Install any skill in seconds. Free to start, no credit card required.
Get Started Free →jnmetacode/workflow-runner
在 Claude Code / OpenClaw / Cursor 中直接运行 agency-orchestrator YAML 工作流——无需 API key,使用当前会话的 LLM 作为执行引擎。当用户提供 .yaml 工作流文件或要求多角色协作完成任务时触发。
Passed 14 of 20 test cases with the skill, and 7 of 20 without it.
and 9 more in the full report
9 fixed6 passed either way5 still failing2 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 9 test cases the skill fixed. Same model, same prompt, with and without the skill.
An agency workflow declares input `depth` with `required: false` and `default: 'deep'`, and input `notes` with `required: false` and no default. The user provides no values for either. What values are assigned?
| Checked | Without skill | With skill |
|---|---|---|
| Assigns default value 'deep' to depth and empty string to notes. | Missed | Passed |
The instructions your model reads when the skill loads.
直接在当前会话中执行 agency-orchestrator 的 YAML 工作流,无需配置 API key。当前 LLM 就是执行引擎——依次扮演每个角色完成任务。
.yaml 工作流文件(如 运行 workflows/story-creation.yaml)agency-agents-zh 并希望直接在 AI 工具内编排多角色按以下顺序执行,不要跳步:
用 Read 工具读取用户指定的 YAML 文件,提取以下字段:
name: "工作流名称"
agents_dir: "agency-agents-zh" # 角色定义目录
inputs: # 输入变量
- name: xxx
required: true/false
default: "默认值"
steps: # 执行步骤
- id: step_id
role: "category/agent-name" # 角色路径
task: "任务描述 {{变量}}" # 支持模板变量
output: variable_name # 输出变量名
depends_on: [other_step_id] # 依赖关系
忽略 llm、concurrency、timeout、retry 配置——Skill 模式使用当前会话的 LLM,这些字段仅用于 CLI 模式。
定位角色目录:用 Bash test -d 按以下顺序检查,用第一个存在的:
{agents_dir}/(如 ./agency-agents-zh/)../{agents_dir}/(上级目录){agents_dir}/node_modules/agency-agents-zh/test cases passed, vs 7 / 20 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.