Automation
Task automation and scripting
prd
by hellbellies
"Generate a Product Requirements Document (PRD) for a new feature. Use when planning a feature, starting a new project, or when asked to create a PRD. Triggers on: create a prd, write prd for, plan this feature, requirements for, spec out."
youtube-archiver
by Chuenemulisa
Archive YouTube playlists into markdown notes with metadata, transcripts, AI summaries, and tags. Use when a user asks to import/sync YouTube playlists, archive Watch Later or Liked videos, enrich YouTube notes, batch process video notes, or automate recurring YouTube-to-markdown sync jobs with cron.
Dummy Skill
by pachoroa
No hace nada útil, solo sirve para probar el script de instalación.
ogt-docs-init
by OpenDNDApps
Initialize the OGT docs-first folder structure in a new project. Use when setting up a new project, migrating to docs-first workflow, or bootstrapping documentation structure.
basecamp
by cgk-platform
Complete Basecamp 4 REST API integration for project management, task tracking, kanban boards, messaging, scheduling, documents, and team coordination. Read for ANY Basecamp or project management work.
task-planning-shrimp
by janjaszczak
Plan, split, and track multi-step work using Shrimp Task Manager MCP (or equivalent). Use for multi-file refactors, migrations, or any work that benefits from task tracking.
ai-agents-architect
by yunaamelia
"Expert in designing and building autonomous AI agents. Masters tool use, memory systems, planning strategies, and multi-agent orchestration. Use when: build agent, AI agent, autonomous agent, tool ..."
ml-research
by Pranav-Karra-3301
Comprehensive skill for ML/AI research experiments and finetuning. Use when: (1) Setting up new ML research project ("create ML project", "init experiment") (2) Finetuning models ("finetune LLM", "adapt pretrained model", "LoRA", "QLoRA") (3) Training from scratch ("train model", "run experiment") (4) Debugging ML issues ("model not converging", "loss exploding", "GPU OOM") (5) Setting up experiment tracking ("add W&B", "setup MLflow") (6) Optimizing GPU usage ("batch size tuning", "memory optimization") (7) Creating visualizations ("plot training curves", "confusion matrix") (8) Auditing ML code ("check reproducibility", "review experiment") Triggers: "ML", "machine learning", "deep learning", "training", "finetuning", "PyTorch", "TensorFlow", "experiment", "GPU", "CUDA", "model", "neural network", "W&B", "MLflow", "reproducibility", "learning rate", "checkpoint", "epoch"
revit-mcp
by BTankut
Revit MEP automation expert for HVAC, plumbing, fire protection, and smoke control systems via the Revit MCP server. Use this skill when the user asks to write or run Revit API code through send_code_to_revit, work with ducts, pipes, fittings, accessories, valves, dampers, sprinklers, diffusers, air handling units, fans, or any mechanical/plumbing element, operate on HVAC, sanitary, domestic water, storm drainage, sprinkler, fire hose, fire pressurization, or smoke duct systems, or perform engineering calculations such as BOQ/quantity takeoff, pressure loss, critical path, or system flow. Turkish trigger phrases also apply: "kanal metrajı", "boru listesi", "sprinkler sayısı", "basınç kaybı hesapla", "yağmur tesisatı", "difüzör sayısı", "BOQ çıkar".
agent-orchestration-workflow
by NguyenGiaThuy
ACTIVATE THIS SKILL whenever the user says "I want to build", "build me", "I want to make", "make me", "create a", "let's build", "help me build", "I want to create", "let's make", or ANY phrase expressing intent to build, create, or make software (app, game, website, tool, API, service, clone, system, bot, dashboard, platform, or any other software artifact). This is the DEFAULT and ONLY skill for any "build X", "make X", or "create X" request. Do NOT answer with plans or suggestions — run the Config Collection phase from this skill instead. Also triggers on: new project, start a project, project idea, scrum, sprint, autonomous team, orchestration, PM/PO/DEV/QC, discovery, start-idea, clone an app, I want to ship.
harmony-hdc-py
by httprunner
HarmonyOS device control and UI automation via HDC. Use when tasks involve connecting to HarmonyOS devices/emulators, running hdc shell commands, inputting taps/text, launching abilities, or general device management.
teams
by khaki4
문제를 분석하여 Agent Teams를 자동 구성하고, 4가지 조율 패턴(distribute/monitor/discourse/sequence) 중 최적 패턴으로 협업한다. "/teams {문제 설명}"으로 호출한다.
siebel-development
by ujawal7
Comprehensive Siebel CRM development skill for configuration, scripting, workflow, and integration requirements. Use when: (1) Creating/modifying Siebel workflows, (2) Writing eScript or Business Services, (3) Configuring BCs, Applets, MVGs, Links, or Picklists, (4) Building REST/SOAP integrations, (5) Setting up Runtime Events, (6) Troubleshooting Siebel issues, or (7) Any Siebel CRM development task.
generate-ad-images
by feed-mob
Generate two distinct, AI-powered image variations for advertising campaigns using Google Gemini's image generation capabilities. Use when creating visual assets for ads based on campaign parameters and research insights. Triggers on requests to generate ad images, create visual assets, produce image variations for A/B testing, or develop platform-specific ad visuals.
skill-schema-v2
by xiaoshiyilangzhao1996-droid
"Load when creating, auditing, refactoring, or repairing an Agent Skill for reuse, governance, and runtime efficiency."
nvda
by denis-skripnik
Practical workflow for creating, updating, debugging, and packaging NVDA add-ons from concrete feature requests. Use when working on global plugins, app modules, gestures, settings panels, manifests, build scripts, .nvda-addon packaging, or NVDA runtime failures during add-on development. Use this skill for /nvda requests about add-on development.
forge-methodology
by davidgarciagordo
Disciplined pipeline for substantial software work with AI agents — spec → adversarial grill (×3 lenses) → global plan → parallel execution (model-per-task, isolated worktrees) → green verify → visual gate. Apply to any new feature, architectural change, large refactor, or migration. Skip for trivial one-liners.
tmf628-performance-manager
by contextware
Advanced TMF628 analytics skill. Handles time-series filtering, threshold extraction, and severity-based ranking for network hotspots.
sirv-ai-studio
by IgorVaryvoda
Guide for using Sirv AI Studio (www.sirv.studio), an AI-powered image and video processing platform. Use when working with product images, background removal, image upscaling, AI generation, video creation, batch processing, or e-commerce image workflows. Triggers on mentions of Sirv AI Studio, product photography, background removal, image upscaling, AI image generation, batch image processing, or marketplace optimization. IMPORTANT - If sirv-ai MCP tools are available (sirv_remove_background, sirv_upscale, sirv_generate, etc.), USE THEM directly for image processing tasks instead of telling user to visit the website.
quick-plan
by ianphil
This skill should be used when the user asks to "create a quick plan", "draft a plan", "capture this idea", "plan this feature", or wants a lightweight plan without full feature planning. Creates concise plans in backlog/plans/ for later expansion.
engineer
by Nomik94
Engineer 에이전트 스폰. Use when: /engineer, 설계해줘, 구현해줘, API 설계, DB 스키마, 시스템 설계, 아키텍처, TDD로 만들어줘, SOLID 적용, 성능 최적화해줘, 보안 구현, 느려, 병목, N+1, 커버리지 분석, 프로덕션 코드, 확장성 설계. NOT for: 단순 1줄 수정, 오타 수정, 코드 리뷰 (/code-review), 버그 분석 (/root-cause).
n8n-prd-generator
by prabha-oss
Convert discovery call transcripts into concise n8n Automation Blueprints with interactive question flow. USE THIS SKILL WHEN user says "create a blueprint", "generate automation spec", "convert transcript to blueprint", provides discovery call transcripts or client documentation, needs an n8n automation blueprint for workflow implementation, mentions scoping calls, client requirements, or workflow documentation, or asks to document automation requirements or create implementation specs.
Human Extractor Skill
by yousufjoyian
Claude agent skills and workspace configuration
task
by eljun
Create task documents for new features, updates, or fixes. Creates detailed specs in docs/task/*.md with full implementation context. Updates TASKS.md for tracking. Use when starting any new work.