AgentCC Logo

AgentCC

Skills MCP Servers AI Tools
Home
Browse

deepplan

fieldingfielding

Implementation planning phase. Creates and iterates plan.md until it is implementation-ready and approved by the human. Use after research.md is ACCEPTED, or when the user says /deepplan, "plan this", "create a plan", "design the implementation", or "write a plan". Uses Human++ markers (!! blocker, ?? question, >> reference).

194 days ago

presearch

fieldingfielding

Deep codebase research phase. Creates and iterates research.md as a review surface until it is accurate and grounded in the actual codebase. Use when the user says /presearch, "research this", "understand the code", "investigate the system", or needs to start a new task with proper research. Uses Human++ annotation markers (!! blocker, ?? question, >> reference).

194 days ago

FAQ

AgentCC is a discovery hub for AI agent capabilities. We index Agent Skills as the primary dataset, and also organize MCP servers and selected AI tools so developers can quickly find, compare, and evaluate what to integrate into their workflows.
An Agent Skill is a reusable capability package for an AI agent. It can define workflows, tool usage patterns, domain knowledge, or execution rules that help the agent perform more reliably in a specific task or environment.
AgentCC is a resource and discovery layer, not a one-click installer. On each skill page, you should review the repository, file tree, install command, and usage notes, then integrate it according to the runtime or client you are using.
No. AgentCC primarily indexes external repositories and metadata. We help you understand what a skill is, where it comes from, and how it may be used, but execution and security decisions still belong to your own runtime environment.
No directory can guarantee absolute safety. AgentCC can help surface repository links, file structures, and metadata, but you should still verify permissions, external dependencies, API usage, and code quality before using a skill in production or on sensitive machines.
Yes. AgentCC is designed to be an evolving resource graph. As the submission and curation workflow matures, contributors will be able to recommend high-quality skills, MCP servers, and AI tools into the directory.
Can't find your answer here? Get in touch

Explore

  • Skills Directory
  • MCP Servers
  • AI Tools
  • Changelog

Platform

  • About AgentCC
  • Privacy Policy
  • Terms of Service

Network

CS
ClawiSkill

Explore ClawiSkill for more agent-related content, projects, and community context.

onlinev0.1.0
AgentCC / The Agent Context Center
© 2026 AgentCC
fielding

Explore Skills

2 available
fielding
Sort by:
fielding