Browse reusable Agent Skills, each with a clear purpose and practical guidance.
Convert a GraphQL endpoint, OpenAPI spec, or MCP server into bash CLI commands and a `tools.*` JS API runnable inside `just-bash`'s `js-exec` sandbox. Use when the user wants to expose a remote API to a sandboxed bash agent, build a tool-calling agent on top of just-bash, or generate CLI commands from an existing API spec.
Inspect and manage guarded Codex App-native or launchd heartbeats for Codex main control threads. Use when the user wants Codex to periodically continue a specific thread only when it is idle, avoid interrupting active work, keep App-visible interactions, inspect thread status, or enable/disable project autopilot heartbeats.
将传统文档导向的 Procedural Skill 转换为紧凑的 Strategy Gene 格式。基于论文 "From Procedural Skills to Strategy Genes" 的 Gene Evolution Protocol (GEP)，将 ~2500 token 的文档型 Skill 蒸馏为 ~200-300 token 的控制型 Gene 集合。当用户要求将 skill 转为 gene、优化 skill 的 token 效率、将经验知识蒸馏为紧凑控制指令、或提到 gene/GEP/strategy-gene 时调用。
Show full session token usage, costs, TLDR savings, and hook activity
Research-to-implement pipeline chaining 5 MCP tools with graceful degradation
Parallel Agent Type Contracts
Create and configure Claude Code sub-agents with custom prompts, tools, and models
新增或更新 CCX 项目中的 Claude 模型注册。当用户提到新模型发布、添加模型、更新模型元数据、model registry、模型注册时触发。覆盖上游能力表、AgentModelProfile、优先级排序和代码生成。