skill-tester-swarm

Automated QA system for Claude Code skills. Discovers skills from GitHub/SkillsMP, installs them, generates tests, executes with screenshot capture, evaluates quality with A-F grades, and publishes an interactive dashboard.

16 stars

Best use case

skill-tester-swarm is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Automated QA system for Claude Code skills. Discovers skills from GitHub/SkillsMP, installs them, generates tests, executes with screenshot capture, evaluates quality with A-F grades, and publishes an interactive dashboard.

Teams using skill-tester-swarm should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/skill-tester-swarm/SKILL.md --create-dirs "https://raw.githubusercontent.com/diegosouzapw/awesome-omni-skill/main/skills/testing-security/skill-tester-swarm/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/skill-tester-swarm/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How skill-tester-swarm Compares

Feature / Agentskill-tester-swarmStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Automated QA system for Claude Code skills. Discovers skills from GitHub/SkillsMP, installs them, generates tests, executes with screenshot capture, evaluates quality with A-F grades, and publishes an interactive dashboard.

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

Related Guides

SKILL.md Source

# Skill Tester Swarm

> "I don't just use skills. I test them all and show you which ones actually work."

An 8-agent swarm that automatically tests Claude Code skills and generates visual reports with screenshots.

## What It Does

1. **Discovers** skills from GitHub and marketplaces
2. **Installs** each in isolation
3. **Generates** test prompts from triggers
4. **Executes** tests and captures output
5. **Screenshots** terminal and file results
6. **Scores** quality (A-F grades)
7. **Reports** with pass/fail matrix
8. **Publishes** interactive dashboard

## Quick Start

```bash
./scripts/orchestrator.sh run
```

## Output

- Screenshots of every test
- Quality scores and grades
- Interactive web dashboard
- JSON data for automation

## Agents

| Agent | Role |
|-------|------|
| 0 | Skill Discoverer |
| 1 | Skill Installer |
| 2 | Test Generator |
| 3 | Test Executor |
| 4 | Screenshot Capturer |
| 5 | Quality Evaluator |
| 6 | Report Generator |
| 7 | Dashboard Publisher |

See README.md for full documentation.

Related Skills

dev-swarm-stage-market-research

16
from diegosouzapw/awesome-omni-skill

Conduct comprehensive market research and competitive analysis to validate the problem, understand the market landscape, and identify opportunities. Use when starting stage 01 (market-research) or when user asks about competitors or market analysis.

qa-tester

16
from diegosouzapw/awesome-omni-skill

QA Tester Agent. 테스트 작성, 실행, 검증을 담당합니다. 테스트, 검증, 단위테스트, 통합테스트, E2E 관련 요청 시 사용됩니다.

playwright-e2e-tester

16
from diegosouzapw/awesome-omni-skill

Expert in end-to-end testing with Playwright, the modern cross-browser testing framework. Specializes in test generation, page object patterns, visual regression testing, and CI/CD integration. Handles complex testing scenarios including authentication flows, API mocking, and mobile emulation.

oss-contributor-swarm

16
from diegosouzapw/awesome-omni-skill

Autonomous 9-agent swarm that continuously contributes to open source projects on GitHub. Finds good-first-issues, analyzes requirements, writes code/tests/docs, creates PRs, and responds to reviews - all automatically with learning.

memo-stress-tester

16
from diegosouzapw/awesome-omni-skill

Use when evaluating business documents for structural integrity and persuasive logic.

core-tester

16
from diegosouzapw/awesome-omni-skill

Comprehensive testing and quality assurance specialist for ensuring code quality through testing strategies

agent-penetration-tester

16
from diegosouzapw/awesome-omni-skill

Expert penetration tester specializing in ethical hacking, vulnerability assessment, and security testing. Masters offensive security techniques, exploit development, and comprehensive security assessments with focus on identifying and validating security weaknesses.

agent-accessibility-tester

16
from diegosouzapw/awesome-omni-skill

Expert accessibility tester specializing in WCAG compliance, inclusive design, and universal access. Masters screen reader compatibility, keyboard navigation, and assistive technology integration with focus on creating barrier-free digital experiences.

accessibility-tester

16
from diegosouzapw/awesome-omni-skill

Expert accessibility tester specializing in WCAG compliance, inclusive design, and universal access. Masters screen reader compatibility, keyboard navigation, and assistive technology integration with focus on creating barrier-free digital experiences.

acceptance-tester

16
from diegosouzapw/awesome-omni-skill

Execute systematic acceptance testing to verify implementations against acceptance criteria. Use this skill when tasks mention "驗收測試", "acceptance testing", "驗收", "validate implementation", or when Gherkin scenarios need to be executed.

qcsd-refinement-swarm

16
from diegosouzapw/awesome-omni-skill

QCSD Refinement phase swarm for Sprint Refinement sessions using SFDIPOT product factors, BDD scenario generation, and requirements validation.

dyad:swarm-pr-review

16
from diegosouzapw/awesome-omni-skill

Team-based PR review using Claude Code swarm. Spawns three specialized teammates (correctness expert, code health expert, UX wizard) who review the PR diff, discuss findings with each other, and reach consensus on real issues. Posts a summary with merge verdict and inline comments for HIGH/MEDIUM issues.