By manykarim
Generate, analyze, and debug Robot Framework tests with AI assistance for web (Selenium, Playwright), API (Requests, RESTinstance), and mobile (Appium) automation. Provides keyword explanations, test architecture design, migration support, and result analysis from output.xml.
Diagnose and resolve Robot Framework test failures, flaky tests, environment issues, and execution errors. Invoke when the user needs to analyze output.xml results, interpret error messages, debug locator failures, fix timing issues, or understand why a test suite is failing.
Find, explain, and recommend Robot Framework keywords across all installed libraries and resource files. Invoke when the user asks which keyword to use for a task, needs keyword argument details, wants to compare keywords across libraries, or is looking for the right keyword for a specific automation action.
Assist with Robot Framework migration tasks including upgrading RF versions, migrating between test libraries (SeleniumLibrary to Browser Library, RequestsLibrary to RESTinstance), converting test syntax, and modernizing legacy test suites. Invoke when the user needs to upgrade, migrate, or modernize existing Robot Framework tests.
Plan and design Robot Framework test suites, resource structures, and keyword hierarchies. Invoke when the user needs to architect a complete test automation project, decide between testing libraries (Browser vs Selenium, Requests vs RESTinstance), design page object patterns, or structure test data and variables across environments.
Guide AI agents in creating AppiumLibrary tests for iOS and Android native apps, hybrid apps, and mobile browsers. Load when asked about mobile testing, Appium, or mobile app automation.
Guide AI agents in creating Browser Library tests using Playwright-powered automation with auto-waiting, assertion engine, and modern web features. Use when asked to create web tests with Browser Library, handle locators, assertions, iframes, Shadow DOM, or multi-tab scenarios.
Generate Robot Framework user keywords from structured intent. Use when asked to create keywords, add arguments, documentation, tags, setup/teardown, or to apply embedded-argument style based on existing project conventions.
Explain Robot Framework keywords and their arguments from library/resource/suite documentation. Use when asked how to use a keyword, what arguments it takes, or to retrieve detailed keyword docs from libdoc across one or more libraries/resources.
Search Robot Framework library/resource/suite documentation to find matching keywords for a use case. Use when asked to find keywords, search libdoc, match a use case to keywords, or scan multiple libraries/resources for relevant keywords.
Modifies files
Hook triggers on file write and edit operations
Uses power tools
Uses Bash, Write, or Edit tools
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
A Claude Code plugin marketplace providing AI agent skills for Robot Framework test automation. Includes skills for web testing (Browser/Selenium), API testing (Requests/RESTinstance), mobile testing (Appium), asset generation, and RF analysis tools.
# Install as Claude Code Plugin
claude plugin add github:manykarim/robotframework-agentskills
# Or install skills directly to your project
cp -r skills/robotframework-browser-skill .claude/skills/
# Install from VSIX
code --install-extension vscode-extension/robotframework-agentskills-1.0.0.vsix
# Load the plugin directory directly
claude --plugin-dir ./plugins/rf-agentskills
Or copy individual skills from skills/ to your project's .claude/skills/ for standalone usage without the plugin system.
| Skill | Type | Command | Description |
|---|---|---|---|
| Browser Library | library-reference | /rf-agentskills:browser | Web testing with Playwright (auto-waiting, assertions, Shadow DOM) |
| SeleniumLibrary | library-reference | /rf-agentskills:selenium | Web testing with Selenium WebDriver |
| AppiumLibrary | library-reference | /rf-agentskills:appium | Mobile testing for iOS and Android |
| RequestsLibrary | library-reference | /rf-agentskills:requests | REST API testing with HTTP methods |
| RESTinstance | library-reference | /rf-agentskills:restinstance | REST API testing with JSON Schema validation |
| Keyword Builder | script-based | /rf-agentskills:keyword-builder | Generate RF user keywords from structured input |
| Test Case Builder | script-based | /rf-agentskills:testcase-builder | Generate RF test cases from structured input |
| Resource Architect | script-based | /rf-agentskills:resource-architect | Design resource/variable file layouts |
| Libdoc Search | script-based | /rf-agentskills:libdoc-search | Search library keywords by use case |
| Libdoc Explain | script-based | /rf-agentskills:libdoc-explain | Explain keyword arguments and documentation |
| Results | script-based | /rf-agentskills:results | Parse output.xml into JSON summaries (requires robotframework) |
The 5 library-reference skills provide documentation and usage guidance. The 6 script-based skills execute Python scripts to generate code or analyze artifacts. Library-reference skills cross-reference their companion script-based skills (e.g., the Browser skill suggests using Keyword Builder and Libdoc Search).
| Agent | Purpose |
|---|---|
| RF Test Architect | Plan test suites, select libraries, design project structure |
| RF Debug Expert | Diagnose test failures, analyze output.xml, fix flaky tests |
| RF Keyword Consultant | Find, explain, and compare keywords across libraries |
| RF Migration Guide | Upgrade RF versions, migrate between libraries |
.robot files after every write/editpip install robotframework
All scripts handle a missing robotframework package gracefully -- script-based skills that do not require it (keyword-builder, testcase-builder, resource-architect) work with the Python standard library alone.
Optional libraries (for their respective skills):
pip install robotframework-browser # Browser skill
pip install robotframework-seleniumlibrary # Selenium skill
pip install robotframework-appiumlibrary # Appium skill
pip install robotframework-requests # Requests skill
pip install RESTinstance # RESTinstance skill
Add to your project's .claude/settings.json to auto-configure for your team:
{
"extraKnownMarketplaces": {
"robotframework-agentskills": {
"source": {
"source": "github",
"repo": "manykarim/robotframework-agentskills",
"ref": "stable"
}
}
},
"enabledPlugins": {
"rf-agentskills@robotframework-agentskills": true
}
}
Agent Skills are modular, self-contained packages that include a SKILL.md file (instructions) plus optional scripts, references, and assets. AI agents load a skill when its name or description matches the user request. Skills use progressive disclosure: only metadata is loaded initially; the full skill body and references are loaded on demand.
npx claudepluginhub manykarim/robotframework-agentskills --plugin rf-agentskillsTool-agnostic QA Automation library: Playwright, Selenium, API testing, accessibility (WCAG 2.1 AA), QA Planner, and ISTQB-aligned artifacts. Includes 13 specialized agents and 10 reusable skills.
End-to-end test automation with Playwright, Cypress, and Selenium for browser-based testing
QA skills for automation domain.
AI test generation with Ralph-loop quality gate: coder → reviewer → iterate
Production-grade Playwright testing toolkit. Generate tests from specs, fix flaky failures, migrate from Cypress/Selenium, sync with TestRail, run on BrowserStack. 55+ ready-to-use templates, 3 specialized agents, smart reporting that plugs into your existing workflow.
Testing workflow skill for high-value test discovery, strategy selection, focused implementation, realistic workload generation, strict review, and suite health diagnostics.