eduramos21/qa-automation-framework
Skeleton for wiring AI agents into a real test automation stack, web and native mobile. Stack agnostic, driven by one config file and per-stack profiles.
stack: Python
ARCHETYPE
Skill Collector
Ten-plus skills loaded on demand. A procedural-knowledge library.
CONTEXT TAX · EVERY TURN
up to ~8.5k tokens
Claude Code loads MCP tools on demand, so the real cost is usually lower.
Heavy · median rig: 2.3k · breakdown
Copy this rig
# review before running: this installs third-party code $ claude mcp add playwright -- npx -y @playwright/mcp@latest $ npx degit eduramos21/qa-automation-framework/.claude ./rig-qa-automation-framework # inspect, then merge into .claude/
MCP servers are added to Claude Code at local scope; env vars are shown as YOUR_… placeholders — we never store values. Files are fetched with degit into a separate folder so you can review before merging.
$ claude mcp add playwright -- npx -y @playwright/mcp@latest $ npx degit eduramos21/qa-automation-framework/skills/audit .claude/skills/audit $ npx degit eduramos21/qa-automation-framework/skills/bug-report .claude/skills/bug-report $ npx degit eduramos21/qa-automation-framework/skills/design .claude/skills/design $ npx degit eduramos21/qa-automation-framework/skills/explore .claude/skills/explore $ npx degit eduramos21/qa-automation-framework/skills/fix .claude/skills/fix $ npx degit eduramos21/qa-automation-framework/skills/flake-triage .claude/skills/flake-triage $ npx degit eduramos21/qa-automation-framework/skills/generate .claude/skills/generate $ npx degit eduramos21/qa-automation-framework/skills/init .claude/skills/init $ npx degit eduramos21/qa-automation-framework/skills/prevalidate .claude/skills/prevalidate $ npx degit eduramos21/qa-automation-framework/skills/profile .claude/skills/profile $ npx degit eduramos21/qa-automation-framework/skills/qa-config .claude/skills/qa-config $ npx degit eduramos21/qa-automation-framework/skills/refine .claude/skills/refine $ npx degit eduramos21/qa-automation-framework/skills/test-design-techniques .claude/skills/test-design-techniques
This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 16.2k rigs:
{
"permissions": {
"deny": [
"Read(./.env)",
"Read(./.env.*)",
"Read(**/.env)",
"Read(~/.ssh/**)",
"Bash(git push --force:*)",
"Read(**/*.pem)",
"Read(.env)",
"Read(~/.aws/**)",
"Read(**/*.key)",
"Read(**/.env.*)",
"Bash(git push --force*)",
"Bash(rm -rf:*)",
"Bash(rm -rf *)",
"Bash(sudo *)",
"Bash(sudo:*)",
"Bash(rm -rf /)",
"Bash(git push -f:*)",
"Read(.env.*)",
"Bash(git reset --hard*)",
"Bash(rm -rf /*)"
],
"ask": [
"Bash(git push:*)",
"Bash(git push *)",
"Bash(gh pr merge *)",
"Bash(git commit:*)",
"Bash(rm *)",
"Bash(gh pr merge:*)",
"Bash(gh pr create *)",
"Bash(git reset --hard:*)",
"Bash(npm publish:*)",
"Bash(git rebase *)"
]
}
} MCP servers (1)
| server | source | est. tokens |
|---|---|---|
| Playwright MCP · "playwright" | npm | 7.5k |
Skills (13)
auditbug-reportdesignexplorefixflake-triagegenerateinitprevalidateprofileqa-configrefinetest-design-techniques
Plugins (2)
qa@eduramos21-qaponytail@ponytail
Similar rigs
iamvonpasion/hashb
Dev workflow toolkit for Claude Code — 14 skills that turn AI into a structured development partner. Spec → Design → Eng → TDD → Review → QA → Ship.
Skill Collector 2.5k tok · · Q0
fschifone/claude-setup-wizard
Interactive wizard that configures the complete Claude Code environment for any project
Fort Knox 2.7k tok · · Q25
rulebased-io/harness
Harness engineering tools for AI agents — audit, init, recommend your project's agent-readiness (AGENTS.md, context engineering, eval)
Minimalist 1.7k tok · · Q0
usmanmanii/realitygate
RealityGate: prove your AI-written code is real. Reality Score (0–100) for vibe-coded apps, a CI gate that blocks stubs, fake data, hallucinated npm packages & leaked secrets, a malware scanner for AI skills/plugins, and a spec-driven build
Pragmatist 745 tok · · Q8