AI & ML

jaj42 Bundle

Author, edit, debug, and interpret NONMEM control streams (.ctl, .mod), datasets, and output files for population PK/PD modeling. Use whenever the user mentions NONMEM, NM-TRAN, PREDPP, control streams, $PROBLEM/$INPUT/$DATA/$SUBROUTINES/$PK/$ERROR/$THETA/$OMEGA/$SIGMA/$ESTIMATION blocks, ADVAN/TRANS routines, FOCE/FOCEI/Laplace/SAEM/IMP/BAYES/ITS/NUTS methods, MU referencing, EVID/AMT/RATE/ADDL/SS/MDV dataset items, .lst/.ext/.phi/.cov/.cor output files, VPCs/pcVPCs, or anything resembling a NONMEM workflow. Use even when the user just shows a `.ctl`-looking file or talks about "estimating a pop-PK model" without naming NONMEM explicitly — this skill applies.

shadowwood Bundle

Replace this with one sentence describing WHAT the skill does, then one sentence describing WHEN the agent should trigger it. Include concrete trigger terms users will say.

shadowwood Bundle

Analyzes staged git diffs and proposes a Conventional Commits–style commit message using local heuristics. Optionally uses an LLM (OpenAI) for more nuanced messages when the `--llm` flag is passed and `OPENAI_API_KEY` is set. The agent should trigger this skill when the user says "write a commit message", "commit this", "help me commit", or any time the agent is about to create a git commit and wants a well-formatted message.

tianming23 Bundle

蒸馏苏剑林（kexue.fm）的**思维程序**（thinking program），严格分离方法论与立场；**v2.3 起**正式挂载 **L7 视频语料锚点**（Karpathy / Silver / 3B1B / Deepia 的 `.ideas.md`），用于 RL 入门、LLM 流水线、Tokenizer、Attention 直觉等苏神原文未覆盖或需跨媒体对照的主题——**锚点观点不归苏神，须按 L7 表引用**。五种推导 archetype；批判 8 级证据（含物理守恒律）；苏神具体判断仅在 L3（25 条）。触发条件：(1)–(6) 同 v2.2；(7) 用户问题落在 L7 主题且已安装 SuGPT `corpus/videos/**/*.ideas.md`。不触发：纯 coding、无方法论需求的工程排障。文风默认关闭。

martin-hausleitner Skill

Built-in MCP (Model Context Protocol) client that connects to external MCP servers, discovers their tools, and registers them as native Hermes Agent tools. Supports stdio and HTTP transports with automatic reconnection, security filtering, and zero-config tool injection.

martin-hausleitner Skill

Use when external services should trigger agent runs through webhook events

martin-hausleitner Bundle

Use when the user asks to compare products, tools, GitHub repos, packages, frameworks, guides, platforms, plugins, or alternatives with Deep Research. Produces a strict research prompt and output format with at least 10 candidates, ideally 50, clickable GitHub and website links, five use-case-specific scoring categories, a 100-point total score, ranking, diagrams, and recommendation tables. Trigger on "vergleichen", "compare products", "best packages", "best tools", "GitHub links", "score 100", "rank platforms", "beste Programme", "Plugins vergleichen", or any broad comparison request that should become a reusable Deep Research scorecard.

martin-hausleitner Bundle

Discover local Brave, Comet/Komet, Chrome, or Edge profiles and run ChatGPT/Gemini research or agent workflows with hidden/headless launch arguments and screenshot-backed E2E records.

martin-hausleitner Bundle

Use when discovering, verifying, or sharing SKILL.md based skills across local Hermes, Codex, OpenClaw, Gemini, OpenCode, Claude-adjacent, and generic agent skill roots without overwriting existing skills or leaking private paths.

martin-hausleitner Bundle

Use when running, debugging, or explaining the ai-research-browser CLI for real Browser/CDP AI-provider automation, including Brave/Comet live sessions, restart recovery, workflow-live-run, workflow-suite, Deep Research/Agent/image runs, rate-limit cooldowns, screenshots, clipboard output, and safe E2E evidence.

xut82429-glitch Skill

为项目自动生成 AGENTS.md 配置文件。当用户需要为代码仓库创建 AGENTS.md、想让 Codex/LLM 更好理解项目结构、或需要为多个子目录生成 agent 指令时触发。分析语言、框架、构建工具、测试框架、CI 配置和目录结构，输出专业的 AGENTS.md。

romeosy Skill

Chief Security Officer style security review for Python-first codebases. Uses OWASP+STRIDE threat modeling, confidence-gated findings, and changed-files scope. Dynamic base branch detection and Bash/PowerShell command branches are included. Trigger: security review, cso, 安全审查, threat model, OWASP, STRIDE.

romeosy Skill

Feishu (Lark) MCP server setup guide. Configures document-centric capabilities (docx read/write, wiki, folder, whiteboard, image, search) via the feishu-mcp and @larksuiteoapi/lark-mcp npm packages.

romeosy Bundle

Read and write Feishu spreadsheets (sheet) and bitable (multi-dimensional tables) via Feishu Open API. Use when you need to read/write sheet or bitable content, or when a Feishu document is blocked because the MCP only supports docx.

coreycore123 Bundle

Orchestrate paid creative analysis for Xiaohongshu/Juguang lead-generation campaigns. Use when the user provides 投放数据、创意数据、笔记链接、客资数据、点击率、进线、开口、留资、开口成本、素材诊断、行业优秀笔记、14日阅读开口率高笔记、优化反馈、复盘反馈, or asks to analyze/optimize paid creatives. This agent first diagnoses the funnel, can calibrate against industry high-opening note benchmarks, can use and update wiki judgment logic, then requests complete note information, routes to ad-cover-title-audit, ad-body-copy-audit, and ad-supporting-images-audit, and outputs an optimization plan.

kiralpoon Skill

Setup Chrome DevTools MCP with Linux Chrome and mirrored networking

0xagi-bsky-social Bundle

Guided bias-deconstruction dialogue that combines Madhyamaka catuskoti, phenomenological epoche, Socratic elenchus, and Popperian falsification into progressive questions. Use when the user asks to examine assumptions, biases, beliefs, polarizing claims, identity or group judgments, ethical or political disputes, certainty, interpretations of experience, or explicitly asks for a bias-breaking/debiasing agent or always-on dialectical questioning for any topic.

liaosw97 Bundle

Use when working with AI — development rules

liaosw97 Bundle

Use when working with low-code platforms — model-driven, BPMN, visual development

liaosw97 Bundle

Use when working with model compression — quantization, pruning, knowledge distillation

liaosw97 Bundle

指定 LLM 集成规则，包括使用 Python 包装器和 API 端点，适用于所有 LLM 相关文件

liaosw97 Bundle

Use when writing OOP Java code — POJO, entity, model, DTO, VO, equals, hashCode, toString

sadlay Bundle

Create, review, or improve Agent Skills in this repository. Use when the user asks to write a new skill, update an existing skill, design skill triggers, split skill references, generate skill UI metadata, validate skills, or package skills for Claude/Codex distribution.

sadlay Bundle

Use when an agent needs to discover, query, or inspect configured PostgreSQL, MySQL, Elasticsearch, or Neo4j data sources from a portable YAML datasource registry with safe read-only defaults and explicit write opt-in.

sadlay Bundle

Use when managing a live New API instance through management REST APIs, especially model management, user and token administration, usage statistics, logs, channels, vendors, groups, pricing options, and health audits.

mitkox Skill

Use when: running SkillOpt, training a skill, evaluating a skill, using the local mitko model on port 8000, working with the dotnetdebug benchmark, adding a benchmark, adding a backend, or optimizing agent instructions with SkillOpt in this repository.

adam-s-builder-club Skill

Install and manage the WhatsApp MCP for Claude Desktop / Claude Code on macOS. Bridge syncs WhatsApp Web → local SQLite; the patched MCP server resolves contacts against the user's iPhone/Android address book (no more raw phone numbers in query results). Use when asked to "install whatsapp", "set up whatsapp mcp", "connect whatsapp to claude", or any first-time WhatsApp + Claude setup. Also handles --update, --uninstall, --reimport.

adam-s-builder-club Skill

Re-import contacts into the WhatsApp MCP from a vCard (.vcf) file and/or macOS Contacts.app (via JXA). Updates ~/.whatsapp-mcp/contacts.json so the patched MCP server returns real names instead of raw phone numbers in WhatsApp queries. Use when asked to "refresh whatsapp contacts", "re-import contacts", "update whatsapp names", or after adding new contacts on the phone.

profrino Bundle

Use this skill whenever a user asks anything about a Revit model connected via the Nonica MCP. This includes: reading element data, checking model quality, auditing warnings, extracting parameters, creating views or sheets, exporting PDFs, inspecting geometry, changing colors, moving elements, or writing parameter values. Trigger on any mention of Revit, families, walls, doors, rooms, sheets, schedules, levels, views, or BIM data.

profrino Bundle

Use this skill whenever building, assembling, or creating any 3D model in Blender via MCP tools (mcp__blender__execute_blender_code). Covers all object types: furniture, vehicles, architecture, characters, props, mechanical parts, scenes. Trigger any time Blender Python code will create geometry with primitives, bmesh, or modifiers. Even simple objects benefit from correct primitive math and verification. Always invoke this skill before writing any Blender geometry code - it prevents the three most common geometry bugs that cause exploded-looking models.

mat-garcia Skill

A complete guide for Advisors in Spring AI, covering memory, RAG, tool calling, authentication, and custom advisor implementation.

manager-rubens Bundle

Evaluate Brazilian PJ individual service arrangements for career decisions using contract scope, role/vacancy description, company context, operating model, and contexto-pj-brasil.md or the bundled PJ Brazil reference. Use when the user asks to review a vaga PJ, proposta PJ, contrato PJ, escopo de prestacao de servicos, pejotizacao risk, questions for the company/legal team, or points to negotiate before accepting or signing a PJ engagement.

manager-rubens Bundle

Create a ready-to-paste Gemini prompt that turns Gemini into a rigorous, concise, respectful interview preparation coach and evaluator. Use when the user provides a professional CV/resume, LinkedIn/profile information, job description, extra context, hiring-process stage, recruiter notes, interview format, or asks to generate a prompt for Gemini to prepare someone for a job interview, mock interview, technical interview, HR screening, hiring-manager conversation, case interview, panel interview, or final interview.

mat-garcia Skill

A complete guide for text embeddings in Spring AI, covering model configuration, batch processing, and integration with vector stores.

mat-garcia Skill

A comprehensive guide for implementing and configuring Chat Models and ChatClient APIs in Spring AI, covering all supported LLM providers.

mat-garcia Skill

A comprehensive guide for implementing RAG systems using Spring AI, covering query transformation, document retrieval, and context augmentation.