Workbench Ops Skill

What it does

When your agent uses it

• Delete widgets (desktop components / mini apps / dashboard cards) on the OpenLoaf workbench / desktop
• Tasks that involve Image generation
• Tasks that involve Focus and ADHD support

Example prompts

• “add a weather widget”
• “build a pomodoro component”
• “change the color of this widget”
• “/workbench-ops-skill”

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

1. 1WidgetInit — generate the scaffold directory
2. 2ToolSearch(names: "generate-dynamic-widget") — load the coding conventions
3. 3Write — write widget.tsx (the frontend component)
4. 4Write — write functions.ts (server-side functions, if needed)
5. 5WidgetCheck — compile + trigger live preview

What it can do on your machine

Read from SKILL.md and the folder at commit f7eccf6. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  No scripts in the folder and no shell commands in SKILL.md.

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Workbench Ops Skill loads about 1.3k tokens when it runs. Until then it costs about 123 tokens; SKILL.md has 501 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~123

When it runs · the whole SKILL.md, loaded when a task matches

~1.3k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

• NoteMentions a .env fileSKILL.md:91

  mation (API keys, etc.) is injected via `.env` under the widget directory — never hardcode

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from OpenLoaf/OpenLoaf at commit f7eccf6, republished under its AGPL-3.0 licence (© OpenLoaf). 501 words, ~1,279 tokens.

name

workbench-ops-skill

description

Triggered when the user wants to add, modify, view, or delete widgets (desktop components / mini apps / dashboard cards) on the OpenLoaf workbench / desktop. Typical phrasings: "add a weather widget", "build a pomodoro component", "change the color of this widget". **Not for**: one-off chart rendering inside a chat message (→visualization-ops-skill), AI image generation (→cloud-media-skill), casually mentioning "clock / countdown" in conversation (→answer directly).

User wants a Widget
├── Does one already exist?
│   ├── Yes → WidgetList → WidgetGet → Read → understand the current state
│   │        └── Needs code changes → ToolSearch(names: "generate-dynamic-widget")
│   │        └── Edit → WidgetCheck
│   └── No → Create a new Widget (see flow below)
└── Just querying / browsing?
    └── WidgetList / WidgetGet is enough

© OpenLoaf, AGPL-3.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in apps/server/src/ai/builtin-skills/workbench-ops/en of OpenLoaf/OpenLoaf.

Open the folder on GitHubat commit f7eccf6