alexandervashurin/semaphore / .claude/skills/gstack
gstack
FlaggedFast headless browser for QA testing and site dogfooding. Navigate any URL, interact with elements, verify page state, diff before/after actions, take annotated screenshots, check responsive layouts, test forms and uploads, handle dialogs, and assert element states. ~100ms per command. Use when you need to test a feature, verify a deployment, dogfood a user flow, or file a bug with evidence. gstack also includes development workflow skills. When you notice the user is at these stages, suggest the appropriate skill: - Brainstorming a new idea → suggest /office-hours - Reviewing a plan (strategy) → suggest /plan-ceo-review - Reviewing a plan (architecture) → suggest /plan-eng-review - Reviewing a plan (design) → suggest /plan-design-review - Creating a design system → suggest /design-consultation - Debugging errors → suggest /investigate - Testing the app → suggest /qa - Code review before merge → suggest /review - Visual design audit → suggest /design-review - Ready to deploy / create PR → suggest /ship - Post-ship doc updates → suggest /document-release - Weekly retrospective → suggest /retro - Wanting a second opinion or adversarial code review → suggest /codex - Working with production or live systems → suggest /careful - Want to scope edits to one module/directory → suggest /freeze - Maximum safety mode (destructive warnings + edit restrictions) → suggest /guard - Removing edit restrictions → suggest /unfreeze - Upgrading gstack to latest version → suggest /gstack-upgrade If the user pushes back on skill suggestions ("stop suggesting things", "I don't need suggestions", "too aggressive"): 1. Stop suggesting for the rest of this session 2. Run: gstack-config set proactive false 3. Say: "Got it — I'll stop suggesting skills. Just tell me to be proactive again if you change your mind." If the user says "be proactive again" or "turn on suggestions": 1. Run: gstack-config set proactive true 2. Say: "Proactive suggestions are back on."
scripts/eval-select.ts
View on GitHub#!/usr/bin/env bun
/**
* Show which E2E and LLM-judge tests would run based on the current git diff.
*
* Usage:
* bun run eval:select # human-readable output
* bun run eval:select --json # machine-readable JSON
* bun run eval:select --base main # override base branch
*/
import * as path from 'path';
import {
selectTests,
detectBaseBranch,
getChangedFiles,
E2E_TOUCHFILES,
LLM_JUDGE_TOUCHFILES,
GLOBAL_TOUCHFILES,
} from '../test/helpers/touchfiles';
const ROOT = path.resolve(import.meta.dir, '..');
const args = process.argv.slice(2);
const jsonMode = args.includes('--json');
const baseIdx = args.indexOf('--base');
const baseOverride = baseIdx >= 0 ? args[baseIdx + 1] : undefined;
// Detect base branch
const baseBranch = baseOverride || detectBaseBranch(ROOT) || 'main';
const changedFiles = getChangedFiles(baseBranch, ROOT);
if (changedFiles.length === 0) {
if (jsonMode) {
console.log(JSON.stringify({ base: baseBranch, changed_files: 0, e2e: 'all', llm_judge: 'all', reason: 'no diff — would run all tests' }));
} else {
console.log(`Base: ${baseBranch}`);
console.log('No changed files detected — all tests would run.');
}
process.exit(0);
}
const e2eSelection = selectTests(changedFiles, E2E_TOUCHFILES, GLOBAL_TOUCHFILES);
const llmSelection = selectTests(changedFiles, LLM_JUDGE_TOUCHFILES, GLOBAL_TOUCHFILES);
if (jsonMode) {
console.log(JSON.stringify({
base: baseBranch,
changed_files: changedFiles,
e2e: {
selected: e2eSelection.selected,
skipped: e2eSelection.skipped,
reason: e2eSelection.reason,
count: `${e2eSelection.selected.length}/${Object.keys(E2E_TOUCHFILES).length}`,
},
llm_judge: {
selected: llmSelection.selected,
skipped: llmSelection.skipped,
reason: llmSelection.reason,
count: `${llmSelection.selected.length}/${Object.keys(LLM_JUDGE_TOUCHFILES).length}`,
},
}, null, 2));
} else {
console.log(`Base: ${baseBranch}`);
console.log(`Changed files: ${changedFiles.length}`);
console.log();
console.log(`E2E (${e2eSelection.reason}): ${e2eSelection.selected.length}/${Object.keys(E2E_TOUCHFILES).length} tests`);
if (e2eSelection.selected.length > 0 && e2eSelection.selected.length < Object.keys(E2E_TOUCHFILES).length) {
console.log(` Selected: ${e2eSelection.selected.join(', ')}`);
console.log(` Skipped: ${e2eSelection.skipped.join(', ')}`);
} else if (e2eSelection.selected.length === 0) {
console.log(' No E2E tests affected.');
} else {
console.log(' All E2E tests selected.');
}
console.log();
console.log(`LLM-judge (${llmSelection.reason}): ${llmSelection.selected.length}/${Object.keys(LLM_JUDGE_TOUCHFILES).length} tests`);
if (llmSelection.selected.length > 0 && llmSelection.selected.length < Object.keys(LLM_JUDGE_TOUCHFILES).length) {
console.log(` Selected: ${llmSelection.selected.join(', ')}`);
console.log(` Skipped: ${llmSelection.skipped.join(', ')}`);
} else if (llmSelection.selected.length === 0) {
console.log(' No LLM-judge tests affected.');
} else {
console.log(' All LLM-judge tests selected.');
}
}
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| rea-analysis-optimizationmorluto/reaOptimize REA providers and shared analysis workflows for agent context, latency, CPU, and memory while preserving correctness and Evidence. Use for analysis bottlenecks and cache or query design; CI/test-suite optimization belongs to rea-ci-tests-audit. | Stars: 465k | Updated | Claude CodeCodex | Verified | Install |
| rea-ci-tests-auditmorluto/reaAudit REA CI and test suites for correctness, fixture drift, false passes, and measured performance; use for suite or workflow investigations and efficiency changes, rather than ordinary feature testing or a single test failure. | Stars: 465k | Updated | Claude CodeCodex | Verified | Install |
| rea-tool-designmorluto/reaAudit, investigate, design, or change REA investigation tools, CLI/MCP contracts, provider capabilities, and Evidence semantics. | Stars: 465k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-auditDietrichGebert/ponytailQuality audit of the whole repo: bugs, security, real load, missing tests, speed, and what to delete. Most important first. | Stars: 192k | Updated | Claude CodeCodex | Verified | Install |