智能体
Agent 规划、多步流程与编排
Lore
simota
エコシステム横断の知識統合・パターン抽出・伝播を担うメモリキュレーター。エージェントjournalから共通パターンを発見し、カタログ化して関連エージェントへ配信。知識の腐敗検出・ベストプラクティス伝播により制度的記憶を維持。
Darwin
simota
エコシステム自己進化オーケストレーター。プロジェクトライフサイクルを検出し、エージェントの関連性を評価し、横断的知識を統合してエコシステム全体を進化させる。エコシステムの健全性チェックや進化提案が必要な時に使用。
tech-debt-portfolio
proflead
Assess and prioritize tech debt items. Use when a senior developer needs an investment plan for debt reduction.
Architect
simota
æ°è¦ã¹ãã«ã¨ã¼ã¸ã§ã³ãã®è¨è¨ã»çæãè¡ãã¡ã¿ãã¶ã¤ãã¼ãã¨ã³ã·ã¹ãã ã®ã®ã£ããåæãéè¤æ¤åºãSKILL.mdï¼ãªãã¡ã¬ã³ã¹çæãNexusçµ±åè¨è¨ãæ å½ãæ°è¦ã¨ã¼ã¸ã§ã³ãä½æãå¿ è¦ãªæã«ä½¿ç¨ã
cursor-webhooks
hookdeck
Receive and verify Cursor Cloud Agent webhooks. Use when setting up Cursor webhook handlers, debugging signature verification, or handling Cloud Agent status change events (ERROR, FINISHED).
ask
doodledood
Single-model consultation using consultant agent. Defaults to gpt-5.2-pro.
investigate-bug
doodledood
Deep bug investigation using consultant agent. Identifies root causes and fix suggestions.
explore-codebase
doodledood
'Find all files relevant to a query with orthogonal exploration for comprehensive coverage. Returns topic-specific overview + file list with line ranges. Uses parallel agents for thorough+ levels to ensure nothing is missed.'
clean-slop
doodledood
Find and remove AI-generated slop (useless comments, verbose patterns, unnecessary abstractions).
review-prompt
doodledood
Review and analyze LLM prompts using the 10-Layer Architecture. Provides detailed assessment without modifying files.
research-web
doodledood
'Deep web research with parallel investigators, multi-wave exploration, and structured synthesis. Spawns multiple web-researcher agents to explore different facets of a topic simultaneously, launches additional waves when gaps are identified, then synthesizes findings. Use when asked to research, investigate, compare options, find best practices, or gather comprehensive information from the web.\n\nThoroughness: quick for factual lookups medium for focused topics thorough for comparisons/evaluations (waves continue while critical gaps remain) very-thorough for comprehensive research (waves continue until satisficed). Auto-selects if not specified.'
define-design-guidelines
doodledood
'Create a DESIGN_GUIDELINES.md that defines how to design UI/UX for your customer. Requires CUSTOMER.md to exist first. Covers aesthetic direction, design tokens, typography, color, motion, components, and layout patterns. Bakes in frontend-design skill principles to avoid generic AI aesthetics.'
git-chain
dashed
Manage and rebase chains of dependent Git branches (stacked branches). Use when working with multiple dependent PRs, feature branches that build on each other, or maintaining clean branch hierarchies. Automates the tedious process of rebasing or merging entire branch chains.
find-skills
sanity-io
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
openai-agents-sdk
laguagu
OpenAI Agents SDK (Python) development. Use when building AI agents, multi-agent workflows, tool integrations, or streaming applications with the openai-agents package.
auto-dev-setup
miles990
設定 Auto-Dev workflow，實現 Human-in-the-Loop 自動化開發
get-block-number
tradingstrategy-ai
Get the latest block number for a blockchain using Web3.py and JSON-RPC environment variables
more-vaults
tradingstrategy-ai
Add more vault smart contract types to an existing protocol
agent-creator
ssiumha
Creates and manages custom Claude Code sub-agents. Use when automating workflows as dedicated agents, delegating recurring tasks, or modifying .claude/agents/ files.
tidy
ssiumha
Performs small structural code cleanups (tidyings). Use when preparing code changes, removing dead code, reducing nesting, or cleaning up before feature work.
claudish-usage
MadAppGang
CRITICAL - Guide for using Claudish CLI ONLY through sub-agents to run Claude Code with any AI model (OpenRouter, Gemini, OpenAI, local models). NEVER run Claudish directly in main context unless user explicitly requests it. Use when user mentions external AI models, Claudish, OpenRouter, Gemini, OpenAI, Ollama, or alternative models. Includes mandatory sub-agent delegation patterns, agent selection guide, file-based instructions, and strict rules to prevent context window pollution.
brainstorming
FradSer
This skill should be used when the user has a new idea, feature request, or ambiguous requirement. It clarifies needs, explores options, and produces a solid design document and BDD specs before implementation starts.
Git Workflow Guide
AsiaOstrich
Guide Git branching strategies, branch naming, and merge operations. Use when: creating branches, merging, pull requests, Git workflow questions. Keywords: branch, merge, PR, pull request, GitFlow, GitHub Flow, 分支, 合併, 工作流程.
specification-writing
EpicenterHQ
Write technical specifications that give agents enough context to implement features while leaving room for autonomous research and decision-making. Use when planning features, documenting architecture decisions, or creating implementation guides.