Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Agent Workflow Pattern Designer

ASecurity

当需要为多步骤 LLM 任务选型多智能体编排模式、定义交接契约或重构存在上下文膨胀/交接不可靠的工作流时使用;做模式选型(顺序/并行/路由/编排/评估)+ 用脚手架生成 JSON 骨架 + 补齐交接契约、重试超时与质量门,产出可落地的工作流配置;不适用于单条结构化提示即可解决的简单任务;触发词:多智能体、工作流编排、交接契约

3 stars
0 votes
0 copies
1 views
Added 9/19/2026
ai-agentspythonbash

Works with

cursorcli

Security Analysis

A100/100

Scanned 9/19/2026

$npx -y skills add findscripter/everything-skills --skill agent-workflow-pattern-designer --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Agent Workflow Pattern Designer?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Agent Workflow Pattern Designer
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/findscripter-agent-workflow-pattern-designer/badge)](https://www.skillsdirectory.com/skills/findscripter-agent-workflow-pattern-designer)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: agent-workflow-pattern-designer
title: 智能体工作流模式设计
description: 当需要为多步骤 LLM 任务选型多智能体编排模式、定义交接契约或重构存在上下文膨胀/交接不可靠的工作流时使用;做模式选型(顺序/并行/路由/编排/评估)+ 用脚手架生成 JSON 骨架 + 补齐交接契约、重试超时与质量门,产出可落地的工作流配置;不适用于单条结构化提示即可解决的简单任务;触发词:多智能体、工作流编排、交接契约
domain: 智能/agents
triggers: [多智能体工作流, 工作流编排模式, 智能体交接契约, 单智能体还是多智能体, 上下文膨胀重构, 顺序/并行/路由/编排/评估, agent workflow, orchestrator]
tags: [智能体, agents, 工作流编排, 多智能体, 模式选型, 交接契约, 成本控制]
level: 进阶
status: stable
agents: [claude-code, codex, cursor, gemini-cli]
tools: [Bash, Write, Read]
requires: []
related: [multi-agent-workflow-designer, multi-agent-system-designer, langgraph-agent-framework, crewai-multi-agent]
combines_with: [agent-tool-design, llm-agent-benchmarking, context-compression]
license: MIT
source: alirezarezvani/claude-skills
source_license: MIT
---
采编自 alirezarezvani/claude-skills(MIT),适配重写为中文版本。

## 何时使用

在「实现之前」先确定多智能体工作流的结构时使用本技能:

- 单条提示无法承载任务复杂度,需要拆成多个有明确边界的专职智能体。
- 要在编码前确定确定性的工作流骨架(节点、依赖、交接字段)。
- 需要为质量或安全设置校验回路(生成 + 评审门)。
- 重构一个已存在但「上下文膨胀」或「交接不可靠」的 LLM 流水线。
- 纠结「单智能体 vs 多智能体」该选哪个。

不该用(负边界):

- 一条结构良好的提示即可解决的任务——不要过度编排(见注意事项第 1 条)。
- 纯粹的提示词调优、模型选型、或与「工作流结构」无关的单步推理问题。

## 步骤 / 指令

1. 按「依赖形态 + 风险画像」选模式(见下方模式速查)。
2. 用脚手架脚本生成 JSON 骨架配置。
3. 为「每一条边」定义交接契约字段(见交接最小契约)。
4. 补齐重试、超时与输出校验门。
5. 用小上下文预算先 dry-run,验证通过再扩容。

脚手架命令(脚本 `scripts/workflow_scaffolder.py`,参数 `pattern` 取值 `sequential|parallel|router|orchestrator|evaluator`):

```bash
# 生成顺序工作流骨架并打印到 stdout
python3 scripts/workflow_scaffolder.py sequential --name content-pipeline

# 生成编排器工作流并落盘保存
python3 scripts/workflow_scaffolder.py orchestrator --name incident-triage --output workflows/incident-triage.json
```

模式速查(按依赖形态选):

- `sequential` 顺序:严格的步步依赖链。例 research → draft → review。
- `parallel` 并行:独立子任务 fan-out 后 fan-in 汇总,提升吞吐、降低延迟。
- `router` 路由:按意图/类型分派到专职处理器,必须带 fallback 兜底。
- `orchestrator` 编排:planner 动态规划、按 DAG 依赖协调多个 specialist。
- `evaluator` 评估:generator + quality gate 回路,强制质量门后才定稿。

详细模板见 `references/workflow-patterns.md`。

## 示例

评估器(生成 + 质量门回路)骨架,脚本输出形如:

```json
{
  "name": "incident-triage",
  "pattern": "evaluator",
  "generator": {"agent": "generator"},
  "evaluator": {"agent": "evaluator", "criteria": ["accuracy", "format", "safety"]},
  "loop": {"max_iterations": 3, "pass_threshold": 0.8, "on_fail": "revise_and_retry"}
}
```

顺序模式自带重试策略:`"retry": {"max_attempts": 2, "backoff_seconds": 2}`;并行模式自带超时:`"timeouts": {"per_task_seconds": 180, "fan_in_seconds": 120}`;编排模式执行约束:`"execution": {"dependency_mode": "dag", "max_parallel": 3, "completion_policy": "all_required"}`。

交接最小契约(每条边都应携带这些字段):

- `workflow_id` 工作流标识
- `step_id` 步骤标识
- `task` 任务描述
- `constraints` 约束
- `upstream_artifacts` 上游产物(只传定向产物,不传完整上下文)
- `budget_tokens` token 预算
- `timeout_seconds` 超时秒数

## 注意事项

常见坑:

1. 过度编排——能用一条结构化提示解决的任务别拆成多智能体。
2. 对外部模型调用缺少 timeout/retry 策略。
3. 把完整上游上下文整包透传,而不是只传定向产物(导致上下文膨胀、成本飙升)。
4. 忽视逐步累积的成本。

最佳实践:

1. 从能满足需求的「最小模式」起步。
2. 交接 payload 保持显式且有界。
3. fan-in 汇总前先校验中间输出。
4. 每一步都强制预算与超时上限。

## 互见

- `references/workflow-patterns.md`:五种模式的完整 JSON 模板与选型启发式。
- 智能/agents 域下的智能体设计、提示工程、上下文管理相关条目。

Attribution

findscripterfindscripter
View sourceSee grades on GitHubMore from findscripter →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

698621 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →