SoloFlow
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| soloflow_list_skillsA | 列出所有可用的 SoloFlow Skill。返回 Skill 名称、版本、描述。 |
| soloflow_get_skillA | 获取一个 Skill 的完整定义——包括 CoSTAR 背景、目标、风格、语气、受众、规则、示例和 Instructions 正文。当你需要了解某个 Skill 的详细内容时使用。 |
| soloflow_run_skillA | 使用指定的 Skill 执行一个任务。Skill 会按照其定义的 CoSTAR 框架和规则来指导 AI 输出。支持抽卡模式（一次生成多个版本）。 |
| soloflow_list_flowsA | 列出所有可用的 SoloFlow Flow 工作流。返回 Flow 名称、版本、步骤数、描述。 |
| soloflow_run_flowA | 执行一个 Flow 工作流。Flow 会按照 DAG 编排自动执行多个步骤——并行步骤同时运行，串行步骤按序运行。支持 dry_run 预览。 |
| soloflow_list_agentsA | 列出所有可用的 SoloFlow Agent 智能体。返回 Agent 名称、描述、绑定的 Skill、性格设定。 |
| soloflow_run_agentA | 让一个 Agent 执行任务。Agent 会加载其绑定的所有 Skill，注入角色设定，然后执行任务。 |
| soloflow_validate_skillB | 校验一个 Skill 文件的格式完整性。 |
| soloflow_validate_flowA | 校验一个 Flow 文件——检查 DAG 结构、循环依赖、步骤引用。返回校验结果和拓扑层级。 |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 9 tools
Each tool targets a distinct combination of entity (Skill, Flow, Agent) and action (list, get, run, validate). There is no overlap between list, run, validate, or get operations, and the three entity types are clearly separated.
All tool names follow the consistent pattern soloflow_<verb>_<entity>, with verbs limited to list, get, run, and validate. Snake_case is used uniformly, making the naming scheme highly predictable.
Nine tools is well-scoped for a platform managing three entity types with core operations. Each tool serves a clear purpose without redundancy, and the count feels neither thin nor bloated.
The set covers list, get, run, and validate for skills; list, validate, and run for flows; and list and run for agents. Missing get_flow and get_agent are minor gaps, but the core workflow (discover, validate, execute) is fully covered.