agentrigs
+ submit rig
~ / rigs / SandeepTakasi / qa-pilot

SandeepTakasi/qa-pilot

Evidence-first feature testing for Claude Code. Verdicts only from committed Playwright runs, with a trace and deploy SHA per case, a write guard for production, and ClickUp or local files as the record.

↗ GitHub ★ 0 NOASSERTION updated today project Claude Code Claude plugin
share on X
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
CONTEXT TAX · EVERY TURN
~1.1k tokens
Featherweight · median rig: 2.3k · breakdown
GUARDRAILS
0/5
No committed guardrails · details

Copy this rig

$ git clone --depth 1 https://github.com/SandeepTakasi/qa-pilot

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.

$ npx degit SandeepTakasi/qa-pilot/qa-pilot/skills/generate-tests .claude/skills/generate-tests
$ npx degit SandeepTakasi/qa-pilot/qa-pilot/skills/publish-results .claude/skills/publish-results
$ npx degit SandeepTakasi/qa-pilot/qa-pilot/skills/qa-init .claude/skills/qa-init
$ npx degit SandeepTakasi/qa-pilot/qa-pilot/skills/qa-review .claude/skills/qa-review
$ npx degit SandeepTakasi/qa-pilot/qa-pilot/skills/run-tests .claude/skills/run-tests
$ npx degit SandeepTakasi/qa-pilot/qa-pilot/skills/setup-profiles .claude/skills/setup-profiles

This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 7,204 rigs:

{
  "permissions": {
    "deny": [
      "Read(./.env)",
      "Read(**/.env)",
      "Read(~/.ssh/**)",
      "Bash(rm -rf *)",
      "Read(**/*.pem)",
      "Bash(rm -rf /)",
      "Bash(git push --force:*)",
      "Bash(sudo *)",
      "Read(.env)",
      "Bash(rm -rf /*)",
      "Read(./.env.*)",
      "Read(~/.aws/**)",
      "Bash(git push --force*)",
      "Bash(rm -rf:*)",
      "Read(**/*.key)",
      "Read(**/.env.*)",
      "Bash(sudo:*)",
      "Bash(git reset --hard*)",
      "Bash(git reset --hard:*)",
      "Read(.env.*)"
    ],
    "ask": [
      "Bash(git push:*)",
      "Bash(git push *)",
      "Bash(git commit:*)",
      "Bash(rm *)",
      "Bash(rm:*)",
      "Bash(git rebase *)",
      "Bash(wget *)",
      "Bash(npm publish:*)",
      "Bash(git commit *)",
      "Bash(gh pr merge *)"
    ]
  }
}

Skills (6)

generate-testspublish-resultsqa-initqa-reviewrun-testssetup-profiles

Similar rigs

mavka-ai/unit-tests-skills
AI agent skills for generating high-quality unit tests — Given-When-Then test cases, JUnit 5, Mockito, AssertJ. Works with Claude Code, Cursor, and any AGENTS.md-compatible agent.
★ 67 project Claude CodeCodex 2 skills 16d ago
Minimalist 2.1k tok ·
JSchOBL/agentic-ai-learning-journey
A hands-on lab for learning to write CLAUDE.md files and Claude Code setups — you write the context, the agent builds the code, a coach reviews your work.
★ 3 project Claude Code 3 skills 2mo ago
Minimalist 1.3k tok ·
saichandra1199/kickstart-with-claude-code
Smart Task Manager CLI demo showing all major Claude Code features: CLAUDE.md, Skills, Agents, Hooks, MCP, Settings, and Memory
★ 0 project Claude Code 1 mcp 3 skills 1 agents 7mo ago
Pragmatist 4.3k tok ·
trupo-zz/claude-code-setup-sample
Sample Claude Code config pack for a fictional app: CLAUDE.md, permissions, a guard hook with tests, 3 skills. AI-assisted. MIT.
★ 0 setup Claude Code 2 mcp 3 skills 1 hooks today
Fort Knox 19.0k tok ·
copied ✓