跳到正文
cccskills
免费在 GitHub 公开

workflow-diagram

Generates a Mermaid workflow diagram showing process steps, decisions, and state transitions. Use when documenting CI/CD pipelines or lifecycle processes.

中文简介正在准备中。当前显示原文说明。

实测评分 未实测

查看安装方法

包含的文件(1)

  • SKILL.md3.2 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

Workflow Diagram

Generate a Mermaid flowchart showing process workflows, pipelines, or state machines from code or documentation.

When To Use

  • Visualizing CI/CD or deployment pipelines
  • Documenting multi-step development workflows
  • Mapping state machines or lifecycle processes
  • Answering "what steps happen when X runs?"

When NOT To Use

  • Data moving between components (use cartograph:data-flow)
  • Component structure (use cartograph:architecture-diagram)

Workflow

Step 1: Explore the Codebase

Dispatch the codebase explorer agent:

Agent(cartograph:codebase-explorer)
Prompt: Explore [scope] and return a structural model.
Focus on process steps, conditional logic, state
transitions, and pipeline stages for a workflow diagram.
Look for: Makefiles, CI configs, hook chains, command
sequences, and lifecycle methods.

Step 2: Generate Mermaid Syntax

Transform the structural model into a Mermaid flowchart with decision nodes and process steps.

Rules for workflow diagrams:

  • Use flowchart TD for sequential processes
  • Use flowchart LR for pipelines with parallel tracks
  • Use shapes to distinguish step types:
    • [Rectangle] for process steps
    • {Diamond} for decision points
    • ([Stadium]) for start/end states
    • [[Subroutine]] for sub-processes
    • ((Circle)) for join/sync points
  • Use -->|label| for transition conditions
  • Group parallel tracks into subgraphs
  • Color-code by outcome:
    • Default for happy path
    • Dotted (-.->) for error/fallback paths
    • Thick (==>) for critical path
  • Limit to 20 nodes maximum

Example output:

flowchart TD
    start([Start: PR Created])
    lint[Run Linters]
    test[Run Tests]
    review{Code Review}
    approve[Approved]
    changes[Request Changes]
    merge([Merge to Main])

    start --> lint --> test
    test --> review
    review -->|pass| approve --> merge
    review -->|fail| changes -.-> lint

Step 3: Render via MCP

Call the Mermaid Chart MCP to render:

mcp__claude_ai_Mermaid_Chart__validate_and_render_mermaid_diagram
  prompt: "Workflow diagram of [scope/process]"
  mermaidCode: [generated syntax]
  diagramType: "flowchart"
  clientName: "claude-code"

If rendering fails, fix syntax and retry (max 2 retries).

Step 4: Present Results

Show the rendered diagram with a brief description of the workflow stages and decision points (2-3 sentences).

Exit Criteria

  • Mermaid flowchart syntax generated containing at least one diamond {Decision} node representing a conditional branch
  • mcp__claude_ai_Mermaid_Chart__validate_and_render_mermaid_diagram called and returns without error (or retry attempted and result reported)
  • Error/fallback paths rendered as dotted arrows (-.->) distinct from happy-path arrows when error paths exist in the source
  • Node count is at most 20; if more steps exist, sub-processes are collapsed into [[Subroutine]] nodes
  • A 2-3 sentence description of workflow stages and decision points is shown alongside the diagram

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

Shapes turns action-first: action leads, steps numbered, state restated. Use for ADHD-friendly output. Do not use to trim tokens; use response-compression.

中文简介正在准备中。当前显示原文说明。

athola/claude-night-market3432026年10月24日 更新

Inverts burden of proof for code additions. Use when reviewing PRs, planning refactors, or running unbloat to challenge every addition's necessity.

中文简介正在准备中。当前显示原文说明。

athola/claude-night-market3432026年10月24日 更新

Tracks per-agent token usage and flags waste in parallel dispatch. Use when evaluating parallel agent efficiency or after a multi-agent run.

中文简介正在准备中。当前显示原文说明。

athola/claude-night-market3432026年10月24日 更新

Coordinates Claude agent teams via filesystem protocol. Use when orchestrating parallel agents with task dependencies. Do not use for single-agent tasks.

中文简介正在准备中。当前显示原文说明。

athola/claude-night-market3432026年10月24日 更新

Evaluates API surface design, consistency, and exemplar alignment. Use when reviewing public API changes or before releasing a new API surface.

中文简介正在准备中。当前显示原文说明。

athola/claude-night-market3432026年10月24日 更新

Selects architecture paradigm via research before scaffolding. Use when architecture is undecided and the choice needs justification and documentation.

中文简介正在准备中。当前显示原文说明。

athola/claude-night-market3432026年10月24日 更新

查看 athola 的全部技能

报告此技能的问题