Skip to content

alexandervashurin/semaphore / .claude/skills/gstack

gstack

Flagged

Fast 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."

FileKindSize
.env.exampleother171 B
.github/workflows/skill-docs.ymlconfig648 B
.gitignoreother137 B
AGENTS.mdmarkdown2.5 KB
ARCHITECTURE.mdmarkdown20.7 KB
BROWSER.mdmarkdown16.5 KB
CHANGELOG.mdmarkdown73.3 KB
CLAUDE.mdmarkdown12.8 KB
CONTRIBUTING.mdmarkdown15.1 KB
ETHOS.mdmarkdown5.5 KB
LICENSEother1.0 KB
README.mdmarkdown21.5 KB
SKILL.mdskill md27.2 KB
SKILL.md.tmplother8.4 KB
TODOS.mdmarkdown21.9 KB
VERSIONother8 B
bin/dev-setupother2.4 KB
bin/dev-teardownother1.6 KB
bin/gstack-analyticsother6.3 KB
bin/gstack-community-dashboardother4.7 KB
bin/gstack-configother1.1 KB
bin/gstack-diff-scopeother2.4 KB
bin/gstack-review-logother409 B
bin/gstack-review-readother526 B
bin/gstack-slugother478 B
bin/gstack-telemetry-logother6.7 KB
bin/gstack-telemetry-syncother4.4 KB
bin/gstack-update-checkother6.9 KB
conductor.jsonconfig87 B
docs/images/github-2013.pngbinary61.9 KB
docs/images/github-2026.pngbinary59.1 KB
docs/skills.mdmarkdown44.2 KB
package.jsonmanifest3.1 KB
scripts/analytics.tsscript5.3 KB
scripts/dev-skill.tsscript2.4 KB
scripts/eval-compare.tsscript3.0 KB
scripts/eval-list.tsscript3.5 KB
scripts/eval-select.tsscript3.1 KB
scripts/eval-summary.tsscript6.4 KB
scripts/eval-watch.tsscript5.4 KB
scripts/gen-skill-docs.tsscript89.5 KB
scripts/skill-check.tsscript5.8 KB
setupother8.4 KB
supabase/config.shscript454 B
supabase/functions/community-pulse/index.tsscript1.7 KB
supabase/functions/telemetry-ingest/index.tsscript4.1 KB
supabase/functions/update-check/index.tsscript1.1 KB
supabase/migrations/001_telemetry.sqlother3.2 KB
test/analytics.test.tsscript10.2 KB
test/codex-e2e.test.tsscript7.5 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.tsscript6.3 KB
test/gen-skill-docs.test.tsscript37.3 KB
test/helpers/codex-session-runner.tsscript8.9 KB
test/helpers/e2e-helpers.tsscript9.5 KB
test/helpers/eval-store.test.tsscript19.8 KB
test/helpers/eval-store.tsscript23.6 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.tsscript11.6 KB
test/helpers/skill-parser.tsscript5.6 KB
test/helpers/touchfiles.tsscript11.0 KB
test/hook-scripts.test.tsscript13.6 KB
test/skill-e2e-browse.test.tsscript11.8 KB
test/skill-e2e-deploy.test.tsscript11.2 KB
test/skill-e2e-design.test.tsscript24.4 KB
test/skill-e2e-plan.test.tsscript19.7 KB
test/skill-e2e-qa-bugs.test.tsscript8.1 KB
test/skill-e2e-qa-workflow.test.tsscript15.4 KB
test/skill-e2e-review.test.tsscript23.2 KB
test/skill-e2e-workflow.test.tsscript23.2 KB
test/skill-llm-eval.test.tsscript33.6 KB
test/skill-parser.test.tsscript5.3 KB
test/skill-routing-e2e.test.tsscript26.3 KB
test/skill-validation.test.tsscript54.5 KB
test/telemetry.test.tsscript10.3 KB
test/touchfiles.test.tsscript10.1 KB

test/helpers/gemini-session-runner.test.ts

View on GitHub
import { describe, test, expect } from 'bun:test';
import { parseGeminiJSONL } from './gemini-session-runner';

// Fixture: actual Gemini CLI stream-json output with tool use
const FIXTURE_LINES = [
  '{"type":"init","timestamp":"2026-03-20T15:14:46.455Z","session_id":"test-session-123","model":"auto-gemini-3"}',
  '{"type":"message","timestamp":"2026-03-20T15:14:46.456Z","role":"user","content":"list the files"}',
  '{"type":"message","timestamp":"2026-03-20T15:14:49.650Z","role":"assistant","content":"I will list the files.","delta":true}',
  '{"type":"tool_use","timestamp":"2026-03-20T15:14:49.690Z","tool_name":"run_shell_command","tool_id":"cmd_1","parameters":{"command":"ls"}}',
  '{"type":"tool_result","timestamp":"2026-03-20T15:14:49.931Z","tool_id":"cmd_1","status":"success","output":"file1.ts\\nfile2.ts"}',
  '{"type":"message","timestamp":"2026-03-20T15:14:51.945Z","role":"assistant","content":"Here are the files.","delta":true}',
  '{"type":"result","timestamp":"2026-03-20T15:14:52.030Z","status":"success","stats":{"total_tokens":27147,"input_tokens":26928,"output_tokens":87,"cached":0,"duration_ms":5575,"tool_calls":1}}',
];

describe('parseGeminiJSONL', () => {
  test('extracts session ID from init event', () => {
    const parsed = parseGeminiJSONL(FIXTURE_LINES);
    expect(parsed.sessionId).toBe('test-session-123');
  });

  test('concatenates assistant message deltas into output', () => {
    const parsed = parseGeminiJSONL(FIXTURE_LINES);
    expect(parsed.output).toBe('I will list the files.Here are the files.');
  });

  test('ignores user messages', () => {
    const lines = [
      '{"type":"message","role":"user","content":"this should be ignored"}',
      '{"type":"message","role":"assistant","content":"this should be kept","delta":true}',
    ];
    const parsed = parseGeminiJSONL(lines);
    expect(parsed.output).toBe('this should be kept');
  });

  test('extracts tool names from tool_use events', () => {
    const parsed = parseGeminiJSONL(FIXTURE_LINES);
    expect(parsed.toolCalls).toHaveLength(1);
    expect(parsed.toolCalls[0]).toBe('run_shell_command');
  });

  test('extracts total tokens from result stats', () => {
    const parsed = parseGeminiJSONL(FIXTURE_LINES);
    expect(parsed.tokens).toBe(27147);
  });

  test('skips malformed lines without throwing', () => {
    const lines = [
      '{"type":"init","session_id":"ok"}',
      'this is not json',
      '{"type":"message","role":"assistant","content":"hello","delta":true}',
      '{incomplete json',
      '{"type":"result","status":"success","stats":{"total_tokens":100}}',
    ];
    const parsed = parseGeminiJSONL(lines);
    expect(parsed.sessionId).toBe('ok');
    expect(parsed.output).toBe('hello');
    expect(parsed.tokens).toBe(100);
  });

  test('skips empty and whitespace-only lines', () => {
    const lines = [
      '',
      '  ',
      '{"type":"init","session_id":"s1"}',
      '\t',
      '{"type":"result","status":"success","stats":{"total_tokens":50}}',
    ];
    const parsed = parseGeminiJSONL(lines);
    expect(parsed.sessionId).toBe('s1');
    expect(parsed.tokens).toBe(50);
  });

  test('handles empty input', () => {
    const parsed = parseGeminiJSONL([]);
    expect(parsed.output).toBe('');
    expect(parsed.toolCalls).toHaveLength(0);
    expect(parsed.tokens).toBe(0);
    expect(parsed.sessionId).toBeNull();
  });

  test('handles missing fields gracefully', () => {
    const lines = [
      '{"type":"init"}',                              // no session_id
      '{"type":"message","role":"assistant"}',         // no content
      '{"type":"tool_use"}',                           // no tool_name
      '{"type":"result","status":"success"}',          // no stats
    ];
    const parsed = parseGeminiJSONL(lines);
    expect(parsed.sessionId).toBeNull();
    expect(parsed.output).toBe('');
    expect(parsed.toolCalls).toHaveLength(0);
    expect(parsed.tokens).toBe(0);
  });

  test('handles multiple tool_use events', () => {
    const lines = [
      '{"type":"tool_use","tool_name":"run_shell_command","tool_id":"cmd_1","parameters":{"command":"ls"}}',
      '{"type":"tool_use","tool_name":"read_file","tool_id":"cmd_2","parameters":{"path":"foo.ts"}}',
      '{"type":"tool_use","tool_name":"run_shell_command","tool_id":"cmd_3","parameters":{"command":"cat bar.ts"}}',
    ];
    const parsed = parseGeminiJSONL(lines);
    expect(parsed.toolCalls).toEqual(['run_shell_command', 'read_file', 'run_shell_command']);
  });
});
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: 468kUpdated Claude CodeCodexVerifiedInstall
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: 468kUpdated Claude CodeCodexVerifiedInstall
rea-tool-designmorluto/reaAudit, investigate, design, or change REA investigation tools, CLI/MCP contracts, provider capabilities, and Evidence semantics.Stars: 468kUpdated Claude CodeCodexVerifiedInstall
ponytail-auditDietrichGebert/ponytailQuality audit of the whole repo: bugs, security, real load, missing tests, speed, and what to delete. Most important first.Stars: 194kUpdated Claude CodeCodexVerifiedInstall