SKILLEMALL.ai
GitHub ↗ RU Sign in

BB vscode-dev-workbench

Use when the user wants to run the vscode.dev server locally and exercise the VS Code workbench or Agents window in the integrated browser against the local `microsoft/vscode` sources. Covers starting the dev server, the `vscode-quality=dev` URL, browser-driven interaction patterns, and optionally wiring up a local mock agent host for the Agents window.

The skillemall take

This skill spins up a local vscode.dev server and lets your AI agent control VS Code in a browser—interact with the UI, open files, test features. The description promises the full stack: server startup, URL handling, even a mock agent host for the Agents window.

Grade B with 82% quality score is solid. One file, no critical issues, linting passes. The gap: no model runs, no sandbox testing. The description is wordy but thin on actual commands or dependencies. Your agent will get instructions, but without a worked example of real interface interaction.

Install if you're hacking on VS Code locally and don't mind filling in the gaps. Skip if you want turnkey.

microsoft/vscode Agent Skills author: microsoft MIT 1 file body ≈ 1 984 tokens Open the sourcegithub.com↗ analyzed 2 d ago

dev server locally and exercise the VS Code workbench or Agents window in the integrated browser against the local microsoft/vscode sources.

As a process B 67/100 · Nearly there — weak spots: result and completion, running it twice

IntegrationVS CodeAI and agentstype and topics are labelled automatically from the skill text
Runs in: Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) OpenClaw Goose OpenCode
JSON
Technical rating
B
93/100
safety, quality, tests
Safety 60%
100
Quality 40%
82
Run on models
none yet
Process rating
B
67/100
Nearly there
Result and completion w 14
0
Running it twice w 4
30
Tools and files w 18
60
the three weakest of ten parameters · all ten

How to improve

    For the model run — optional
    • 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: 1. Evidence is masked. Grey chips explain why severity was lowered.

    Against the Agent Skills spec

    ✓ No remarks against the Agent Skills spec

    Process rating: all ten parameters 67/100

    • 0Result and completion. Does not say what the result is
    • 30Running it twice. 8 mutating operations with no state check
    • 60Tools and files. Uses tools (bash, web, node) that frontmatter does not declare
    • 70When it triggers. States when to use, but not when not to
    • 70Inputs and preconditions. Inputs and preconditions are listed
    • 85Steps. 15 steps, 1 vague phrases
    • 100Failures and branches. 1 branches, has a failure section
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 1984 tokens
    • 100Progress reporting. Reports progress

    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

    • +5Description has no quoted example phrases that should trigger the skill
    • +4Description does not say when NOT to use the skill (false activations)
    • +3Output format is not stated: the model decides each time
    • -2localhost URLs: will not work for another user
    • +1No license
    • +2Single-language instructions
    • +3Description length 355: enough signal without eating the budget
    • +4Structure: 11 headings
    • +3Step-by-step instructions: 15 items
    • +4Has examples (7 code blocks)

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 82.