plugins/exploration-cycle-plugin/skills/business-workflow-doc/SKILL.md
Generate Mermaid flowcharts documenting business processes, state machines, and workflow logic from session captures. Use when you need to map multi-step processes, approval flows, user journeys, or decision trees during exploration. Trigger with "map this workflow", "create a process diagram", "flowchart the business process", "document this workflow", or "visualize the state machine".
npx skillsauth add richfrem/agent-plugins-skills business-workflow-docInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Generate visual Mermaid flowcharts from exploration session captures and session briefs.
python ./scripts/generate_workflow.py \
--input <capture_file_or_glob> \
--output <output_file.md> \
--type <flowchart|stateDiagram|sequenceDiagram>
Flags:
--input PATH : Input file(s) — session brief, BRD draft, or problem framing capture--output PATH : Output markdown file (default: exploration/captures/workflow-map.md)--type TYPE : Diagram type: flowchart (default), stateDiagram, or sequenceDiagram--title TEXT : Optional diagram titlepython scripts/dispatch.py \
--agent .agents/skills/exploration-cycle-plugin-requirements-doc-agent/SKILL.md \
--context exploration/session-brief.md exploration/captures/brd-draft.md \
--instruction "Mode: workflow-map. Generate a Mermaid flowchart diagram of the core business process described in this context. Use a flowchart TD layout. Label each step clearly. Include decision nodes for branches and validation gates." \
--output exploration/captures/workflow-map.md
The skill always outputs a Markdown file with one or more fenced Mermaid code blocks:
# Business Workflow: [Process Name]
Source: [input file(s)]
Date: [today]
## Core Process Flow
```mermaid
flowchart TD
A[Start: Trigger Event] --> B{Validation Gate}
B -->|Pass| C[Step 1: Process Action]
B -->|Fail| D[Error: Notify User]
C --> E[Step 2: Business Rule Applied]
E --> F{Approval Required?}
F -->|Yes| G[Approval Workflow]
F -->|No| H[Auto-Proceed]
G --> I[End: Complete]
H --> I
```
## Open Questions
- [NEEDS HUMAN INPUT] (step ordering unclear from captures)
| Type | Use When |
|------|----------|
| flowchart | Sequential multi-step processes with decision branches |
| stateDiagram | Object lifecycle states (e.g., order status transitions) |
| sequenceDiagram | Service-to-service or user-to-system interaction flows |
[NEEDS HUMAN INPUT].DRAFT until confirmed by the human explorer.data-ai
Task management agent. Auto-invoked for task creation, status tracking, and kanban board operations using Markdown files across lane directories. V2 enforces Kanban Sovereignty constraints preventing manual task file edits.
development
Create, audit, repair, and document cross-platform symlinks that work correctly on both Windows and macOS/Linux. Use this skill whenever the user mentions symlinks, symbolic links, junction points, .gitconfig symlinks, broken links after git pull, cross-platform path issues, or needs help with ln -s equivalents on Windows. Also trigger when the user reports that files are missing or wrong after switching between Mac and Windows machines using Git. This skill solves the common problem where symlinks committed on macOS show up as plain text files on Windows (and vice versa) because of Git's core.symlinks setting or missing Developer Mode / elevated permissions. **IMPORTANT FOR WINDOWS USERS:** Developer Mode must be enabled before creating symlinks. Without it, Git will check out symlinks as plain-text files or hardlinks, breaking cross-platform workflows.
development
Interactively prepares a targeted Red Team Review package. It conducts a brief discovery interview to determine the threat model, generates a strict security auditor prompt, compiles a manifest of relevant project files, and bundles them into a single Markdown artifact or ZIP archive ready for an external LLM (like Grok, ChatGPT, or Gemini) or a human reviewer.
tools
Reduces AI agent context bloat across three dimensions: (1) duplicate skill deduplication — clears stale agent directory copies since the IDE already reads from plugins/ directly; (2) instruction file optimization — rewrites CLAUDE.md, GEMINI.md, or .github/copilot-instructions.md to under ~80 lines, keeping only rules that directly change agent behaviour; (3) session token efficiency — guidance on cheap subagent delegation, context compounding across turns, and session hygiene. Trigger with "optimize context", "reduce context bloat", "deduplicate skills", "trim CLAUDE.md", "trim GEMINI.md", "fix my context usage", "why are my skills loading twice", "how do I reduce token usage", or "clean up agent directories".