跳到正文
cccskills
免费在 GitHub 公开

chain

Use when the workflow needs multi-step processing with sequential, parallel, or conditional tool compositions and proper data flow.

中文简介正在准备中。当前显示原文说明。

sharpdeveye/maestro星标 591(GitHub 591 + cccskills 0)

实测评分 未实测

查看安装方法

包含的文件(1)

  • SKILL.md2.4 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

MANDATORY PREPARATION

Invoke /agent-workflow — it contains workflow principles, anti-patterns, and the Context Gathering Protocol. Follow the protocol before proceeding — if no workflow context exists yet, you MUST run /teach-maestro first. Consult the tool-orchestration reference in the agent-workflow skill for composition patterns and error handling.


Design tool chains that do complex work reliably. A chain is only as strong as its weakest link.

Chain Patterns

Sequential: A → B → C (each step depends on the previous) Parallel: [A, B, C] → Merge (independent steps run simultaneously) Conditional: A → (if X then B, else C) → D (branching based on results) Iterative: A → Check → (if not done) → A again (loop until convergence)

Chain Design Process

For each chain, define:

## Chain: [Name]

### Steps
1. [Tool A] — [what it does] — Input: [schema] — Output: [schema]
2. [Tool B] — [what it does] — Input: [output of step 1] — Output: [schema]
3. [Tool C] — [what it does] — Input: [output of step 2] — Output: [schema]

### Data Flow
Step 1 output.field_a → Step 2 input.source_data
Step 2 output.results → Step 3 input.items

### Error Handling
Step 1 failure → [retry 3x, then return error]
Step 2 failure → [return partial results from step 1]
Step 3 failure → [retry with simplified input]

### Constraints
Max total execution time: 60s
Max retries per step: 3

Chain Validation

  • Data schemas are compatible between connected steps
  • Every step has error handling
  • Total chain timeout is set
  • Maximum iteration count is set for loops
  • Partial results are handled (what if step 2 of 4 fails?)

Recommended Next Step

After building the chain, run /fortify to add error handling at each step, then /evaluate to test the full pipeline.

NEVER:

  • Build chains without defining data contracts between steps
  • Create loops without maximum iteration counts
  • Skip error handling at any step (the chain breaks at the weakest link)
  • Assume output of step N is always valid input for step N+1
  • Build long chains when a single prompt could handle the task

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

Use when the workflow is too slow, too expensive, or both and needs latency, cost, or token usage optimization.

中文简介正在准备中。当前显示原文说明。

sharpdeveye/maestro5912026年4月29日 更新

Use when porting a workflow to a different AI provider, deployment environment, model tier, or organizational context.

中文简介正在准备中。当前显示原文说明。

sharpdeveye/maestro5912026年4月29日 更新

Use when any Maestro command is invoked — provides foundational workflow design principles across prompt engineering, context management, tool orchestration, agent architecture, feedback loops, knowledge systems, and guardrails.

中文简介正在准备中。当前显示原文说明。

sharpdeveye/maestro5912026年4月29日 更新

amplify

免费

Use when the workflow works but needs to handle more complex cases or produce higher-quality output through better tools, context, prompts, or models.

中文简介正在准备中。当前显示原文说明。

sharpdeveye/maestro5912026年4月29日 更新

calibrate

免费

Use when workflow components are inconsistent, naming conventions vary, or a new team member's work needs alignment to project standards.

中文简介正在准备中。当前显示原文说明。

sharpdeveye/maestro5912026年4月29日 更新

capture

免费

Capture a session summary — what was done, what decisions were made, and what to do next.

中文简介正在准备中。当前显示原文说明。

sharpdeveye/maestro5912026年4月29日 更新

查看 sharpdeveye 的全部技能

报告此技能的问题