Install
$ agentstack add skill-trecek-useful-claude-skills-arch-lens-process-flow ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Process Flow Architecture Lens
Cognitive Mode: Physiological Primary Question: "How does it behave?" Focus: Runtime Behavior, State Transitions, Decision Points, Control Flow
When to Use
- Need to understand runtime execution paths
- Documenting state machines or workflows
- Analyzing decision points and branching logic
- User invokes
/arch-lens-process-flowor/make-arch-diag process
Critical Constraints
NEVER:
- Modify any source code files
- Include static structure details (that's C4 lens)
- Show data storage details (that's data lineage lens)
ALWAYS:
- Focus on BEHAVIOR and STATE TRANSITIONS
- Show decision points as diamonds
- Include loop mechanisms and retry logic
- BEFORE creating any diagram, LOAD the
/mermaidskill using the Skill tool - this is MANDATORY
Analysis Workflow
Step 1: Launch Parallel Exploration Subagents
Spawn Explore subagents to investigate:
State Machines & Workflows
- Find state definitions and transitions
- Identify workflow orchestration
- Look for: state machine patterns, workflow graphs, FSM implementations, state enum/constants
Entry Points & Triggers
- Find how processes are started
- Identify triggers and events
- Look for: main(), run(), execute(), start(), __call__, async handlers
Decision Points
- Find conditional logic that affects flow
- Identify routing functions
- Look for: if/else chains, switch/case, route, should, can, is
Loop Mechanisms
- Find iteration and retry patterns
- Identify continuation conditions
- Look for: while, for, retry logic, max_iterations, loop constructs
Terminal States
- Find completion conditions
- Identify error termination
- Look for: return, raise/throw, complete, error, success, failure states
Step 2: Map State Transitions
For each workflow/state machine discovered:
- States/Nodes: List all distinct states
- Transitions: Map state-to-state connections
- Guards: Conditions that determine transitions
- Actions: What happens during transitions
Step 3: Identify Flow Patterns
Document key patterns:
- Linear sequences (A -> B -> C)
- Branches (decision points)
- Loops (with termination conditions)
- Error paths
- Parallel paths (if any)
CRITICAL - Analyze Read/Write Direction: For EVERY node that interacts with state or storage:
- Reads from: What data does this node consume? From where?
- Writes to: What data does this node produce? To where?
- State mutations: Does it modify in-memory state, database, or files?
Label state interactions on edges:
- "reads" / "loads" / "queries" for input
- "writes" / "saves" / "updates" for output
- Distinguish primary storage (read/write) from write-only artifacts
Step 4: Create the Diagram
Use flowchart with:
Direction: TB for hierarchical flow, LR for sequential processes
Node Types:
([Label])- Rounded: Start/End terminals{Label}- Diamond: Decision points[Label]- Rectangle: Process nodes[[Label]]- Subroutine: Subgraph calls
Subgraphs for Phases:
- Group related states into phases
- Keep START/END outside subgraphs
Node Styling:
terminalclass: START, END, ERROR nodesphaseclass: Control flow, analysis nodeshandlerclass: Processing, execution nodesstateNodeclass: Decision, routing nodesdetectorclass: Validation gates, failure handling
Edge Labels:
- Show conditions on decision branches
- Include loop counts where relevant
Step 5: Write Output
Write the diagram to: temp/arch-lens-process-flow/arch_diag_process_flow_{YYYY-MM-DD_HHMMSS}.md
Output Template
# Process Flow Diagram: {Workflow Name}
**Lens:** Process Flow (Physiological)
**Question:** How does it behave?
**Date:** {YYYY-MM-DD}
**Scope:** {What was analyzed}
## Workflow Overview
| Phase | Nodes | Key Decision Points | Loop Mechanism |
|-------|-------|---------------------|----------------|
| {phase} | {count} | {decisions} | {loop info} |
## Flow Diagram
```mermaid
%%{init: {'flowchart': {'nodeSpacing': 40, 'rankSpacing': 50, 'curve': 'basis'}}}%%
flowchart TB
%% CLASS DEFINITIONS %%
classDef terminal fill:#1a237e,stroke:#7986cb,stroke-width:2px,color:#fff;
classDef stateNode fill:#004d40,stroke:#4db6ac,stroke-width:2px,color:#fff;
classDef handler fill:#e65100,stroke:#ffb74d,stroke-width:2px,color:#fff;
classDef phase fill:#6a1b9a,stroke:#ba68c8,stroke-width:2px,color:#fff;
classDef detector fill:#b71c1c,stroke:#ef5350,stroke-width:2px,color:#fff;
%% TERMINALS %%
START([START])
COMPLETE([COMPLETE])
ERROR([ERROR])
subgraph Phase1 ["Phase Name"]
direction TB
N1["Node Name━━━━━━━━━━Description"]
N2{"Decision━━━━━━━━━━Condition?"}
N3["Process Node━━━━━━━━━━Action"]
end
%% FLOW %%
START --> N1
N1 --> N2
N2 -->|"condition A"| N3
N2 -->|"condition B"| ERROR
N3 --> COMPLETE
%% CLASS ASSIGNMENTS %%
class START,COMPLETE,ERROR terminal;
class N1,N3 handler;
class N2 stateNode;
Color Legend: | Color | Category | Description | |-------|----------|-------------| | Dark Blue | Terminal | Start, complete, and error states | | Purple | Phase | Control flow and analysis nodes | | Orange | Handler | Processing and execution nodes | | Teal | State | Selection and routing decisions | | Red | Detector | Validation gates and failure handling |
State Machine Characteristics
| Aspect | Value | Notes | |--------|-------|-------| | Total Nodes | {count} | | | Decision Points | {count} | | | Loop Mechanism | {description} | {max iterations} | | Error Paths | {count} | |
Critical Routing Logic
- Condition A: {what triggers this path}
- Condition B: {what triggers this path}
---
## Pre-Diagram Checklist
Before creating the diagram, verify:
- [ ] LOADED `/mermaid` skill using the Skill tool
- [ ] Using ONLY classDef styles from the mermaid skill (no invented colors)
- [ ] Diagram will include a color legend table
---
## Related Skills
- `/make-arch-diag` - Parent skill for lens selection
- `/mermaid` - MUST BE LOADED before creating diagram
- `/arch-lens-concurrency` - For parallel execution details
- `/arch-lens-error-resilience` - For failure handling specifics
## Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- **Author:** [Trecek](https://github.com/Trecek)
- **Source:** [Trecek/useful-claude-skills](https://github.com/Trecek/useful-claude-skills)
- **License:** MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.