Test the specific feature/fix implemented in the current session using browser or API tools.
Tests the specific feature or bug fix implemented in the current session using browser or API tools.
/plugin marketplace add https://www.claudepluginhub.com/api/plugins/yuvasee-samocode/marketplace.json/plugin install yuvasee-samocode@cpd-yuvasee-samocodeThis skill inherits all available tools. When active, it can use any tool Claude has access to.
Tests the specific feature or bug fix implemented in the current session. NOT full E2E testing - focused on the session's work.
Read session context:
_overview.md to understand what was implementedDetermine test strategy:
Select browser testing tool (if frontend testing needed):
Choose the most suitable tool for your needs:
| Tool | Best For | Setup |
|---|---|---|
| chrome-devtools MCP | Quick inspection, console access | Add to .mcp.json |
| Puppeteer | Scripted browser automation | npx puppeteer |
| Playwright | Cross-browser testing, screenshots | npx playwright |
Recommendation:
If adding MCP: After modifying .mcp.json, signal continue to restart the agent process (MCP doesn't hot-reload).
Start the application:
.samocode file or README for startup instructionsExecute feature tests:
Browser testing:
API testing:
# Example: Test endpoint
curl -X POST http://localhost:8000/api/endpoint \
-H "Content-Type: application/json" \
-d '{"test": "data"}'
Smoke test (side effect):
Document results:
Create [SESSION_PATH]/[TIMESTAMP_FILE]-test-[feature-slug].md:
# Test: [feature name]
Date: [TIMESTAMP_LOG]
## What Was Tested
[Brief description of implemented feature]
## Test Environment
- Working Dir: [path]
- App Status: [running/failed to start]
- Testing Tools: [chrome-devtools/puppeteer/playwright/curl]
## Test Steps
1. [Step and result]
2. [Step and result]
...
## Results
- Feature Test: [PASS/FAIL]
- Smoke Test: [PASS/FAIL]
## Issues Found
[None or list of issues]
Update session:
_overview.md:
- [TIMESTAMP_ITERATION] Feature tested: [result] -> [filename].md- [filename].md - Test reportcd [SESSION_DIR] && git add . && git commit -m "Test: [feature]"Signal result:
continue, recommend quality phaseblocked with failure details (don't auto-fix)Add to .mcp.json:
{
"mcpServers": {
"chrome-devtools": {
"command": "npx",
"args": ["chrome-devtools-mcp@latest", "--headless=true"]
}
}
}
Then signal continue to restart with new MCP.
# Quick test script
npx puppeteer <<'EOF'
const puppeteer = require('puppeteer');
(async () => {
const browser = await puppeteer.launch({ headless: true });
const page = await browser.newPage();
await page.goto('http://localhost:3000');
// ... test steps
await browser.close();
})();
EOF
# Quick test
npx playwright test --headed=false
# Or inline script
npx playwright <<'EOF'
const { chromium } = require('playwright');
(async () => {
const browser = await chromium.launch();
const page = await browser.newPage();
await page.goto('http://localhost:3000');
await page.screenshot({ path: 'test.png' });
await browser.close();
})();
EOF
_overview.md -> Check project .samocode file for MAIN_REPO, or ask userActivates when the user asks about AI prompts, needs prompt templates, wants to search for prompts, or mentions prompts.chat. Use for discovering, retrieving, and improving prompts.
Search, retrieve, and install Agent Skills from the prompts.chat registry using MCP tools. Use when the user asks to find skills, browse skill catalogs, install a skill for Claude, or extend Claude's capabilities with reusable AI agent components.
Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.