← Back to Skills Marketplace
ProcessOn Diagram Generator
by
ying zhang @po
· GitHub ↗
· v2.3.1
· MIT-0
256
Downloads
0
Stars
0
Active Installs
7
Versions
Install in OpenClaw
/install processon-diagram-generator
Description
A fast diagramming tool developed by ProcessOn that allows you to quickly create beautiful, editable visual diagrams such as flowcharts, swimlane diagrams, s...
Usage Guidance
Before installing: (1) Expect to provide a PROCESSON_API_KEY in the terminal where the agent runs — the skill requires this though the registry metadata omitted it. (2) The skill includes a Python client that will send prompts and (potentially) local content to https://smart.processon.com and will save image files to outputs/processon in the agent's working directory. If you plan to use it to analyze project architecture, it may access local source files (entry points, routes, configs) — avoid sending files containing secrets. (3) The package source/homepage in the registry is missing; verify the skill's origin (e.g., the README references a GitHub repo) before trusting your API key. (4) If you have sensitive data, run the skill in a sandboxed environment or inspect/modify scripts/processon_api_client.py to confirm exactly what is transmitted. (5) If you want this skill, ask the maintainer to update the registry metadata to declare PROCESSON_API_KEY and other env vars used, and to provide an authoritative source URL.
Capability Tags
Capability Assessment
Purpose & Capability
The skill's stated purpose (generate editable diagrams via ProcessOn) matches the included Python client that calls smart.processon.com endpoints. However the registry metadata declares no required environment variables while the SKILL.md and scripts clearly require a PROCESSON_API_KEY and respect other PROCESSON_* env vars. The skill also includes a script that performs network calls and saves files locally; those are reasonable for the stated purpose but the missing declaration in metadata is an incoherence.
Instruction Scope
Runtime instructions require running scripts/processon_api_client.py and mandate immediate display of generated DSL, editor link, and image URLs. The SKILL.md also instructs the agent to 'prioritize reading entry file, routes, core config and key modules' when generating architecture diagrams — that implies accessing the user's project files (which may contain secrets). The script will stream prompts and uploaded data to ProcessOn endpoints, and it writes image files to outputs/processon. These behaviors are within the diagramming scope but broaden the data-surface (local files and networked content) beyond what the registry metadata documents.
Install Mechanism
There is no install spec in the registry (instruction-only), which is low risk. The package includes a Python script and README with an npx install command referencing a GitHub repo; the registry 'Source' was marked unknown and 'Homepage' is none — this mismatch (no authoritative source URL) is worth noting and verifying. No external download or extract steps are defined in the skill bundle itself.
Credentials
The skill requires PROCESSON_API_KEY (used as Authorization/Bearer) and the script also reads PROCESSON_OUTPUT_MODE and PROCESSON_STREAM_STYLE — none of these env vars were declared in the registry metadata. Requesting a single API key is proportionate to the skill's function, but the omission from declared requirements is an inconsistency and increases risk because users may not expect to provide credentials.
Persistence & Privilege
The skill is not always-enabled and does not request elevated platform privileges. It writes generated images to a local outputs/processon directory and may save generated DSL/images; this is expected behavior. It does not appear to modify other skills or system-wide configurations.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install processon-diagram-generator - After installation, invoke the skill by name or use
/processon-diagram-generator - Provide required inputs per the skill's parameter spec and get structured output
Version History
v2.3.1
**Changelog for version 2.3.1:**
- Updated and expanded the skill description in SKILL.md to provide clearer bilingual (Chinese/English) explanations and usage scenarios.
- Clarified supported diagram types and improved summary of key features in the description.
- No functional changes to code or workflow; updates are documentation only.
v2.3.0
**This version enhances onboarding, configuration guidance, and adjusts output specifications for better user clarity.**
- Added clear first-time installation guidance, including proactive environment checks and explicit PROCESSON_API_KEY configuration instructions.
- Emphasized that all configuration steps must be performed in the current agent's terminal environment.
- Updated execution flow to require intermediate DSL and editing links before image rendering completes.
- Changed output rules: all links must be provided as plain URLs—no Markdown or rich text formatting.
- Strengthened requirements for result completeness and self-checks before responding, including mandatory DSL, editing links, and image links (if available) in all final replies.
- Refined failure handling and configuration prompts for incomplete setups.
v1.0.6
No functional or code changes in this version.
- SKILL.md description updated to clarify diagram types and trigger phrases in both Chinese and English.
- Enhanced description emphasizes wide support for various diagram formats (flowcharts, swimlanes, architecture, etc.).
- Audience orientation made clearer: developers, product managers, and designers.
- All core usage instructions, configuration details, and the structured output template remain unchanged.
v1.0.5
No changes detected in this version.
- Version 1.0.5 introduces no file or documentation changes compared to the previous release.
v1.0.3
No file changes were detected in this version.
- No code or documentation updates included in this release.
- Internal or metadata version update only; no impact on features or functionality.
v1.0.2
processon-diagramgen v1.0.1
- Added a README.md file with basic information and usage instructions.
- No changes to core functionality or behavior in this release.
v1.0.1
- Improved skill description and usage instructions for broader and clearer diagram generation scenarios.
- Added strict output formatting rules to ensure compatibility and visibility in third-party chat platforms.
- Clarified diagram types, trigger phrases (both Chinese and English), and user interaction guidelines.
- Specified fallback mechanisms and configuration steps for MCP and API modes.
- Included detailed output templates, emphasizing link placement and text structure for consistent user experience.
Metadata
Frequently Asked Questions
What is ProcessOn Diagram Generator?
A fast diagramming tool developed by ProcessOn that allows you to quickly create beautiful, editable visual diagrams such as flowcharts, swimlane diagrams, s... It is an AI Agent Skill for Claude Code / OpenClaw, with 256 downloads so far.
How do I install ProcessOn Diagram Generator?
Run "/install processon-diagram-generator" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is ProcessOn Diagram Generator free?
Yes, ProcessOn Diagram Generator is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does ProcessOn Diagram Generator support?
ProcessOn Diagram Generator is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created ProcessOn Diagram Generator?
It is built and maintained by ying zhang @po (@leilizhang); the current version is v2.3.1.
More Skills