-reply comment & chat.

career-cafe Skill

High-priority rules and automated procedures for continuously keeping repository documentation, API references, architecture guides, changelogs, and agent skills synchronized with code changes autonomously without requiring human reminders.

career-cafe Skill

Standard operating procedure for ephemeral Git worktree isolation, directory conventions, branch-to-worktree 1:1 mapping, dirty-state protection, and multi-agent safety.

career-cafe Skill

Step-by-step instructions for building and extending Python AI agent services: adding LangChain/LiteLLM tools, Tool-Calling RAG workflows, enforcing Human-in-the-Loop approvals, multi-key model failover, and pgvector embeddings.

career-cafe Skill

Rules, patterns, and runbooks for writing and running unit, integration, and AI agent test suites across Go, Python, and TypeScript frontends.

thanhlamauto Bundle

Turn a research method into a short 3Blue1Brown-style visual explainer video with Manim. Use when a method mechanism is hard to understand statically, when a representation changes through time (iterative algorithms, diffusion, temporal caching, attention, optimization dynamics, multi-stage processes), or when the user asks to animate a method, make a method explainer clip for a lab meeting, or turn a paper's method into a video. Produces persistent scientific objects, animated transformations, an MP4, and PowerPoint-ready keyframes. Not for generic YouTube videos, narration, or avatar presenters.

rogue-dev-studio Bundle

Canonical MCP server integration playbook: allowlist, Cursor mcp.json merge, smoke tests, and scaffolding. Use with Rogue Market MCP packages.

zephyrdeng Bundle

Jev (TypeSafe System One) inner loop for ego-browser — one ~0.4 s typed decision per DOM step instead of an LLM turn. Use for multi-step clicking through a semantic page: fill known values into a form, set filters, open a row/card/menu by name, reach a page via nav or site search. Escalates login, payment, free text, canvas and content reading back to you.

emaspa Bundle

Hand a self-contained coding or analysis task to the OpenAI Codex CLI and get its answer back. Use when the user says to ask/delegate to codex, wants a second opinion from another model, or wants work done in parallel by another agent. Also use for "get codex to ...", "have codex review ...", or /codex.

aaravkashyap12 Bundle

Route every task to the cheapest model tier and reasoning effort that holds output quality. The session model stays the orchestrator and delegates bounded work to subagents on smaller models, or answers inline when delegating would cost more. Use at the start of any coding, research, or writing session in Claude Code, Codex, or another Agent Skills harness when the user cares about token usage, usage limits, or cost, asks to be efficient, save tokens, use subagents, or delegate, or when a task mixes trivial and hard work. Also use when deciding whether to answer inline or dispatch a subagent.

mavericktfius Bundle

Arma Reforger / Enfusion mod development — Blender-to-Enfusion export discipline, fitting character clothing and garments, terrain and surface materials, AI behaviour trees, rigging and animation, prefab inheritance, MCP tooling setup, and the seven-level QA pass before Workshop release. Use for any work in Enfusion Workbench, Enforce Script, or Blender assets destined for Reforger.

tobihagemann Skill

Run a multi-agent review of changed files for scope, reuse, quality, efficiency, clarity, and altitude issues followed by fixes. Use when the user asks to "simplify code", "review changed code", "check for code reuse", "review code quality", "review efficiency", "simplify changes", "clean up code", "refactor changes", or "run simplify".

qq13144946939-lab Skill

Coordinate bounded, parallel subtasks with Codex agents when complex work benefits from separate ownership or the user requests a multi-agent team. Supports explicit cross-window role teams through Agent Hub.

minihellboy Bundle

Discover alpha factors by running the FactorMiner research engine — the paper-faithful Ralph loop or the enhanced Helix loop (causal validation, regime conditioning, multi-specialist debate, canonicalization). Use to generate a new factor library from a validated dataset. Triggers on "mine factors", "discover factors", "run mining", "find alpha", "helix loop", "ralph loop", "build a factor library".

zerotokenclaw Bundle

Use for ANY task involving Ultralytics Platform, the ultralytics Python package, yolo CLI, YOLO model weights (.pt), dataset annotation, training, validation, prediction, tracking, export, deployment, or the detect / segment / semantic / depth / classify / pose / OBB vision tasks.

zerotokenclaw Skill

当用户问「怎么做 X」「找一个 X 相关的 skill」「有没有能…的 skill」或想扩展能力时，帮助发现并安装 agent skills。用户寻找可能以可安装 skill 形式存在的功能时应使用本 skill。

getedgehq Bundle

Discover better ways to complete tasks. Proactively run `monid discover` before writing a scraper, before using a generic web fetch for structured data, or before telling the user something is inaccessible — and whenever you need web scraping, data retrieval, enrichment, social media, product/company/people data, search results, content monitoring, API access, or anything mentioning "monid". Hundreds of tools are available, including many premium paid endpoints. Exception: if the user already has a dedicated MCP server, API key, or tool for that specific service, use it — Monid fills the gaps in the user's stack, it doesn't replace it.

getedgehq Bundle

Check whether one additional AI-agent Skill would materially help with a task, then find the best matching GetEdge Skill and return its exact install command. Use before starting when someone asks which Skill or workflow package to use, asks for a setup or capability check, says "find a skill for this", asks whether the agent needs another package, invokes SkillNeed, or wants to know whether the current agent setup is missing relevant procedural expertise.

getedgehq Bundle

Scan authorized Claude, Codex, or OpenCode session logs for recurring correction themes, reconstruct real tasks, and measure whether a selected Skill improves the actual output in a blinded no-Skill versus explicitly-loaded comparison. Use when someone asks for an agent brain scan, wants to know which Skills materially help their own work, or asks to test a Skill against their real sessions.

getedgehq Bundle

Build evals for an AI agent that already does real work. Use when someone asks "how do I know my agent is right", wants to test an agent before trusting it, compare models on cost versus quality, or turn production failures into tests. Walks from first tasks and yes/no verifiers, to isolated environments, to a trace-driven improvement loop.