Skip to content

olaafrossi/FoamPilot / .claude/skills/gstack

gstack

Flagged

Fast headless browser for QA testing and site dogfooding. Navigate pages, interact with elements, verify state, diff before/after, take annotated screenshots, test responsive layouts, forms, uploads, dialogs, and capture bug evidence. Use when asked to open or test a site, verify a deployment, dogfood a user flow, or file a bug with screenshots.

FileKindSize
.env.exampleother171 B
.github/actionlint.yamlconfig82 B
.github/docker/Dockerfile.ciother2.7 KB
.github/workflows/actionlint.ymlconfig176 B
.github/workflows/ci-image.ymlconfig1.0 KB
.github/workflows/evals-periodic.ymlconfig3.8 KB
.github/workflows/evals.ymlconfig8.1 KB
.github/workflows/skill-docs.ymlconfig1.2 KB
.gitignoreother243 B
AGENTS.mdmarkdown2.5 KB
ARCHITECTURE.mdmarkdown21.4 KB
BROWSER.mdmarkdown23.1 KB
CHANGELOG.mdmarkdown146.8 KB
CLAUDE.mdmarkdown19.2 KB
CONTRIBUTING.mdmarkdown17.6 KB
DESIGN.mdmarkdown4.4 KB
ETHOS.mdmarkdown7.3 KB
LICENSEother1.0 KB
README.mdmarkdown23.8 KB
SKILL.mdskill md26.1 KB
SKILL.md.tmplother7.8 KB
TODOS.mdmarkdown33.9 KB
VERSIONother9 B
actionlint.yamlconfig56 B
agents/openai.yamlconfig351 B
bun.lockother18.0 KB
conductor.jsonconfig87 B
design/prototype.tsscript5.4 KB
design/src/auth.tsscript1.7 KB
design/src/brief.tsscript1.9 KB
design/src/check.tsscript3.0 KB
design/src/cli.tsscript8.9 KB
design/src/commands.tsscript3.0 KB
design/src/compare.tsscript19.1 KB
design/src/design-to-code.tsscript3.0 KB
design/src/diff.tsscript3.3 KB
design/src/evolve.tsscript5.0 KB
design/src/gallery.tsscript7.0 KB
design/src/generate.tsscript4.0 KB
design/src/iterate.tsscript5.4 KB
design/src/memory.tsscript6.0 KB
design/src/serve.tsscript7.4 KB
design/src/session.tsscript1.8 KB
design/src/variants.tsscript8.4 KB
design/test/feedback-roundtrip.test.tsscript12.6 KB
design/test/gallery.test.tsscript5.0 KB
design/test/serve.test.tsscript12.6 KB
docs/designs/CHROME_VS_CHROMIUM_EXPLORATION.mdmarkdown4.0 KB
docs/designs/CONDUCTOR_CHROME_SIDEBAR_INTEGRATION.mdmarkdown3.5 KB
docs/designs/CONDUCTOR_SESSION_API.mdmarkdown3.9 KB
docs/designs/DESIGN_SHOTGUN.mdmarkdown22.5 KB
docs/designs/DESIGN_TOOLS_V1.mdmarkdown36.0 KB
docs/designs/ML_PROMPT_INJECTION_KILLER.mdmarkdown20.7 KB
docs/designs/SELF_LEARNING_V0.mdmarkdown5.5 KB
docs/images/github-2013.pngbinary61.9 KB
docs/images/github-2026.pngbinary59.1 KB
docs/skills.mdmarkdown45.3 KB
extension/background.jsscript8.1 KB
extension/content.cssother2.5 KB
extension/content.jsscript4.7 KB
extension/icons/icon-128.pngbinary2.8 KB
extension/icons/icon-16.pngbinary400 B
extension/icons/icon-48.pngbinary1.1 KB
extension/manifest.jsonconfig749 B
extension/popup.htmlother2.3 KB
extension/popup.jsscript1.7 KB
extension/sidepanel.cssother17.1 KB
extension/sidepanel.htmlother3.3 KB
extension/sidepanel.jsscript23.6 KB
lib/worktree.tsscript9.2 KB
package.jsonmanifest3.7 KB
pw-test-node.mjsscript147 B
scripts/analytics.tsscript5.3 KB
scripts/dev-skill.tsscript2.4 KB
scripts/discover-skills.tsscript1.2 KB
scripts/eval-compare.tsscript3.0 KB
scripts/eval-list.tsscript3.5 KB
scripts/eval-select.tsscript3.1 KB
scripts/eval-summary.tsscript6.5 KB
scripts/eval-watch.tsscript5.4 KB
scripts/gen-skill-docs.tsscript19.8 KB
scripts/resolvers/browse.tsscript4.3 KB
scripts/resolvers/codex-helpers.tsscript5.0 KB
scripts/resolvers/confidence.tsscript1.6 KB
scripts/resolvers/constants.tsscript2.7 KB
scripts/resolvers/design.tsscript44.8 KB
scripts/resolvers/index.tsscript3.1 KB
scripts/resolvers/learnings.tsscript3.9 KB
scripts/resolvers/preamble.tsscript27.7 KB
scripts/resolvers/review.tsscript47.1 KB
scripts/resolvers/testing.tsscript27.3 KB
scripts/resolvers/types.tsscript1.1 KB
scripts/resolvers/utility.tsscript15.5 KB
scripts/skill-check.tsscript7.1 KB
setupexecutablescript24.4 KB
supabase/config.shscript420 B
supabase/functions/community-pulse/index.tsscript4.1 KB
supabase/functions/telemetry-ingest/index.tsscript4.1 KB
supabase/functions/update-check/index.tsscript1.1 KB
supabase/migrations/001_telemetry.sqlother3.2 KB
supabase/migrations/002_tighten_rls.sqlother1.7 KB
supabase/verify-rls.shexecutablescript5.3 KB
test/analytics.test.tsscript10.2 KB
test/audit-compliance.test.tsscript3.9 KB
test/codex-e2e.test.tsscript8.0 KB
test/fixtures/coverage-audit-fixture.tsscript2.7 KB
test/fixtures/eval-baselines.jsonconfig388 B
test/fixtures/qa-eval-checkout-ground-truth.jsonconfig1.6 KB
test/fixtures/qa-eval-ground-truth.jsonconfig1.5 KB
test/fixtures/qa-eval-spa-ground-truth.jsonconfig1.6 KB
test/fixtures/review-eval-design-slop.cssother1.5 KB
test/fixtures/review-eval-design-slop.htmlother1.3 KB
test/fixtures/review-eval-enum-diff.rbscript986 B
test/fixtures/review-eval-enum.rbscript759 B
test/fixtures/review-eval-vuln.rbscript406 B
test/gemini-e2e.test.tsscript6.7 KB
test/gen-skill-docs.test.tsscript93.2 KB
test/global-discover.test.tsscript6.4 KB
test/helpers/codex-session-runner.tsscript9.4 KB
test/helpers/e2e-helpers.tsscript11.3 KB
test/helpers/eval-store.test.tsscript19.8 KB
test/helpers/eval-store.tsscript24.6 KB
test/helpers/gemini-session-runner.test.tsscript4.4 KB
test/helpers/gemini-session-runner.tsscript6.0 KB
test/helpers/llm-judge.tsscript4.2 KB
test/helpers/observability.test.tsscript9.9 KB
test/helpers/session-runner.test.tsscript3.7 KB
test/helpers/session-runner.tsscript11.8 KB
test/helpers/skill-parser.tsscript5.6 KB
test/helpers/touchfiles.tsscript18.7 KB
test/hook-scripts.test.tsscript13.6 KB
test/learnings.test.tsscript12.0 KB
test/review-log.test.tsscript2.7 KB
test/skill-e2e-bws.test.tsscript12.5 KB
test/skill-e2e-cso.test.tsscript8.7 KB
test/skill-e2e-deploy.test.tsscript17.6 KB
test/skill-e2e-design.test.tsscript24.4 KB
test/skill-e2e-learnings.test.tsscript5.1 KB
test/skill-e2e-plan.test.tsscript27.6 KB
test/skill-e2e-qa-bugs.test.tsscript8.1 KB
test/skill-e2e-qa-workflow.test.tsscript15.4 KB
test/skill-e2e-review.test.tsscript28.7 KB
test/skill-e2e-sidebar.test.tsscript9.6 KB
test/skill-e2e-workflow.test.tsscript21.0 KB
test/skill-e2e.test.tsscript131.7 KB
test/skill-llm-eval.test.tsscript36.7 KB
test/skill-parser.test.tsscript5.3 KB
test/skill-routing-e2e.test.tsscript25.8 KB
test/skill-validation.test.tsscript59.5 KB
test/telemetry.test.tsscript15.5 KB
test/touchfiles.test.tsscript11.9 KB
test/uninstall.test.tsscript6.2 KB
test/worktree.test.tsscript9.2 KB
ws-test.tsscript692 B

scripts/eval-summary.ts

View on GitHub
#!/usr/bin/env bun
/**
 * Aggregate summary of all eval runs from ~/.gstack-dev/evals/
 *
 * Usage: bun run eval:summary
 */

import * as fs from 'fs';
import * as path from 'path';
import * as os from 'os';
import type { EvalResult } from '../test/helpers/eval-store';
import { getProjectEvalDir } from '../test/helpers/eval-store';

const EVAL_DIR = getProjectEvalDir();

let files: string[];
try {
  files = fs.readdirSync(EVAL_DIR).filter(f => f.endsWith('.json'));
} catch {
  console.log('No eval runs yet. Run: EVALS=1 bun run test:evals');
  process.exit(0);
}

if (files.length === 0) {
  console.log('No eval runs yet. Run: EVALS=1 bun run test:evals');
  process.exit(0);
}

// Load all results
const results: EvalResult[] = [];
for (const file of files) {
  try {
    results.push(JSON.parse(fs.readFileSync(path.join(EVAL_DIR, file), 'utf-8')));
  } catch { continue; }
}

// Aggregate stats
const e2eRuns = results.filter(r => r.tier === 'e2e');
const judgeRuns = results.filter(r => r.tier === 'llm-judge');
const totalCost = results.reduce((s, r) => s + (r.total_cost_usd || 0), 0);
const avgE2ECost = e2eRuns.length > 0 ? e2eRuns.reduce((s, r) => s + r.total_cost_usd, 0) / e2eRuns.length : 0;
const avgJudgeCost = judgeRuns.length > 0 ? judgeRuns.reduce((s, r) => s + r.total_cost_usd, 0) / judgeRuns.length : 0;

// Duration + turns from E2E runs
const avgE2EDuration = e2eRuns.length > 0
  ? e2eRuns.reduce((s, r) => s + (r.total_duration_ms || 0), 0) / e2eRuns.length
  : 0;
const e2eTurns: number[] = [];
for (const r of e2eRuns) {
  const runTurns = r.tests.reduce((s, t) => s + (t.turns_used || 0), 0);
  if (runTurns > 0) e2eTurns.push(runTurns);
}
const avgE2ETurns = e2eTurns.length > 0
  ? e2eTurns.reduce((a, b) => a + b, 0) / e2eTurns.length
  : 0;

// Per-test efficiency stats (avg turns + duration across runs)
const testEfficiency = new Map<string, { turns: number[]; durations: number[]; costs: number[] }>();
for (const r of e2eRuns) {
  for (const t of r.tests) {
    if (!testEfficiency.has(t.name)) {
      testEfficiency.set(t.name, { turns: [], durations: [], costs: [] });
    }
    const stats = testEfficiency.get(t.name)!;
    if (t.turns_used !== undefined) stats.turns.push(t.turns_used);
    if (t.duration_ms > 0) stats.durations.push(t.duration_ms);
    if (t.cost_usd > 0) stats.costs.push(t.cost_usd);
  }
}

// Detection rates from outcome evals
const detectionRates: number[] = [];
for (const r of e2eRuns) {
  for (const t of r.tests) {
    if (t.detection_rate !== undefined) {
      detectionRates.push(t.detection_rate);
    }
  }
}
const avgDetection = detectionRates.length > 0
  ? detectionRates.reduce((a, b) => a + b, 0) / detectionRates.length
  : null;

// Flaky tests (passed in some runs, failed in others)
const testResults = new Map<string, boolean[]>();
for (const r of results) {
  for (const t of r.tests) {
    const key = `${r.tier}:${t.name}`;
    if (!testResults.has(key)) testResults.set(key, []);
    testResults.get(key)!.push(t.passed);
  }
}
const flakyTests: string[] = [];
for (const [name, outcomes] of testResults) {
  if (outcomes.length >= 2) {
    const hasPass = outcomes.some(o => o);
    const hasFail = outcomes.some(o => !o);
    if (hasPass && hasFail) flakyTests.push(name);
  }
}

// Branch stats
const branchStats = new Map<string, { runs: number; avgDetection: number; detections: number[] }>();
for (const r of e2eRuns) {
  if (!branchStats.has(r.branch)) {
    branchStats.set(r.branch, { runs: 0, avgDetection: 0, detections: [] });
  }
  const stats = branchStats.get(r.branch)!;
  stats.runs++;
  for (const t of r.tests) {
    if (t.detection_rate !== undefined) {
      stats.detections.push(t.detection_rate);
    }
  }
}
for (const stats of branchStats.values()) {
  stats.avgDetection = stats.detections.length > 0
    ? stats.detections.reduce((a, b) => a + b, 0) / stats.detections.length
    : 0;
}

// Print summary
console.log('');
console.log('Eval Summary');
console.log('═'.repeat(70));
console.log(`  Total runs:        ${results.length} (${e2eRuns.length} e2e, ${judgeRuns.length} llm-judge)`);
console.log(`  Total spend:       $${totalCost.toFixed(2)}`);
console.log(`  Avg cost/e2e:      $${avgE2ECost.toFixed(2)}`);
console.log(`  Avg cost/judge:    $${avgJudgeCost.toFixed(2)}`);
if (avgE2EDuration > 0) {
  console.log(`  Avg duration/e2e:  ${Math.round(avgE2EDuration / 1000)}s`);
}
if (avgE2ETurns > 0) {
  console.log(`  Avg turns/e2e:     ${Math.round(avgE2ETurns)}`);
}
if (avgDetection !== null) {
  console.log(`  Avg detection:     ${avgDetection.toFixed(1)} bugs`);
}
console.log('─'.repeat(70));

// Per-test efficiency averages (only if we have enough data)
if (testEfficiency.size > 0 && e2eRuns.length >= 2) {
  console.log('  Per-test efficiency (averages across runs):');
  const sorted = [...testEfficiency.entries()]
    .filter(([, s]) => s.turns.length >= 2)
    .sort((a, b) => {
      const avgA = a[1].costs.reduce((s, c) => s + c, 0) / a[1].costs.length;
      const avgB = b[1].costs.reduce((s, c) => s + c, 0) / b[1].costs.length;
      return avgB - avgA;
    });
  for (const [name, stats] of sorted) {
    const avgT = Math.round(stats.turns.reduce((a, b) => a + b, 0) / stats.turns.length);
    const avgD = Math.round(stats.durations.reduce((a, b) => a + b, 0) / stats.durations.length / 1000);
    const avgC = (stats.costs.reduce((a, b) => a + b, 0) / stats.costs.length).toFixed(2);
    const label = name.length > 30 ? name.slice(0, 27) + '...' : name.padEnd(30);
    console.log(`    ${label}  $${avgC}  ${avgT}t  ${avgD}s  (${stats.turns.length} runs)`);
  }
  console.log('─'.repeat(70));
}

if (flakyTests.length > 0) {
  console.log(`  Flaky tests (${flakyTests.length}):`);
  for (const name of flakyTests) {
    console.log(`    - ${name}`);
  }
  console.log('─'.repeat(70));
}

if (branchStats.size > 0) {
  console.log('  Branches:');
  const sorted = [...branchStats.entries()].sort((a, b) => b[1].avgDetection - a[1].avgDetection);
  for (const [branch, stats] of sorted) {
    const det = stats.detections.length > 0 ? ` avg det: ${stats.avgDetection.toFixed(1)}` : '';
    console.log(`    ${branch.padEnd(30)} ${stats.runs} runs${det}`);
  }
  console.log('─'.repeat(70));
}

// Date range
const timestamps = results.map(r => r.timestamp).filter(Boolean).sort();
if (timestamps.length > 0) {
  const first = timestamps[0].replace('T', ' ').slice(0, 16);
  const last = timestamps[timestamps.length - 1].replace('T', ' ').slice(0, 16);
  console.log(`  Date range: ${first} → ${last}`);
}

console.log(`  Dir: ${EVAL_DIR}`);
console.log('');
finishing-a-development-branchobra/superpowersUse when implementation is complete, all tests pass, and you need to decide how to integrate the workStars: 321kUpdated Claude CodeCodexVerifiedInstall
systematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixesStars: 321kUpdated Claude CodeCodexVerifiedInstall
test-driven-developmentobra/superpowersUse when implementing any feature or bugfix, before writing implementation codeStars: 321kUpdated Claude CodeCodexVerifiedInstall
skill-creatoranthropics/skillsCreate new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.Stars: 197kUpdated Claude CodeCodexVerifiedInstall