Agent Skills Hub

reflect-appworld-failure

Analyze AppWorld task failures to extract specific API patterns and generate actionable playbook bullets with concrete code examples.

nav-task

Manage Navigator task documentation: create implementation plans, archive completed features, and maintain the task index for Claude Code workflows.

read-only-gh-pr-review

Review backend pull requests with security enforcement and GitHub CLI integration in a strict read-only environment.

ctx-planning

Generate daily and weekly planning reports from backlog and carryover state, applying WIP limits and priority rules from BaseContext.yaml with automatic git commit/push.

gpt-researcher

GPT Researcher is an autonomous AI agent for comprehensive web and local research, generating detailed, cited reports using a planner-executor-publisher architecture.

claude-code-project-bootstrap

Project bootstrap for Claude Code with safety guardrails, git workflow automation, project auditing, and structured multi-phase planning.

news-briefing

Real-time AI news briefing tool. Instantly search the web for any topic, get summarized insights in Chinese, and receive professional briefing cards via Feishu.

agentdb-state-manager

Persistent state management and workflow analytics using DuckDB for task dependency tracking, historical metrics, and context checkpointing.

webmcp

Create and test AI-ready MCP tools for any web application. Inject code, automate browser interactions, and turn websites into intelligent agents.

lead-gen-pipeline

AI-powered lead generation pipeline: intelligent lead scoring (0-100) and context-aware follow-up generation for sales, cold outreach, and CRM integration.

problem-mapping

Structured problem-framing tool for design sprints and product strategy. Facilitates collaborative or individual sessions to define goals, stakeholders, constraints, and pain points before solution generation.

skill-reinforcement

An automated meta-learning skill that improves agent workflows by capturing patterns, failures, and shortcuts after each task execution.