Agents
AI agents and automation
cc-dev-skills
by choru-k
Guide for creating effective skills. Use for "create a skill", "new skill", "write a SKILL.md", "update a skill", "skill template", or extending Claude's capabilities with specialized workflows and tools.
architecting-agents
by Git-Fg
"Provides industry-proven design patterns for effective AI agents based on production systems like Claude Code, Manus, and Cursor. Use when designing agent architectures, optimizing context management, or implementing sub-agent patterns."
implementation-agent
by vishal2457
Implements tracker subtasks tagged implement, publishes/updates the PR, and routes review using handoff-first context loading, lazy artifact reads, and rework_mode support.
workflow-local-dev
by lgariv-dn
Support local workflow platform development in the DAP workspace across frontend, backend, and infra teams. Provides access to Kubernetes (Kind), Tilt service management, database queries, and troubleshooting. Use when building backend/API features, adjusting infra configurations, checking logs, running tests, or debugging issues against locally deployed workflow engine components.
agent-builder
by Within-7
Design and build AI agents for any domain. Use when users: (1) ask to "create an agent", "build an assistant", or "design an AI system" (2) want to understand agent architecture, agentic patterns, or autonomous AI (3) need help with capabilities, subagents, planning, or skill mechanisms (4) ask about Claude Code, Cursor, or similar agent internals (5) want to build agents for business, research, creative, or operational tasks Keywords: agent, assistant, autonomous, workflow, tool use, multi-step, orchestration
session-handoff
by cachemoney
"Creates comprehensive handoff documents for seamless AI agent session transfers. Triggered when: (1) user requests handoff/memory/context save, (2) context window approaches capacity, (3) major task milestone completed, (4) work session ending, (5) user says 'save state', 'create handoff', 'I need to pause', 'context is getting full', (6) resuming work with 'load handoff', 'resume from', 'continue where we left off'. Proactively suggests handoffs after substantial work (multiple file edits, complex debugging, architecture decisions). Solves long-running agent context exhaustion by enabling fresh agents to continue with zero ambiguity."
forge-team
by fwehrling
FORGE + Agent Teams — Exploits Agent Teams for true parallel execution of FORGE agents. 3 patterns: pipeline (full pipeline with parallel stories), party (multi-agent debate), build (parallel story development). Requires CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1. Usage: /forge-team pipeline "objective" /forge-team party "topic" /forge-team build [STORY-IDs]
track-issue-flow
by myuon
Operate the local-first track issue workflow from request intake to completion using the CLI. Use this when users ask to list issues, pick a numbered item from track list, inspect details with track show, update status/priority/labels, or move an issue into active work while keeping progress visible in the tracker.
owasp-kubernetes-top-10
by yariv1025
"OWASP Kubernetes Top 10 - prevention, detection, and remediation for Kubernetes security. Use when designing or reviewing K8s workloads and clusters - workload config, supply chain, RBAC, policy enforcement, logging, authentication, network segmentation, secrets, cluster components, vulnerable components."
forge-build
by fwehrling
FORGE Dev Agent — Implements a story with unit + functional tests. Usage: /forge-build or /forge-build STORY-XXX
workers-specialist
by SteveLeve
Provide Cloudflare Workers runtime guidance for routing, bindings, performance, security headers, rate limiting, and Hono patterns used in this repo.
create-agent
by khw1031
Claude Code Agent를 생성합니다. 에이전트 생성, AGENT.md 작성, 새 에이전트 만들기 요청 시 활성화.
mixseek-skills
by drillan
MixSeek Agent Skills collection for AI coding assistants. Provides workspace management, team configuration, evaluation setup, and debugging tools for MixSeek-Core.
migration-skill
by PloLink
从 Cursor 开发模式迁移到 Claude Code 开发模式的完整指南。当项目需要从 Cursor AI IDE 切换到 Claude Code CLI 时使用此技能，包括配置迁移、文档结构转换、工作流适配等。
cloudflare-agents
by ma1orek
Build AI agents with Cloudflare Agents SDK on Workers + Durable Objects. Provides WebSockets, state persistence, scheduling, and multi-agent coordination. Prevents 23 documented errors. Use when: building WebSocket agents, RAG with Vectorize, MCP servers, or troubleshooting "Agent class must extend", "new_sqlite_classes", binding errors, WebSocket payload limits.
triage-agent
by vishal2457
Performs lightweight workflow triage on a parent issue, classifies execution track as trivial standard complex, sets skip_steps guidance, and emits a compact handoff summary for downstream agents without reading full issue history.
epub-chinese-cleaner
by William-Yeh
Use when a user has a Chinese epub with vertical text direction or right-to-left page progression and wants to convert it to standard horizontal reading. Converts from vertical layout (直排) to horizontal layout (橫排) with punctuation normalization and left-to-right page flow.
spendguard-strict-budget-runner
by cynsta
Run application agents through SpendGuard with strict hard budget caps. Use when setting up spendguard-sidecar, creating agent IDs, setting or topping budgets, sending OpenAI/Grok/Gemini/Anthropic calls through SpendGuard endpoints, and troubleshooting budget enforcement errors like insufficient budget, in-flight lock conflicts, missing x-cynsta-agent-id, or remote pricing signature failures.
summarize-ai-agent-trends
by Ontos-AI
Summarizes weekly trends for 'AI Agent Tools', providing a Top 10 table with names, official links, core capabilities, and application scenarios, along with reusable research steps.
iterm2-agent
by xjthy001
Control iTerm2 terminal sessions — read the screen, run commands, send keystrokes, interact with TUIs, monitor output, and manage panes. Use when the user mentions iTerm2, terminal control, split pane, read screen, send keys, or session management. Triggers on "what's on my terminal", "run this in iTerm", "split the terminal", "stop the process", "monitor the output".
ai-era-architecture-principles
by shimo4228
"Framework adoption decision matrix: custom vs large frameworks in the Claude Code era. Use when evaluating whether to adopt a large framework or build custom with AI."
superplan
by choru-k
Hierarchical planner for big/medium/small tiers. Resolves save location, selects one tier, and executes that tier directly. Supports root→phase→item expansion workflow.
sensitive-browser
by napoleond
Execute sensitive browser actions (login, payments, form filling) outside the core agent loop using a dedicated CLI tool. Use when Claude needs to handle credentials, payment information, or other sensitive data in browser automation workflows. Triggers when users ask to log into websites, fill payment forms, or perform authenticated browser actions where sensitive data must be kept secure and separate from the main agent context.
decision-envelope
by tracemem
Using the decision envelope pattern for structured thinking.