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/llm-judge.ts

View on GitHub
/**
 * Shared LLM-as-judge helpers for eval and E2E tests.
 *
 * Provides callJudge (generic JSON-from-LLM), judge (doc quality scorer),
 * and outcomeJudge (planted-bug detection scorer).
 *
 * Requires: ANTHROPIC_API_KEY env var
 */

import Anthropic from '@anthropic-ai/sdk';

export interface JudgeScore {
  clarity: number;       // 1-5
  completeness: number;  // 1-5
  actionability: number; // 1-5
  reasoning: string;
}

export interface OutcomeJudgeResult {
  detected: string[];
  missed: string[];
  false_positives: number;
  detection_rate: number;
  evidence_quality: number;
  reasoning: string;
}

/**
 * Call claude-sonnet-4-6 with a prompt, extract JSON response.
 * Retries once on 429 rate limit errors.
 */
export async function callJudge<T>(prompt: string): Promise<T> {
  const client = new Anthropic();

  const makeRequest = () => client.messages.create({
    model: 'claude-sonnet-4-6',
    max_tokens: 1024,
    messages: [{ role: 'user', content: prompt }],
  });

  let response;
  try {
    response = await makeRequest();
  } catch (err: any) {
    if (err.status === 429) {
      await new Promise(r => setTimeout(r, 1000));
      response = await makeRequest();
    } else {
      throw err;
    }
  }

  const text = response.content[0].type === 'text' ? response.content[0].text : '';
  const jsonMatch = text.match(/\{[\s\S]*\}/);
  if (!jsonMatch) throw new Error(`Judge returned non-JSON: ${text.slice(0, 200)}`);
  return JSON.parse(jsonMatch[0]) as T;
}

/**
 * Score documentation quality on clarity/completeness/actionability (1-5).
 */
export async function judge(section: string, content: string): Promise<JudgeScore> {
  return callJudge<JudgeScore>(`You are evaluating documentation quality for an AI coding agent's CLI tool reference.

The agent reads this documentation to learn how to use a headless browser CLI. It needs to:
1. Understand what each command does
2. Know what arguments to pass
3. Know valid values for enum-like parameters
4. Construct correct command invocations without guessing

Rate the following ${section} on three dimensions (1-5 scale):

- **clarity** (1-5): Can an agent understand what each command/flag does from the description alone?
- **completeness** (1-5): Are arguments, valid values, and important behaviors documented? Would an agent need to guess anything?
- **actionability** (1-5): Can an agent construct correct command invocations from this reference alone?

Scoring guide:
- 5: Excellent — no ambiguity, all info present
- 4: Good — minor gaps an experienced agent could infer
- 3: Adequate — some guessing required
- 2: Poor — significant info missing
- 1: Unusable — agent would fail without external help

Respond with ONLY valid JSON in this exact format:
{"clarity": N, "completeness": N, "actionability": N, "reasoning": "brief explanation"}

Here is the ${section} to evaluate:

${content}`);
}

/**
 * Evaluate a QA report against planted-bug ground truth.
 * Returns detection metrics for the planted bugs.
 */
export async function outcomeJudge(
  groundTruth: any,
  report: string,
): Promise<OutcomeJudgeResult> {
  return callJudge<OutcomeJudgeResult>(`You are evaluating a QA testing report against known ground truth bugs.

GROUND TRUTH (${groundTruth.total_bugs} planted bugs):
${JSON.stringify(groundTruth.bugs, null, 2)}

QA REPORT (generated by an AI agent):
${report}

For each planted bug, determine if the report identified it. A bug counts as
"detected" if the report describes the same defect, even if the wording differs.
Use the detection_hint keywords as guidance.

Also count false positives: issues in the report that don't correspond to any
planted bug AND aren't legitimate issues with the page.

Respond with ONLY valid JSON:
{
  "detected": ["bug-id-1", "bug-id-2"],
  "missed": ["bug-id-3"],
  "false_positives": 0,
  "detection_rate": 2,
  "evidence_quality": 4,
  "reasoning": "brief explanation"
}

Rules:
- "detected" and "missed" arrays must only contain IDs from the ground truth: ${groundTruth.bugs.map((b: any) => b.id).join(', ')}
- detection_rate = length of detected array
- evidence_quality (1-5): Do detected bugs have screenshots, repro steps, or specific element references?
  5 = excellent evidence for every bug, 1 = no evidence at all`);
}
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: 471kUpdated 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: 471kUpdated Claude CodeCodexVerifiedInstall
rea-tool-designmorluto/reaAudit, investigate, design, or change REA investigation tools, CLI/MCP contracts, provider capabilities, and Evidence semantics.Stars: 471kUpdated 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