Agents
AI agents and automation
claude-agent-pr-review-toolkit-silent-failure-hunter
by monkey1sai
Converted from Claude plugin agent "silent-failure-hunter" (pr-review-toolkit).
skill-forge-quiz
by zjfls
Skill Forge 试卷生成工具。支持 AI 生成和 JSON 导入。
experiment-tracker
by aibangjuxin
You are a meticulous and data-obsessed Experiment Tracker. You act as the central nervous system for a growth or product team, ensuring that every experiment is well-documented, tracked, and that the learnings from each test are captured and shared. You are highly organized and proficient with tools like Notion, Airtable, or Jira.
agent-orchestration
by Agentient
Multi-agent orchestration patterns including coordinator agents, LlmAgent vs WorkflowAgent selection, agent-as-tool pattern, and inter-agent communication via session state. PROACTIVELY activate for: (1) multi-agent systems and agent coordination, (2) sub-agent delegation and agent-as-tool implementation, (3) workflow orchestration with LlmAgent and WorkflowAgent. Triggers: "multi-agent", "orchestration", "agent team"
claude-command-code-review-code-review
by monkey1sai
Converted from Claude plugin command "code-review" (code-review). Use
claude-agent-pr-review-toolkit-code-simplifier
by monkey1sai
'Converted from Claude plugin agent "code-simplifier" (pr-review-toolkit).
Oracle Diagram Generator - Complete Reference
by oci-ai-architects
Claude Code skills for OCI AI Architects. Community-led reference implementations and patterns.
pr-screenshot
by madeyexz
Add before/after comparison screenshots to a PR using browser automation. Captures UI on the base branch and the PR branch, saves to docs/screenshot/, and updates the PR body with a side-by-side comparison table using GitHub CDN URLs.
github-actions-daemon
by fast-gateway-protocol
Fast GitHub Actions operations via FGP daemon - 30-60x faster than gh CLI. Use when user needs to trigger workflows, check run status, download artifacts, or view logs. Triggers on "github actions", "trigger workflow", "workflow run", "check CI", "download artifact", "actions logs".
analyze-stock
by jssfy
一键综合分析某只股票/公司。通过并行子代理同时采集股价、新闻舆论、行业对比、市场环境、公司官网五个维度的数据，然后在主线程进行交叉分析、因果归因和趋势预测，输出标准化 HTML 分析报告（含当日行情和7日趋势）。触发词：分析XX股票、analyze TICKER、XX怎么样、XX值得买吗。支持A股、港股和美股。
langgraph-python-expert
by StrayDragon
Expert guidance for LangGraph Python library. Build stateful, multi-actor applications with LLMs using nodes, edges, and state management. Use when working with LangGraph, building agent workflows, state machines, or complex multi-step LLM applications. Requires langgraph, langchain-core packages.
cruise-control
by jschulte
Automatic mode - shift through all 6 gears sequentially without stopping. Like cruise control or automatic transmission, this runs the entire StackShift workflow from analysis to implementation in one go. Perfect for unattended execution or when you want to let StackShift handle everything automatically.
agent-browser
by clawdbrunner
Browser automation CLI for AI agents using Vercel's agent-browser. The best tool for AI-driven browser automation — uses deterministic refs from accessibility trees instead of fragile selectors. Optimized for LLMs with fast Rust CLI, JSON output, and purpose-built AI workflows. Use when you need reliable, scriptable browser automation that just works.
code-simplicity-reviewer
by carmandale
Final review pass to ensure code is as simple and minimal as possible. Use after implementation is complete to identify YAGNI violations and simplification opportunities.
excellence
by clearsmog
Multi-agent document review (visual, pedagogy, proofreading, domain). Use for comprehensive quality check before milestones. Works with any supported file type.
claude-command-agent-sdk-dev-new-sdk-app
by monkey1sai
Converted from Claude plugin command "new-sdk-app" (agent-sdk-dev). Use
task-decomposition
by mindmorass
Break down complex tasks into actionable, atomic steps that can be executed by individual agents.
agent-init
by dyxushuai
Initialize or improve AGENTS.md files that define how coding agents operate in a repo. Use when asked to set up or replace an agent init command (Codex, Claude), standardize multi-agent behavior, or audit an existing AGENTS.md for clarity, commands, boundaries, and repo-specific context. For Claude Code, also create CLAUDE.md as a symlink to AGENTS.md.
Continuous Calibration, Continuous Development (CCCD)
by Coowoolf
105 Product Management Skills extracted from Lenny's Podcast - For use with Claude Code / Cursor / Windsurf
claude-agent-feature-dev-code-explorer
by monkey1sai
Converted from Claude plugin agent "code-explorer" (feature-dev). Use
soul-factory
by frogeclawdbot
A training curriculum for Clawdbot agents. This skill provides soul templates, best practices, and self-test drills to help agents level up.
claude-agent-plugin-dev-agent-creator
by monkey1sai
'Converted from Claude plugin agent "agent-creator" (plugin-dev). Use
design-iterator
by carmandale
Iteratively refines UI design through N screenshot-analyze-improve cycles. Use PROACTIVELY when design changes aren't coming together after 1-2 attempts, or when user requests iterative refinement.
Oracle Agent Spec Expert Skill
by oci-ai-architects
Claude Code skills for OCI AI Architects. Community-led reference implementations and patterns.