AI & ML

first-fluke Bundle

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Agent's capabilities with specialized knowledge, workflows, or tool integrations.

haowjy Skill

Load before writing or revising human-facing text. Choose words deliberately, ground the piece in the reader's context, and remove default LLM phrasing before the final draft.

newmindsgroup Skill

Reviews performance test results and system bottlenecks with multiple analytical perspectives before recommending optimization work.

autom8labs Bundle

Operate a live Revit model through AUTOM8LABS MCP tools with scoped reads, bulk operations and result verification. Use for connector queries and authorized edits. Do not use for general Revit API programming or another host.

autom8labs Bundle

Operate a live 3ds Max scene through AUTOM8LABS MCP tools with filtered reads, typed operations and bounded verification. Use for connector queries and authorized scene changes. Do not use for general image generation or visual-design instruction.

autom8labs Bundle

Inspect and operate a live Dynamo graph through AUTOM8LABS MCP tools using scoped graph reads, batched edits and evaluated-output checks. Use in Revit or Dynamo Sandbox. Do not use for Grasshopper or ordinary Python tasks.

autom8labs Bundle

Operate live AutoCAD drawings through AUTOM8LABS MCP tools with filtered queries, batches and result verification. Use for connector inspection and authorized drawing or folder operations. Do not use for generic drawing advice or another CAD host.

autom8labs Bundle

Operate a live Navisworks coordination model through AUTOM8LABS MCP tools using counts, filtered searches and verified actions. Use for model queries and authorized connector operations. Do not infer Navisworks from a clash request when another host is intended.

autom8labs Bundle

Inspect and operate a live Grasshopper definition through AUTOM8LABS MCP tools using scoped reads, batched graph changes and data-tree verification. Use in Rhino or Rhino.Inside.Revit. Do not use for Dynamo or direct Rhino work without Grasshopper.

autom8labs Bundle

Operate a live MicroStation DGN through AUTOM8LABS MCP tools with counts, bounded scans and verified changes. Use for model inspection and authorized connector operations. Do not use for generic references, levels or another host.

big-data-club Skill

Build grounded reports from LMS and local-only sources through BDC MCP.

big-data-club Skill

Author and save private BDC Hub draft courses using the user's external model.

big-data-club Skill

Author accessible lecture slides externally and format them through BDC MCP.

big-data-club Skill

Safely inspect and operate the caller's BDC Hub LMS courses through MCP.

big-data-club Skill

Help a learner study by combining selected private local sources with read-only evidence from courses they can access through BDC MCP.

big-data-club Skill

Design and safely create complete, grounded LMS quizzes without using the platform LLM gateway.

big-data-club Skill

Draft an LMS lesson from selected local files while keeping the source files local, then save only explicitly approved derived Markdown through BDC MCP.

big-data-club Skill

Organize private local learning sources and derived study artifacts for use alongside BDC Hub MCP without uploading the source files.

infant83 Bundle

Work with DOCX files when reading, creating, or editing documents where formatting and layout fidelity matter. Prefer python-docx for structure edits, use the bundled render_docx.py helper for rendering, and route image-heavy or layout-critical review through the shared on-prem document vision helper when the active model lacks vision.

infant83 Bundle

Analyze rendered document pages with the on-prem OpenAI-compatible vision model when the active Cline or DeepAgents model cannot reliably inspect images. Use for image-heavy PDFs, scanned PDFs, DOCX files with screenshots or diagrams, layout-critical review, table or figure extraction from rendered pages, and any document task where plain text extraction is insufficient.

itsnotailabs Skill

Use when NOVA should route work to Grok Build as an external coding worker for planning, patching, review, MCP tool use, or headless/scripted agent runs.

soyonaoc Bundle

Use when verifying a scientific claim or numerical parameter through project artifacts, implementation semantics, primary literature, supplements, and cited predecessors, and show decisive paper passages as inline PDF evidence crops when available. Applies to paper checking, parameter provenance, model-to-code comparisons, and high-cost misreporting risks. Do not use for a routine paper summary that does not ask whether a claim is correct.

slikon Skill

Compact the current conversation into a handoff document for another agent to pick up.

slikon Skill

Explain what a PR or branch actually does before you review it — the mental model, the execution path, and what to question. Use when the user needs to understand a change they didn't write, or an agent just produced a large diff or PR.

slikon Skill

Build a mental model of an unfamiliar codebase — architecture, subsystems, and where to look when changing something. Use when the user is new to a repo, is picking up a project they didn't write, or asks how a codebase is structured or where something lives.

theworstprogrammerever Bundle

Provision, validate, rotate, revoke, and cut over a durable agent or unattended service to a distinct Linear OAuth app identity. Use when Codex needs per-agent Linear app attribution, client-credentials token lifecycle checks, protected credential-file setup, GraphQL or MCP identity validation, API-key fallback migration, service cutover, rollback, or redacted OAuth diagnostics.

tyrantlucifer Bundle

Migrate or backup Hermes Agent between servers — export/import/verify the full state (config, memories, skills, sessions, cron, gateway). Class-level skill covering any Hermes relocation scenario.

tyrantlucifer Bundle

精修、润色、校正 TyrantLucifer 的中文技术文章，尤其适用于 Agent/LLM 生成的博客草稿、源码解析、架构分析、教程、开源项目体验和技术复盘。去除模板化 AI 腔，同时复现 tyrantlucifer.com 历史原创文章中稳定的个人表达：从真实问题或实践切入，跟随代码和现象逐步推演，穿插克制的第一人称判断与轻微吐槽，并诚实说明局限。保留并校验代码、命令、API、产品名、版本、数字、链接、引用和不确定性；也可仅审阅 AI 痕迹、技术表达和文风偏差而不改写。

ashutoshsinghpr7 Skill

Empty session traces mean launch failure, not agent behavior — verify api_call_count/tool_call_count and stdout.txt before analyzing.

bhoon716 Bundle

Use when the user wants to grill, stress-test, pressure-test, or otherwise validate a plan, design, product idea, architecture decision, implementation plan, business strategy, writing direction, research question, learning plan, personal decision, or Agent Skill design through Socratic, one-question-at-a-time interrogation with options and session logging. Also trigger on casual pre-execution phrasing like "X 하려고 하는데 파헤쳐줘", "빈틈없이 검증해줘", "질문으로 털어줘", "반대신문하듯 봐줘", "압박 검증해줘", or vague validation asks such as "이거 괜찮아?". Do not use for simple factual Q&A, brainstorming lists, text formatting, direct summaries, direct rewrites, or immediate code/plan generation.

carreiras Bundle

Framework completo de análise de segurança para avaliação técnica de MCPs (Model Context Protocol servers) antes de aprovação para uso em ambientes de clientes. Use esta skill sempre que o usuário pedir para avaliar, analisar, aprovar, revisar ou dar parecer sobre um MCP — independente do tipo (produtividade, dados, infraestrutura, API externa, design, automação, etc). Também acionar quando o usuário mencionar: "cliente pediu para usar o MCP X", "posso liberar esse MCP?", "esse MCP é seguro?", "quais riscos desse MCP?", "como avaliar um MCP de terceiro?", "preciso de um parecer sobre o MCP Y", CVEs em MCPs, permissões excessivas de MCP, MCP com acesso a filesystem/banco/e-mail/rede/credenciais. Esta skill produz DOIS entregáveis: (1) análise interna para o time de SbD e (2) documento formal de parecer técnico para apresentar ao cliente.

cassidyrice Bundle

Use when hunting zero-cost public data loops an agent can run without paid APIs. Finds free endpoints, documents a tiny experiment, gates claims.

cc8887 Bundle

This skill should be used when working in AdvancedLocomotionSystemV and the task is to trigger AnimBP2FP or BlueprintLisp conversions through the UE Editor MCP connection, especially for export, import, update, round-trip validation, and EventGraph DSL generation.

cc8887 Bundle

This skill should be used when working in AdvancedLocomotionSystemV and the task involves reading or writing AnimBlueprint assets through the UE Editor MCP connection — such as exporting a blueprint to DSL text, modifying DSL and writing it back, creating a new blueprint from DSL, or exporting the EventGraph as BlueprintLisp. This skill covers the complete read-write workflow using the in-process Python bridge (`unreal.AnimBP2FPPythonBridge`).

lobu-ai Skill

Use when designing or building internal/company AI agents that need shared context across company systems, durable organizational memory across sessions or agents, user-scoped permissions, approvals, audit, or governed actions. Also use when deciding whether ordinary MCP tools, RAG, or local agent memory are enough versus a shared company context and control layer.

mayeack Bundle

Conduct threat hunts in Splunk using the PEAK framework (Prepare, Execute, Act with Knowledge) and create Notable Events for findings. Supports hypothesis-driven, baseline, and model-assisted hunts. Automatically generates Notable Events in Splunk Enterprise Security via sendalert. Use when the user wants to threat hunt, investigate security anomalies, baseline data sources, detect adversary techniques, map findings to MITRE ATT&CK, create notable events, or generate correlation search results.