By swenyai
SWEny AI workflows for Claude Code — triage production alerts, implement fixes, run e2e tests, and create custom workflows
Verify SWEny provider credentials and connectivity. Run to diagnose configuration issues before running workflows.
Generate agent-driven browser E2E test workflows interactively. Creates test files in .sweny/e2e/.
Run SWEny E2E browser test workflows from .sweny/e2e/. Use when the user wants to execute end-to-end tests.
Pick up an issue and implement a fix with SWEny. Use when the user has an issue ID or URL they want resolved.
Set up SWEny in the current project. Interactive wizard that creates .sweny.yml config and .env template.
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.
Turn natural language into reliable AI workflows.
Describe what you want done. SWEny builds a DAG, wires up the right tools, and runs it. Every node, every tool call, every routing decision is tracked.
$ sweny workflow create "audit our GitHub repo for security issues, \
scan dependencies for vulnerabilities, and create Linear tickets \
for anything critical"
GitHub Security Audit
○ Scan Recent Commits for Exposed Secrets
│
├──► ○ Review Open PRs for Security Changes
└──► ○ Scan Dependencies for Vulnerabilities
│
○ Compile Security Posture Report
│
○ Create Linear Tickets for Critical Findings
Save to .sweny/workflows/github_security_audit.yml? [Y/n/refine]
One sentence in, a full workflow out — with structured output schemas, conditional routing, and the right skills at each node. Refine with natural language, run it, or publish to GitHub Actions.
npm install -g @sweny-ai/core
sweny workflow create "your task description here"
sweny workflow run .sweny/workflows/your-workflow.yml
Generate AI-driven end-to-end tests for any web app — no test scripts to write:
sweny e2e init # wizard asks about your flows → generates workflow YAML
sweny e2e run # AI agent drives a real browser to test your app
The wizard supports registration, login, purchase, onboarding, upgrade, cancellation, and custom flows. Each generates a self-contained workflow with auto-generated test credentials and optional cleanup.
| Approach | What it does |
|---|---|
| CLI | Build and run workflows from your terminal. Describe a task, get a DAG, run it. |
| E2E Testing | Generate and run AI-driven browser tests. No Playwright scripts — the agent figures out the DOM. |
| GitHub Action | Publish workflows to CI. Runs on cron schedules or dispatch. |
| Studio | Visual DAG editor and live execution monitor. Watch workflows run in real time. |
| Claude Code Plugin | /plugin install https://github.com/swenyai/sweny — slash commands, MCP tools, hooks, isolated agent. |
| MCP Server | Use SWEny from Claude Code or Claude Desktop. Claude delegates complex tasks to SWEny's DAG executor. |
| SWEny Cloud | Teams. Dashboard, shared credentials, scheduling, cross-repo analytics. |
Skills connect Claude to external services. Set the credential, the skill is ready.
| Skill | Category | What Claude can do |
|---|---|---|
| github | git | Search code, read files, create issues, open PRs |
| linear | tasks | Create, search, and update issues |
| sentry | observability | Query errors, issues, and stack traces |
| datadog | observability | Query logs, metrics, and monitors |
| betterstack | observability | Query incidents, monitors, and logs |
| slack | notification | Send messages via webhook or bot API |
| notification | notification | Discord, Teams, email, generic webhooks |
SWEny splits tasks into nodes in a DAG. Each node gets a focused instruction, scoped tools, and structured output — so instead of one giant prompt, you get a reliable pipeline.
npx claudepluginhub swenyai/sweny --plugin swenyEnd-to-end test automation with Playwright, Cypress, and Selenium for browser-based testing
End-to-end test execution and recording for web applications
Quality assurance - E2E testing, PR review, browser automation
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.
TestForge - Master of quality assurance through intelligent test generation. Analyzes code behavior to auto-generate comprehensive tests that catch real bugs, not just boost coverage numbers. Supports Jest, Pytest, Vitest, and more.