Official agent skill

UI Action

by microsoft in microsoft/copilot-for-eclipse

Authors and validates SWTBot JSON probe scripts for GitHub Copilot for Eclipse UI flows against a real Eclipse workbench.

OfficialMITAuto-check passedTesting & QA

Install UI Action

skills CLI
$ npx skills add microsoft/copilot-for-eclipse --skill ui-action -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install microsoft/copilot-for-eclipse ui-action --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/microsoft/copilot-for-eclipse.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.github/skills/ui-action .claude/skills/ui-action && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
ui-action
GitHub stars
125
Token cost
~1.1k tokens
SKILL.md length
323 words
Files
2
Skills in repo
2
Repo updated
First seen
Licence
MIT

At a glance

Authors and validates SWTBot JSON probe scripts for GitHub Copilot for Eclipse UI flows against a real Eclipse workbench.

  • Works in 5 steps: Create one focused JSON script at → Start by settling the workbench and… → Add user-level steps only, such as… → …
  • Updating probe-scripts
  • SKILL.md covers Quick start, Authoring workflow, Chat send skeleton and Pass/fail judgment, plus 1 more section
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

UI Action is an agent skill from microsoft/copilot-for-eclipse, published by the product's own GitHub organization. Authors and validates SWTBot JSON probe scripts for GitHub Copilot for Eclipse UI flows against a real Eclipse workbench. Use when creating or updating probe-scripts, converting test plans to UI probes, validating end-to-end Eclipse UI behavior, or troubleshooting ProbeRunner failures.

Its SKILL.md is about 1.1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 1 other file (for example `REFERENCE.md`).

It sits in Testing & QA, covering Test generation. The repository describes itself as: GitHub Copilot plugin for Eclipse IDE. The licence is MIT.

When your agent uses it

  • Updating probe-scripts
  • Converting test plans to UI probes
  • Validating end-to-end Eclipse UI behavior
  • Troubleshooting ProbeRunner failures

Example prompts

  • “Use the ui-action skill to author and validates SWTBot JSON probe scripts for GitHub Copilot for Eclipse UI flows against a real Eclipse workbench”
  • “/ui-action”

Workflow steps

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

  1. Create one focused JSON script at
  2. Start by settling the workbench and opening the view under test
  3. Add user-level steps only, such as click, typeIn, clearElement, pressKey,
  4. Run from the repository root
  5. Read com.microsoft.copilot.eclipse.swtbot.test/target/probe-results/results.json,

What it can do on your machine

Read from SKILL.md and the folder at commit 00733c2. 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 (its code samples are json and bash).

    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

UI Action loads about 1.1k tokens when it runs. Until then it costs about 74 tokens; SKILL.md has 323 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~74
When it runs · the whole SKILL.md, loaded when a task matches
~1.1k

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

Auto-check passed

The automated check found no risky patterns in SKILL.md.

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 microsoft/copilot-for-eclipse at commit 00733c2, republished under its MIT licence (© microsoft). 323 words, ~1,066 tokens.

Download SKILL.mdSave it as .claude/skills/ui-action/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
ui-action
description
Authors and validates SWTBot JSON probe scripts for GitHub Copilot for Eclipse UI flows against a real Eclipse workbench. Use when creating or updating probe-scripts, converting test plans to UI probes, validating end-to-end Eclipse UI behavior, or troubleshooting ProbeRunner failures.

SWTBot Probe Scripts

Use this skill to create or update JSON probes for com.microsoft.copilot.eclipse.swtbot.test. Probes drive the workbench through SWTBot actions and run as Tycho tests; no Java is compiled per test case.

Quick start

  1. Create one focused JSON script at com.microsoft.copilot.eclipse.swtbot.test/probe-scripts/<plan-slug>-<tc-id>.json.

  2. Start by settling the workbench and opening the view under test:

    json
    [
      { "action": "waitForIdle" },
      { "action": "screenshot", "id": "01-startup" },
      { "action": "showView", "idRef": "com.microsoft.copilot.eclipse.ui.chat.ChatView" },
      { "action": "waitForIdle" },
      { "action": "screenshot", "id": "02-chat-open" }
    ]
  3. Add user-level steps only, such as click, typeIn, clearElement, pressKey, invokeCommand, waitFor, waitForMethod, assertExists, screenshot, or dumpUi. Prefer widgetId locators for widgets the plugin owns.

  4. Run from the repository root:

    bash
    ./mvnw clean verify -Dprobe.script=probe-scripts/<name>.json

    Use root clean verify as the default. Tycho can reuse stale bundle jars when only the SWTBot module is run, making source edits appear ignored. Use xvfb-run -a on Linux headless.

  5. Read com.microsoft.copilot.eclipse.swtbot.test/target/probe-results/results.json, workspace.log, screenshots/, and ui-dumps/.

If -Dprobe.script is unset, ProbeRunner skips itself so ordinary ./mvnw verify runs are unaffected.

Authoring workflow

  • Convert one scenario/test case into one probe. Split unrelated behaviors so each failure screenshot has one meaning.
  • Drive the UI the way a user does. invokeCommand is allowed for registered Eclipse command IDs; do not call OSGi services, private methods, or test-only shortcuts.
  • Pair screenshots with machine-checked assertions. Screenshots never fail a step; assertExists, waitFor, and waitForMethod decide pass/fail.
  • Wait for asynchronous UI state before acting. For chat, wait for the model-picker selected model before Send, then wait for user-turn and model-info-label.
  • When a locator fails, insert dumpUi before the failure and inspect ui-dumps/*.xml for widget class names and SWTBot widget IDs.
  • For unauthenticated chat probes, assert the "Sign in to GitHub" UI. Do not poll internal auth managers.

Chat send skeleton

json
[
  { "action": "waitForIdle" },
  { "action": "showView", "idRef": "com.microsoft.copilot.eclipse.ui.chat.ChatView" },
  { "action": "waitFor", "locator": { "by": "styledText" }, "timeoutSec": 30 },
  { "action": "clearElement", "locator": { "by": "styledText" } },
  { "action": "typeIn", "locator": { "by": "styledText" }, "text": "hello" },
  { "action": "waitForMethod", "locator": { "by": "widgetId", "value": "model-picker" },
    "method": "getSelectedItemId", "timeoutSec": 60 },
  { "action": "click", "locator": { "by": "buttonWithTooltip", "tooltip": "Send" } },
  { "action": "waitFor", "locator": { "by": "widgetId", "value": "user-turn" }, "timeoutSec": 30 },
  { "action": "waitFor", "locator": { "by": "cssClass", "value": "model-info-label" }, "timeoutSec": 120 },
  { "action": "assertExists", "locator": { "by": "widgetId", "value": "copilot-turn" } },
  { "action": "screenshot", "id": "agent-response" }
]

Pass/fail judgment

A probe passes only when Maven exits 0 and results.json has "failed": 0. On failure, inspect the failed step message, FAILED-stepNN-*.png, nearest ui-dumps/*.xml, and workspace.log.

Extending probes

The vocabulary lives in com.microsoft.copilot.eclipse.swtbot.test/src/.../probe/. Add UI-level primitives in ProbeStep, Locator, and StepExecutor, then update REFERENCE.md.

See REFERENCE.md for action/locator tables, platform notes, result queries, troubleshooting, and current stable widget IDs.

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

Files

SKILL.md and 1 other file in .github/skills/ui-action of microsoft/copilot-for-eclipse.

  • SKILL.md
  • REFERENCE.md

Open the folder on GitHubat commit 00733c2

Compare with similar skills

UI Action next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

UI Action compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
UI Action this skillmicrosoft/copilot-for-eclipse125—~1.1kAutomated safety check: PassMIT
Emcaklofas/kicad-happy1.3k1 repos~2.8kAutomated safety check: PassMIT
Swig Testswig/swig6.3k—~2.3kAutomated safety check: PassCustom licence
Generate Test Cases342164796/generate-test-cases1191 repos~2.9kAutomated safety check: PassNone
Verify Cc Safety Netkenryu42/cc-safety-net1.6k—~2kAutomated safety check: PassMIT
Wioworkersio/skills180—~5.8kAutomated safety check: PassMIT

Similar skills

  • Emc

    aklofas/kicad-happy

    EMC pre-compliance risk analysis for KiCad PCB designs — 18 check categories, 44 rule IDs covering ground planes, decoupling, I/O filtering, switching harmonics, clock routing, differential pair…

    1.3k GitHub starsUsed in 1 repo~2.8k tokens
    Testing & QAAuto-check passed
  • Swig Test

    swig/swig

    Run SWIG test suite for specific languages. An agent skill from swig/swig.

    6.3k GitHub stars~2.3k tokensUpdated yesterday
    Testing & QAAuto-check passed
  • Generate Test Cases

    342164796/generate-test-cases

    自主学习型测试文档生成器。从需求文档(Markdown)生成测试用例 XMind 文件,支持持久化记忆和持续学习。当用户提到"生成测试用例"、"根据需求生成测试"时触发。

    119 GitHub starsUsed in 1 repo~2.9k tokens
    Testing & QAAuto-check passed
  • Verify Cc Safety Net

    kenryu42/cc-safety-net

    Launch and drive the real cc-safety-net CLI — the hook decision path, explain, status/doctor, logs, and the local policy GUI — against an isolated home, capturing evidence.

    1.6k GitHub stars~2k tokensUpdated yesterday
    Testing & QAAuto-check passed
  • Wio

    workersio/skills

    Testing workflow skill for finding high-value test candidates, writing focused tests, generating realistic workloads, reviewing test value, and diagnosing test-suite health.

    180 GitHub stars~5.8k tokensUpdated 2 mo ago
    Testing & QAAuto-check passed
  • File Server

    microsoft/WindowsProtocolTestSuites

    Official

    ALWAYS LOAD THIS SKILL when working with FileServer, SMB, SMB2, SMB3, CIFS, file sharing, MS-SMB2, MS-FSCC, MS-FSA, MS-DFSC, MS-FSRVP, MS-RSVD, MS-SQOS, or any file server protocol test…

    567 GitHub stars~4.1k tokensUpdated 22 days ago
    Testing & QAAuto-check passed

More from microsoft/copilot-for-eclipse

  • Endgame

    microsoft/copilot-for-eclipse

    Official

    Orchestrate endgame verification for a GitHub milestone issue.

    125 GitHub stars~1.4k tokensUpdated 7 days ago
    Auto-check passed

Categories

Questions about UI Action

What does UI Action do?

Authors and validates SWTBot JSON probe scripts for GitHub Copilot for Eclipse UI flows against a real Eclipse workbench. UI Action is an agent skill from microsoft/copilot-for-eclipse, published by the product's own GitHub organization. Authors and validates SWTBot JSON probe scripts for GitHub Copilot for Eclipse UI flows against a real Eclipse workbench.

When should I use UI Action?

UI Action fits situations like: updating probe-scripts; converting test plans to UI probes; validating end-to-end Eclipse UI behavior; troubleshooting ProbeRunner failures.

How do I install UI Action in Claude Code?

Run `npx skills add microsoft/copilot-for-eclipse --skill ui-action -a claude-code`. Or copy the skill folder (.github/skills/ui-action in microsoft/copilot-for-eclipse) into .claude/skills/ui-action in your project. Claude Code loads it when a task matches its description.

How do I install UI Action in Codex?

Run `npx skills add microsoft/copilot-for-eclipse --skill ui-action -a codex`. Or copy the skill folder (.github/skills/ui-action in microsoft/copilot-for-eclipse) into .agents/skills/ui-action in your project. Codex loads it when a task matches its description.

Can I use UI Action in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add microsoft/copilot-for-eclipse --skill ui-action -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/ui-action, .gemini/skills/ui-action, .github/skills/ui-action and .opencode/skills/ui-action in your project.

What does UI Action need to run?

SKILL.md names no scripts, command-line tools or credentials: UI Action is instructions for the agent only.

Does UI Action access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is UI Action safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does UI Action use?

UI Action is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does UI Action use?

About 1.1k tokens (SKILL.md is roughly 4.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to UI Action?

Skills that share tags, products or a category with UI Action: Emc (aklofas/kicad-happy, 1.3k stars), Swig Test (swig/swig, 6.3k stars), Generate Test Cases (342164796/generate-test-cases, 119 stars) and Verify Cc Safety Net (kenryu42/cc-safety-net, 1.6k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains UI Action?

microsoft (a GitHub organization, an official publisher) maintains it in microsoft/copilot-for-eclipse, which has 125 GitHub stars. The repository holds 2 skills in this directory. The repository was last updated on September 30, 2026.

Source: microsoft/copilot-for-eclipse on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.