BC agent-desktop
Reliable computer use via native OS accessibility trees. Use when an AI agent needs to see and operate desktop applications (click buttons, fill forms, navigate menus, read UI state, toggle checkboxes, scroll, drag, type text, take screenshots, manage windows, use clipboard, manage notifications). Covers 59 command names (55 operational; four held-input names fail closed until daemon ownership exists) across observation, interaction, keyboard/mouse, app lifecycle, notifications (macOS), clipboard, wait, session lifecycle, and a `skills` command that bundles docs straight from the binary. Triggers on: "click button", "fill form", "open app", "read UI", "computer use", "operate desktop", "accessibility tree", "snapshot app", "type into field", "navigate menu", "toggle checkbox", "take screenshot", "desktop automation", "agent-desktop", or any desktop GUI interaction task. Supports the macOS Phase 1 adapter, with Windows and Linux planned against the same core contracts.
Reliable computer use via native OS accessibility trees.
As a process C 50/100 · Has gaps — weak spots: result and completion, inputs and preconditions, running it twice
How to improve
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 0
✓ No critical or high findings
Files scanned: 7. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 6333 tokens (recommended < 5000); move details to references/ - note
frontmatter-keyunknown frontmatter key "requirements" - note
edit-residuethe text marks something as outdated (lines 65): check that old rules are not kept next to new ones — the full check reads the text for contradictions
Process rating: all ten parameters 50/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 4 mutating operations with no state check
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 70Execution cost. Instruction body is 6333 tokens
- 85Steps. 36 steps, 1 vague phrases
- 100Consistency. Name and required fields are in place
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 982: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 14 example trigger phrases
- +4Structure: 17 headings
- +3Step-by-step instructions: 36 items
- +4Has examples (10 code blocks)
- +4Reference files are cited in the instructions (5 of 5)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 79.