Agents
AI agents and automation
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 ..."
immundata
by immunomind
Use this skill for AIRR-seq (Adaptive Immune Receptor Repertoire / VDJ-seq) data analysis with immunarch + immundata in R, including ingestion, receptor schema design, immutable transformations, clonality/diversity/public overlap metrics, and Seurat/AnnData integration.
agent-skill-rules
by qiao-925
Agent Skills 开放标准与治理规则。用于 skill 的创建、修改、重构、迁移、审计与维护，提供平台无关的结构标准、frontmatter 规范、渐进式披露与质量门禁。
todo-list
by shadowcz007
智能待办事项管理技能。支持自然语言时间解析、事项记录与追踪、进度更新，数据持久化到本 skill 目录下 temp 的 Markdown；可通过 node scripts/time.js 与 node scripts/todo.js 调用。
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.
blecsd-ai
by Kadajett
Build AI/LLM terminal interfaces with @blecsd/ai. Covers streaming conversation UIs, markdown rendering, token tracking, tool call visualization, and agent workflow displays.
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.
agent-skills-manager
by DriveSpark
"Automatically installs and links local agent skills to available IDEs (Trae, Antigravity). Invoke when user wants to install, add, or link a local skill."
analyze-ticket
by nicolas-codemate
Skill for analyzing ticket complexity and determining required workflow phases. Uses scoring system to classify tickets as SIMPLE, MEDIUM, or COMPLEX, which determines exploration depth and planning approach.
agent-profile
by pythias
Use this skill whenever the user wants an Agent to switch, list, inspect, compare, validate, or manage predefined Agent profiles/personas/workspaces. This includes requests like "switch to architect", "use ops profile", "切到写作人格", "agent-profile switch", or anything involving USER.md, SOUL.md, and AGENTS.md profile sets. The Agent must identify the target Agent configuration directory before switching.
DKG Working Memory Bridge — Agent Skill
by jalopy1
Requires a running DKG v10 node. Auth token from ~/.dkg/auth.token or DKG_AUTH_TOKEN.
pubfi-walletconnect-transactions
by helixbox
"Use when user wants to send/transfer ETH or ERC20 tokens (USDC, USDT, DAI, etc.) to an address. Supports Ethereum, Polygon, Arbitrum, Optimism, and Base chains. Connects wallet via WalletConnect QR code for transaction signing."
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.
skills-manager
by nicmeriano
Manage your agent skills - save, clone, and install skills from GitHub. Use when user wants to save/bookmark a skill, clone a skill to customize, add/install a skill, list saved skills, or install all saved skills. Triggers on "save skill", "clone skill", "add skill", "install skill", "list skills", "unsave skill", "setup skills".
clashd-27
by wiard
Live in a 27-cell cube. Clash with other agents. Miss it and it's gone.
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.
build
by pmco23
Use after /plan to execute the build. Opus leads and coordinates; Sonnets implement. Supports --parallel (independent agent per task group, own context) or --sequential (one task group at a time in current session). Invokes drift-verifier agent post-build. Writes .pipeline/build.complete on pass.
agentic-systems
by NichollsB
A comprehensive skill collection for designing and building production-grade agentic AI systems. Use when building a new agentic system from scratch, making architectural decisions (workflow vs agent, multi-agent topology, framework selection), implementing LangGraph graphs, adding guardrails and security, configuring persistence and memory, setting up model routing and observability, deploying to production, or debugging agent failures. Also use when the user mentions agents, LangGraph, multi-agent, orchestrator, workflows, agentic architecture, or is working on any AI system that uses tools, has multiple steps, or needs to make decisions at runtime. This collection covers the full lifecycle from design through deployment and maintenance.
log-skill
by maxoreric
记录执行过程的 Skill。当需要保存执行记录、工作日志时触发。触发词：记录、log、日志、work log、保存记录。
task-create
by yousufjoyian
Distill a conversation into a comprehensive task briefing for the project queue
unity-claude
by MitchellX
Dispatch Claude Code tasks to Unity HPC via SSH. Use when user asks to run Claude Code on Unity, dispatch a coding task to Unity, or asks Unity's Claude to do something (read/analyze/modify code on Unity). Also triggers on "dispatch to unity", "ask unity claude", "在unity上跑". Tasks run in background via sessions_spawn, auto-notify on completion via Discord.
workflow-designer
by falak-vhora
Design detailed, implementation-ready engineering workflows as checklists. Use when the user asks for a workflow, process, or step-by-step implementation plan related to coding, refactors, or technical tasks.
steve
by aaarnv
The ultimate autonomous dev pipeline. Combines wavybaby (CoVe verification, skill discovery, MCP tooling) + GSD (roadmaps, phases, plans, discovery, state tracking) + Ralph (autonomous loop with circuit breakers). Generates a PRD, equips itself with the best tools, bootstraps a full GSD .planning/ structure, then runs Ralph to autonomously execute each plan with CoVe-verified code until the milestone is complete.
prompt-engineering
by mguinada
"Creates system prompts, writes tool descriptions, and structures agent instructions for agentic systems. Use when the user asks to create, generate, or design prompts for AI agents, especially for tool-using agents, planning agents, or autonomous systems. PROACTIVE ACTIVATION: Auto-invoke when designing prompts for agents, tools, or agentic workflows in AI projects. DETECTION: Check for agent/tool-related code, prompt files, or user mentions of \"prompt\", \"agent\", \"LLM\". USE CASES: Designing system prompts, tool descriptions, agent instructions, prompt optimization, reducing hallucinations."