智能体
Agent 规划、多步流程与编排
biomni
jimmc414
Autonomous biomedical AI agent framework for executing complex research tasks across genomics, drug discovery, molecular biology, and clinical analysis. Use this skill when conducting multi-step biomedical research including CRISPR screening design, single-cell RNA-seq analysis, ADMET prediction, GWAS interpretation, rare disease diagnosis, or lab protocol optimization. Leverages LLM reasoning with code execution and integrated biomedical databases.
multi-perspective
flonat
"Explore a research question from multiple independent perspectives with diverse epistemic priors. Spawns parallel agents with distinct disciplinary lenses, then synthesises findings. Triggers: 'look at this from different angles', 'get diverse perspectives'."
devils-advocate
flonat
"Challenge research assumptions and identify weaknesses in arguments. Stress-test papers before submission or revision. Triggers: 'find holes in my argument', 'what would a reviewer say'. Not for proofreading — use /proofread. Not for full peer review — use referee2-reviewer agent."
creation-guard
flonat
"Pre-flight duplicate check before creating new skills or agents. Prevents duplicates and suggests iterations. MUST be invoked before writing any new artifact definition."
system-audit
flonat
"Run parallel system audits across skills, hooks, agents, rules, bibliographies, conventions, and documentation freshness. Report-only — never modifies files."
auto-trigger
zhaono1
Workflow automation hooks for agent-playbook skills. This skill defines automatic triggers between skills - DO NOT use directly, it's a configuration skill that other skills reference.
Agent Browser
am-will
A fast Rust-based headless browser automation CLI with Node.js fallback that enables AI agents to navigate, click, type, and snapshot pages via structured commands.
session-status
WellApp-ai
Generate breadcrumb headers/footers with takt time tracking and muda metrics
skill-creator
WellApp-ai
Template and guide for creating new skills
workflow-creator
Heyvhuang
"Create workflow-* skills by composing existing skills into end-to-end chains. Turns a user idea into a workflow_spec.md SSOT (via workflow-brainstorm), discovers available skills locally + from skills.sh, and generates a new workflow-<slug>/ skill package. Use when you want to design a new workflow, chain multiple skills into a flow, or turn scattered atomic skills into a resumable plan-then-confirm workflow."
olore-a2a-latest
olorehq
Local a2a documentation reference (latest). A2A (Agent-to-Agent) protocol documentation. Use for agent communication, task management, streaming, push notifications, and enterprise-ready agent interoperability.
workflow-project-intake
Heyvhuang
"Use when you need to clarify requirements and route to the right workflow (idea → executable input). Project intake + routing: help the user brainstorm and clarify intent, persist goal/context artifacts, then dispatch to the right workflow or step skill. Default route is workflow-ship-faster (Next.js 16.1.1) for idea/prototype→launch. Triggers: project kickoff, requirements clarification, brainstorm, ideas, discovery, intake."
Frame
simota
Figma MCP Serverを活用してデザインコンテキストを抽出・構造化し、実装エージェントに渡すブリッジエージェント。Figmaデザインからコードへの橋渡し、Code Connect管理、デザインシステムルール抽出が必要な時に使用。
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。
gui-agent
Fzkuji
"GUI automation via visual perception. Screenshot → detect → click → verify. Use when asked to operate a desktop app, interact with a VM, or complete an OSWorld benchmark task."
project-real-estate-agent
vasilyu1983
Use for London residential property due diligence and investment second opinions (Zone 1-3 focus): mortgage comparison, conveyancing guidance, market/regeneration research, and developer/agent diligence. Invoke when evaluating flats, BTL yields, leasehold risk, or sanity-checking a deal. Not legal/financial advice. (project)
claude-code-agents
vasilyu1983
Create and maintain Claude Code agents/subagents (.claude/agents/*.md) with YAML frontmatter (name/description/tools/model/permissionMode/skills/hooks), least-privilege tool selection, delegation patterns (Task), context budgeting, and safety best practices.
custom-agent-definitions
laurigates
Write and configure custom agent definitions in Claude Code's agents/ directory. Use when you want to create a new agent .md file, define a specialized agent with its own system prompt and tools, set up an agent with isolated context, or configure agent capabilities and restrictions in your project's .claude/ configuration.
agents-analyze
laurigates
Analyze all plugins for sub-agent opportunities. Identifies skills with verbose output, gaps in agent coverage, and model selection improvements.
blueprint-development
laurigates
"Generate project-specific rules and commands from PRDs for Blueprint Development methodology. Use when generating behavioral rules for architecture patterns, testing strategies, implementation guides, or quality standards from requirements documents."
nelson
kylesnowschwartz
This skill SHOULD be used when work requires multi-agent coordination, parallel execution, or structured team workflows. Commands a Royal Navy agent squadron from sailing orders through execution and stand-down with risk-tiered quality gates and a captain's log.
task-management
joelhooks
"Manage Joel's task system in Todoist. Triggers on: 'add a task', 'create a todo', 'what's on my list', 'today's tasks', 'what do I need to do', 'remind me to', 'inbox', 'complete', 'mark done', 'weekly review', 'groom tasks', 'what's next', or when actionable items emerge from other work. Also triggers when Joel mentions something he needs to do in passing — capture it."
gateway-setup
joelhooks
"Set up a persistent AI agent gateway on macOS with Redis event bridge, heartbeat monitoring, and multi-session routing. Interactive Q&A to match your intent — from minimal (Redis + extension) to full (embedded daemon + Telegram + watchdog). Use when: 'set up a gateway', 'I want my agent always on', 'event bridge', 'heartbeat monitoring', 'agent notifications', or any request to make an AI agent persistent and reachable."
add-skill
joelhooks
Create new joelclaw skills with the idiomatic process — repo-canonical, symlinked, git-tracked, slogged.