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.ts

View on GitHub
/**
 * Gemini CLI subprocess runner for skill E2E testing.
 *
 * Spawns `gemini -p` as an independent process, parses its stream-json
 * output, and returns structured results. Follows the same pattern as
 * codex-session-runner.ts but adapted for the Gemini CLI.
 *
 * Key differences from Codex session-runner:
 * - Uses `gemini -p` instead of `codex exec`
 * - Output is NDJSON with event types: init, message, tool_use, tool_result, result
 * - Uses `--output-format stream-json --yolo` instead of `--json -s read-only`
 * - No temp HOME needed — Gemini discovers skills from `.agents/skills/` in cwd
 * - Message events are streamed with `delta: true` — must concatenate
 */

import * as path from 'path';

// --- Interfaces ---

export interface GeminiResult {
  output: string;           // Full assistant message text (concatenated deltas)
  toolCalls: string[];      // Tool names from tool_use events
  tokens: number;           // Total tokens used
  exitCode: number;         // Process exit code
  durationMs: number;       // Wall clock time
  sessionId: string | null; // Session ID from init event
  rawLines: string[];       // Raw JSONL lines for debugging
}

// --- JSONL parser ---

export interface ParsedGeminiJSONL {
  output: string;
  toolCalls: string[];
  tokens: number;
  sessionId: string | null;
}

/**
 * Parse an array of JSONL lines from `gemini -p --output-format stream-json`.
 * Pure function — no I/O, no side effects.
 *
 * Handles these Gemini event types:
 * - init → extract session_id
 * - message (role=assistant, delta=true) → concatenate content into output
 * - tool_use → extract tool_name
 * - tool_result → logged but not extracted
 * - result → extract token usage from stats
 */
export function parseGeminiJSONL(lines: string[]): ParsedGeminiJSONL {
  const outputParts: string[] = [];
  const toolCalls: string[] = [];
  let tokens = 0;
  let sessionId: string | null = null;

  for (const line of lines) {
    if (!line.trim()) continue;
    try {
      const obj = JSON.parse(line);
      const t = obj.type || '';

      if (t === 'init') {
        const sid = obj.session_id || '';
        if (sid) sessionId = sid;
      } else if (t === 'message') {
        if (obj.role === 'assistant' && obj.content) {
          outputParts.push(obj.content);
        }
      } else if (t === 'tool_use') {
        const name = obj.tool_name || '';
        if (name) toolCalls.push(name);
      } else if (t === 'result') {
        const stats = obj.stats || {};
        tokens = (stats.total_tokens || 0);
      }
    } catch { /* skip malformed lines */ }
  }

  return {
    output: outputParts.join(''),
    toolCalls,
    tokens,
    sessionId,
  };
}

// --- Main runner ---

/**
 * Run a prompt via `gemini -p` and return structured results.
 *
 * Spawns gemini with stream-json output, parses JSONL events,
 * and returns a GeminiResult. Skips gracefully if gemini binary is not found.
 */
export async function runGeminiSkill(opts: {
  prompt: string;           // What to ask Gemini
  timeoutMs?: number;       // Default 300000 (5 min)
  cwd?: string;             // Working directory (where .agents/skills/ lives)
}): Promise<GeminiResult> {
  const {
    prompt,
    timeoutMs = 300_000,
    cwd,
  } = opts;

  const startTime = Date.now();

  // Check if gemini binary exists
  const whichResult = Bun.spawnSync(['which', 'gemini']);
  if (whichResult.exitCode !== 0) {
    return {
      output: 'SKIP: gemini binary not found',
      toolCalls: [],
      tokens: 0,
      exitCode: -1,
      durationMs: Date.now() - startTime,
      sessionId: null,
      rawLines: [],
    };
  }

  // Build gemini command
  const args = ['-p', prompt, '--output-format', 'stream-json', '--yolo'];

  // Spawn gemini — uses real HOME for auth, cwd for skill discovery
  const proc = Bun.spawn(['gemini', ...args], {
    cwd: cwd || process.cwd(),
    stdout: 'pipe',
    stderr: 'pipe',
  });

  // Race against timeout
  let timedOut = false;
  const timeoutId = setTimeout(() => {
    timedOut = true;
    proc.kill();
  }, timeoutMs);

  // Stream and collect JSONL from stdout
  const collectedLines: string[] = [];
  const stderrPromise = new Response(proc.stderr).text();

  const reader = proc.stdout.getReader();
  const decoder = new TextDecoder();
  let buf = '';

  try {
    while (true) {
      const { done, value } = await reader.read();
      if (done) break;
      buf += decoder.decode(value, { stream: true });
      const lines = buf.split('\n');
      buf = lines.pop() || '';
      for (const line of lines) {
        if (!line.trim()) continue;
        collectedLines.push(line);

        // Real-time progress to stderr
        try {
          const event = JSON.parse(line);
          if (event.type === 'tool_use' && event.tool_name) {
            const elapsed = Math.round((Date.now() - startTime) / 1000);
            process.stderr.write(`  [gemini ${elapsed}s] tool: ${event.tool_name}\n`);
          } else if (event.type === 'message' && event.role === 'assistant' && event.content) {
            const elapsed = Math.round((Date.now() - startTime) / 1000);
            process.stderr.write(`  [gemini ${elapsed}s] message: ${event.content.slice(0, 100)}\n`);
          }
        } catch { /* skip — parseGeminiJSONL will handle it later */ }
      }
    }
  } catch { /* stream read error — fall through to exit code handling */ }

  // Flush remaining buffer
  if (buf.trim()) {
    collectedLines.push(buf);
  }

  const stderr = await stderrPromise;
  const exitCode = await proc.exited;
  clearTimeout(timeoutId);

  const durationMs = Date.now() - startTime;

  // Parse all collected JSONL lines
  const parsed = parseGeminiJSONL(collectedLines);

  // Log stderr if non-empty (may contain auth errors, etc.)
  if (stderr.trim()) {
    process.stderr.write(`  [gemini stderr] ${stderr.trim().slice(0, 200)}\n`);
  }

  return {
    output: parsed.output,
    toolCalls: parsed.toolCalls,
    tokens: parsed.tokens,
    exitCode: timedOut ? 124 : exitCode,
    durationMs,
    sessionId: parsed.sessionId,
    rawLines: collectedLines,
  };
}
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