/workspace-conventions
File and output conventions for agent workspaces
Claude Code
$ npx -y skills add chekusu/wanman --skill workspace-conventions --agent claude-code
Codex
$ npx skills add chekusu/wanman --skill workspace-conventions -a codex -y
Cursor
$ npx skills add chekusu/wanman --skill workspace-conventions -a cursor -y
Gemini CLI
$ npx skills add chekusu/wanman --skill workspace-conventions -a gemini-cli -y
GitHub Copilot
$ npx skills add chekusu/wanman --skill workspace-conventions -a github-copilot -y
OpenCode
$ npx skills add chekusu/wanman --skill workspace-conventions -a opencode -y
Windsurf
$ npx skills add chekusu/wanman --skill workspace-conventions -a windsurf -y
SKILL.md
workspace-conventions.SKILL.mdname: workspace-conventions
description: File and output conventions for agent workspaces
Workspace Conventions
Directory Structure
Each agent's working directory is `/workspace/agents/{agent-name}/`.
**Rule: Only write files within your own working directory.**
/workspace/agents/
├── ceo/ ← CEO's working directory
├── marketing/ ← Marketing agent
├── finance/ ← Finance agent
├── feedback/ ← Feedback/research agent
├── dev/ ← Dev agent
└── devops/ ← DevOps agent
Output File Naming
| Type | Naming | Example | |------|--------|---------| | Report | `{topic}-report.md` | `budget-report.md` | | Brand guide | `brand-guide.md` | | | Content plan | `{platform}-plan.md` | `social-media-plan.md` | | Web page | `index.html` | | | Design | `{name}-brief.md` | `poster-brief.md` |
Cross-Agent References
When a task description references another agent's output, use the full path:
See brand guide at /workspace/agents/marketing/brand-guide.md
Agent Name Identifier
When using `wanman artifact put`, the system automatically records the agent name. Ensure the environment variable `WANMAN_AGENT_NAME` is correctly set.
Task Completion Checklist
1. Write key data to artifacts (`wanman artifact put`) 2. Write detailed reports to MD files 3. Mark the task as done with `wanman task done`, noting the number of artifacts in the result
Read more
name: workspace-conventions description: File and output conventions for agent workspaces
Workspace Conventions
Directory Structure
Each agent's working directory is `/workspace/agents/{agent-name}/`.
**Rule: Only write files within your own working directory.**
/workspace/agents/ ├── ceo/ ← CEO's working directory ├── marketing/ ← Marketing agent ├── finance/ ← Finance agent ├── feedback/ ← Feedback/research agent ├── dev/ ← Dev agent └── devops/ ← DevOps agent
Output File Naming
| Type | Naming | Example | |------|--------|---------| | Report | `{topic}-report.md` | `budget-report.md` | | Brand guide | `brand-guide.md` | | | Content plan | `{platform}-plan.md` | `social-media-plan.md` | | Web page | `index.html` | | | Design | `{name}-brief.md` | `poster-brief.md` |
Cross-Agent References
When a task description references another agent's output, use the full path:
See brand guide at /workspace/agents/marketing/brand-guide.md
Agent Name Identifier
When using `wanman artifact put`, the system automatically records the agent name. Ensure the environment variable `WANMAN_AGENT_NAME` is correctly set.
Task Completion Checklist
1. Write key data to artifacts (`wanman artifact put`) 2. Write detailed reports to MD files 3. Mark the task as done with `wanman task done`, noting the number of artifacts in the result
Agent Matrix framework — run a supervised network of Claude Code or Codex agents that collaborate on your machine. wanman is an open-source local-mode agent matrix framework.
Other skills on wanman.
More skills from other plugins.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or…
ask-matt
Ask which skill or flow fits your situation. A router over the skills in this repo.
Questions about workspace-conventions.
- Which coding agents can use workspace-conventions?
- workspace-conventions installs in Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, OpenCode and Windsurf with the skills CLI, using each agent's flag shown on this page. Flowy's auto-invocation, which fires a skill when your prompt matches, runs in Claude Code only.

