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."
test/helpers/gemini-session-runner.test.ts
View on GitHubimport { 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']);
});
});
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: 468k | 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: 468k | 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: 468k | 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: 194k | Updated | Claude CodeCodex | Verified | Install |