@runchr/gstack-antigravity 0.1.0 → 0.1.2

package/.agents/skills/gstack/test/skill-e2e-browse.test.ts

@@ -0,0 +1,293 @@
+import { describe, test, expect, beforeAll, afterAll } from 'bun:test';
+import { runSkillTest } from './helpers/session-runner';
+import {
+  ROOT, browseBin, runId, evalsEnabled,
+  describeIfSelected, testConcurrentIfSelected,
+  copyDirSync, setupBrowseShims, logCost, recordE2E,
+  createEvalCollector, finalizeEvalCollector,
+} from './helpers/e2e-helpers';
+import { startTestServer } from '../browse/test/test-server';
+import { spawnSync } from 'child_process';
+import * as fs from 'fs';
+import * as path from 'path';
+import * as os from 'os';
+
+const evalCollector = createEvalCollector('e2e-browse');
+
+let testServer: ReturnType<typeof startTestServer>;
+let tmpDir: string;
+
+describeIfSelected('Skill E2E tests', [
+  'browse-basic', 'browse-snapshot', 'skillmd-setup-discovery',
+  'skillmd-no-local-binary', 'skillmd-outside-git', 'session-awareness',
+], () => {
+  beforeAll(() => {
+    testServer = startTestServer();
+    tmpDir = fs.mkdtempSync(path.join(os.tmpdir(), 'skill-e2e-'));
+    setupBrowseShims(tmpDir);
+  });
+
+  afterAll(() => {
+    testServer?.server?.stop();
+    try { fs.rmSync(tmpDir, { recursive: true, force: true }); } catch {}
+  });
+
+  testConcurrentIfSelected('browse-basic', async () => {
+    const result = await runSkillTest({
+      prompt: `You have a browse binary at ${browseBin}. Assign it to B variable and run these commands in sequence:
+1. $B goto ${testServer.url}
+2. $B snapshot -i
+3. $B text
+4. $B screenshot /tmp/skill-e2e-test.png
+Report the results of each command.`,
+      workingDirectory: tmpDir,
+      maxTurns: 10,
+      timeout: 60_000,
+      testName: 'browse-basic',
+      runId,
+    });
+
+    logCost('browse basic', result);
+    recordE2E(evalCollector, 'browse basic commands', 'Skill E2E tests', result);
+    expect(result.browseErrors).toHaveLength(0);
+    expect(result.exitReason).toBe('success');
+  }, 90_000);
+
+  testConcurrentIfSelected('browse-snapshot', async () => {
+    const result = await runSkillTest({
+      prompt: `You have a browse binary at ${browseBin}. Assign it to B variable and run:
+1. $B goto ${testServer.url}
+2. $B snapshot -i
+3. $B snapshot -c
+4. $B snapshot -D
+5. $B snapshot -i -a -o /tmp/skill-e2e-annotated.png
+Report what each command returned.`,
+      workingDirectory: tmpDir,
+      maxTurns: 10,
+      timeout: 60_000,
+      testName: 'browse-snapshot',
+      runId,
+    });
+
+    logCost('browse snapshot', result);
+    recordE2E(evalCollector, 'browse snapshot flags', 'Skill E2E tests', result);
+    // browseErrors can include false positives from hallucinated paths (e.g. "baltimore" vs "bangalore")
+    if (result.browseErrors.length > 0) {
+      console.warn('Browse errors (non-fatal):', result.browseErrors);
+    }
+    expect(result.exitReason).toBe('success');
+  }, 90_000);
+
+  testConcurrentIfSelected('skillmd-setup-discovery', async () => {
+    const skillMd = fs.readFileSync(path.join(ROOT, 'SKILL.md'), 'utf-8');
+    const setupStart = skillMd.indexOf('## SETUP');
+    const setupEnd = skillMd.indexOf('## IMPORTANT');
+    const setupBlock = skillMd.slice(setupStart, setupEnd);
+
+    // Guard: verify we extracted a valid setup block
+    expect(setupBlock).toContain('browse/dist/browse');
+
+    const result = await runSkillTest({
+      prompt: `Follow these instructions to find the browse binary and run a basic command.
+
+${setupBlock}
+
+After finding the binary, run: $B goto ${testServer.url}
+Then run: $B text
+Report whether it worked.`,
+      workingDirectory: tmpDir,
+      maxTurns: 10,
+      timeout: 60_000,
+      testName: 'skillmd-setup-discovery',
+      runId,
+    });
+
+    recordE2E(evalCollector, 'SKILL.md setup block discovery', 'Skill E2E tests', result);
+    expect(result.browseErrors).toHaveLength(0);
+    expect(result.exitReason).toBe('success');
+  }, 90_000);
+
+  testConcurrentIfSelected('skillmd-no-local-binary', async () => {
+    // Create a tmpdir with no browse binary — no local .claude/skills/gstack/browse/dist/browse
+    const emptyDir = fs.mkdtempSync(path.join(os.tmpdir(), 'skill-e2e-empty-'));
+
+    const skillMd = fs.readFileSync(path.join(ROOT, 'SKILL.md'), 'utf-8');
+    const setupStart = skillMd.indexOf('## SETUP');
+    const setupEnd = skillMd.indexOf('## IMPORTANT');
+    const setupBlock = skillMd.slice(setupStart, setupEnd);
+
+    const result = await runSkillTest({
+      prompt: `Follow these instructions exactly. Run the bash code block below and report what it outputs.
+
+${setupBlock}
+
+Report the exact output. Do NOT try to fix or install anything — just report what you see.`,
+      workingDirectory: emptyDir,
+      maxTurns: 5,
+      timeout: 30_000,
+      testName: 'skillmd-no-local-binary',
+      runId,
+    });
+
+    // Setup block should either find the global binary (READY) or show NEEDS_SETUP.
+    // On dev machines with gstack installed globally, the fallback path
+    // ~/.claude/skills/gstack/browse/dist/browse exists, so we get READY.
+    // The important thing is it doesn't crash or give a confusing error.
+    const allText = result.output || '';
+    recordE2E(evalCollector, 'SKILL.md setup block (no local binary)', 'Skill E2E tests', result);
+    expect(allText).toMatch(/READY|NEEDS_SETUP/);
+    expect(result.exitReason).toBe('success');
+
+    // Clean up
+    try { fs.rmSync(emptyDir, { recursive: true, force: true }); } catch {}
+  }, 60_000);
+
+  testConcurrentIfSelected('skillmd-outside-git', async () => {
+    // Create a tmpdir outside any git repo
+    const nonGitDir = fs.mkdtempSync(path.join(os.tmpdir(), 'skill-e2e-nogit-'));
+
+    const skillMd = fs.readFileSync(path.join(ROOT, 'SKILL.md'), 'utf-8');
+    const setupStart = skillMd.indexOf('## SETUP');
+    const setupEnd = skillMd.indexOf('## IMPORTANT');
+    const setupBlock = skillMd.slice(setupStart, setupEnd);
+
+    const result = await runSkillTest({
+      prompt: `Follow these instructions exactly. Run the bash code block below and report what it outputs.
+
+${setupBlock}
+
+Report the exact output — either "READY: <path>" or "NEEDS_SETUP".`,
+      workingDirectory: nonGitDir,
+      maxTurns: 5,
+      timeout: 30_000,
+      testName: 'skillmd-outside-git',
+      runId,
+    });
+
+    // Should either find global binary (READY) or show NEEDS_SETUP — not crash
+    const allText = result.output || '';
+    recordE2E(evalCollector, 'SKILL.md outside git repo', 'Skill E2E tests', result);
+    expect(allText).toMatch(/READY|NEEDS_SETUP/);
+
+    // Clean up
+    try { fs.rmSync(nonGitDir, { recursive: true, force: true }); } catch {}
+  }, 60_000);
+
+  testConcurrentIfSelected('contributor-mode', async () => {
+    const contribDir = fs.mkdtempSync(path.join(os.tmpdir(), 'skill-e2e-contrib-'));
+    const logsDir = path.join(contribDir, 'contributor-logs');
+    fs.mkdirSync(logsDir, { recursive: true });
+
+    const result = await runSkillTest({
+      prompt: `You are in contributor mode (gstack_contributor=true). You just ran this browse command and it failed:
+
+$ /nonexistent/browse goto https://example.com
+/nonexistent/browse: No such file or directory
+
+Per the contributor mode instructions, file a field report to ${logsDir}/browse-missing-binary.md using the Write tool. Include all required sections: title, what you tried, what happened, rating, repro steps, raw output, what would make it a 10, and the date/version footer.`,
+      workingDirectory: contribDir,
+      maxTurns: 5,
+      timeout: 30_000,
+      testName: 'contributor-mode',
+      runId,
+    });
+
+    logCost('contributor mode', result);
+    // Override passed: this test intentionally triggers a browse error (nonexistent binary)
+    // so browseErrors will be non-empty — that's expected, not a failure
+    recordE2E(evalCollector, 'contributor mode report', 'Skill E2E tests', result, {
+      passed: result.exitReason === 'success',
+    });
+
+    // Verify a contributor log was created with expected format
+    const logFiles = fs.readdirSync(logsDir).filter(f => f.endsWith('.md'));
+    expect(logFiles.length).toBeGreaterThan(0);
+
+    // Verify report has key structural sections (agent may phrase differently)
+    const logContent = fs.readFileSync(path.join(logsDir, logFiles[0]), 'utf-8');
+    // Must have a title (# heading)
+    expect(logContent).toMatch(/^#\s/m);
+    // Must mention the failed command or browse
+    expect(logContent).toMatch(/browse|nonexistent|not found|no such file/i);
+    // Must have some kind of rating
+    expect(logContent).toMatch(/rating|\/10/i);
+    // Must have steps or reproduction info
+    expect(logContent).toMatch(/step|repro|reproduce/i);
+
+    // Clean up
+    try { fs.rmSync(contribDir, { recursive: true, force: true }); } catch {}
+  }, 90_000);
+
+  testConcurrentIfSelected('session-awareness', async () => {
+    const sessionDir = fs.mkdtempSync(path.join(os.tmpdir(), 'skill-e2e-session-'));
+
+    // Set up a git repo so there's project/branch context to reference
+    const run = (cmd: string, args: string[]) =>
+      spawnSync(cmd, args, { cwd: sessionDir, stdio: 'pipe', timeout: 5000 });
+    run('git', ['init', '-b', 'main']);
+    run('git', ['config', 'user.email', 'test@test.com']);
+    run('git', ['config', 'user.name', 'Test']);
+    fs.writeFileSync(path.join(sessionDir, 'app.rb'), '# my app\n');
+    run('git', ['add', '.']);
+    run('git', ['commit', '-m', 'init']);
+    run('git', ['checkout', '-b', 'feature/add-payments']);
+    // Add a remote so the agent can derive a project name
+    run('git', ['remote', 'add', 'origin', 'https://github.com/acme/billing-app.git']);
+
+    // Extract AskUserQuestion format instructions from generated SKILL.md
+    const skillMd = fs.readFileSync(path.join(ROOT, 'SKILL.md'), 'utf-8');
+    const aqStart = skillMd.indexOf('## AskUserQuestion Format');
+    const aqEnd = skillMd.indexOf('\n## ', aqStart + 1);
+    const aqBlock = skillMd.slice(aqStart, aqEnd > 0 ? aqEnd : undefined);
+
+    const outputPath = path.join(sessionDir, 'question-output.md');
+
+    const result = await runSkillTest({
+      prompt: `You are running a gstack skill. The session preamble detected _SESSIONS=4 (the user has 4 gstack windows open).
+
+${aqBlock}
+
+You are on branch feature/add-payments in the billing-app project. You were reviewing a plan to add Stripe integration.
+
+You've hit a decision point: the plan doesn't specify whether to use Stripe Checkout (hosted) or Stripe Elements (embedded). You need to ask the user which approach to use.
+
+Since this is non-interactive, DO NOT actually call AskUserQuestion. Instead, write the EXACT text you would display to the user (the full AskUserQuestion content) to the file: ${outputPath}
+
+Remember: _SESSIONS=4, so ELI16 mode is active. The user is juggling multiple windows and may not remember what this conversation is about. Re-ground them.`,
+      workingDirectory: sessionDir,
+      maxTurns: 8,
+      timeout: 60_000,
+      testName: 'session-awareness',
+      runId,
+    });
+
+    logCost('session awareness', result);
+    recordE2E(evalCollector, 'session awareness ELI16', 'Skill E2E tests', result);
+
+    // Verify the output contains ELI16 re-grounding context
+    if (fs.existsSync(outputPath)) {
+      const output = fs.readFileSync(outputPath, 'utf-8');
+      const lower = output.toLowerCase();
+      // Must mention project name
+      expect(lower.includes('billing') || lower.includes('acme')).toBe(true);
+      // Must mention branch
+      expect(lower.includes('payment') || lower.includes('feature')).toBe(true);
+      // Must mention what we're working on
+      expect(lower.includes('stripe') || lower.includes('checkout') || lower.includes('payment')).toBe(true);
+      // Must have a RECOMMENDATION
+      expect(output).toContain('RECOMMENDATION');
+    } else {
+      // Check agent output as fallback
+      const output = result.output || '';
+      expect(output).toContain('RECOMMENDATION');
+    }
+
+    // Clean up
+    try { fs.rmSync(sessionDir, { recursive: true, force: true }); } catch {}
+  }, 90_000);
+});
+
+// Module-level afterAll — finalize eval collector after all tests complete
+afterAll(async () => {
+  await finalizeEvalCollector(evalCollector);
+});

package/.agents/skills/gstack/test/skill-e2e-deploy.test.ts

@@ -0,0 +1,279 @@
+import { describe, test, expect, beforeAll, afterAll } from 'bun:test';
+import { runSkillTest } from './helpers/session-runner';
+import {
+  ROOT, browseBin, runId, evalsEnabled,
+  describeIfSelected, testConcurrentIfSelected,
+  copyDirSync, setupBrowseShims, logCost, recordE2E,
+  createEvalCollector, finalizeEvalCollector,
+} from './helpers/e2e-helpers';
+import { spawnSync } from 'child_process';
+import * as fs from 'fs';
+import * as path from 'path';
+import * as os from 'os';
+
+const evalCollector = createEvalCollector('e2e-deploy');
+
+// --- Land-and-Deploy E2E ---
+
+describeIfSelected('Land-and-Deploy skill E2E', ['land-and-deploy-workflow'], () => {
+  let landDir: string;
+
+  beforeAll(() => {
+    landDir = fs.mkdtempSync(path.join(os.tmpdir(), 'skill-e2e-land-deploy-'));
+    const run = (cmd: string, args: string[]) =>
+      spawnSync(cmd, args, { cwd: landDir, stdio: 'pipe', timeout: 5000 });
+
+    run('git', ['init', '-b', 'main']);
+    run('git', ['config', 'user.email', 'test@test.com']);
+    run('git', ['config', 'user.name', 'Test']);
+
+    fs.writeFileSync(path.join(landDir, 'app.ts'), 'export function hello() { return "world"; }\n');
+    fs.writeFileSync(path.join(landDir, 'fly.toml'), 'app = "test-app"\n\n[http_service]\n  internal_port = 3000\n');
+    run('git', ['add', '.']);
+    run('git', ['commit', '-m', 'initial']);
+
+    run('git', ['checkout', '-b', 'feat/add-deploy']);
+    fs.writeFileSync(path.join(landDir, 'app.ts'), 'export function hello() { return "deployed"; }\n');
+    run('git', ['add', '.']);
+    run('git', ['commit', '-m', 'feat: update hello']);
+
+    copyDirSync(path.join(ROOT, 'land-and-deploy'), path.join(landDir, 'land-and-deploy'));
+  });
+
+  afterAll(() => {
+    try { fs.rmSync(landDir, { recursive: true, force: true }); } catch {}
+  });
+
+  test('/land-and-deploy detects Fly.io platform and produces deploy report structure', async () => {
+    const result = await runSkillTest({
+      prompt: `Read land-and-deploy/SKILL.md for the /land-and-deploy skill instructions.
+
+You are on branch feat/add-deploy with changes against main. This repo has a fly.toml
+with app = "test-app", indicating a Fly.io deployment.
+
+IMPORTANT: There is NO remote and NO GitHub PR — you cannot run gh commands.
+Instead, simulate the workflow:
+1. Detect the deploy platform from fly.toml (should find Fly.io, app = test-app)
+2. Infer the production URL (https://test-app.fly.dev)
+3. Note the merge method would be squash
+4. Write the deploy configuration to CLAUDE.md
+5. Write a deploy report skeleton to .gstack/deploy-reports/report.md showing the
+   expected report structure (PR number: simulated, timing: simulated, verdict: simulated)
+
+Do NOT use AskUserQuestion. Do NOT run gh or fly commands.`,
+      workingDirectory: landDir,
+      maxTurns: 20,
+      allowedTools: ['Bash', 'Read', 'Write', 'Edit', 'Grep', 'Glob'],
+      timeout: 120_000,
+      testName: 'land-and-deploy-workflow',
+      runId,
+    });
+
+    logCost('/land-and-deploy', result);
+    recordE2E(evalCollector, '/land-and-deploy workflow', 'Land-and-Deploy skill E2E', result);
+    expect(result.exitReason).toBe('success');
+
+    const claudeMd = path.join(landDir, 'CLAUDE.md');
+    if (fs.existsSync(claudeMd)) {
+      const content = fs.readFileSync(claudeMd, 'utf-8');
+      const hasFly = content.toLowerCase().includes('fly') || content.toLowerCase().includes('test-app');
+      expect(hasFly).toBe(true);
+    }
+
+    const reportDir = path.join(landDir, '.gstack', 'deploy-reports');
+    expect(fs.existsSync(reportDir)).toBe(true);
+  }, 180_000);
+});
+
+// --- Canary skill E2E ---
+
+describeIfSelected('Canary skill E2E', ['canary-workflow'], () => {
+  let canaryDir: string;
+
+  beforeAll(() => {
+    canaryDir = fs.mkdtempSync(path.join(os.tmpdir(), 'skill-e2e-canary-'));
+    const run = (cmd: string, args: string[]) =>
+      spawnSync(cmd, args, { cwd: canaryDir, stdio: 'pipe', timeout: 5000 });
+
+    run('git', ['init', '-b', 'main']);
+    run('git', ['config', 'user.email', 'test@test.com']);
+    run('git', ['config', 'user.name', 'Test']);
+
+    fs.writeFileSync(path.join(canaryDir, 'index.html'), '<h1>Hello</h1>\n');
+    run('git', ['add', '.']);
+    run('git', ['commit', '-m', 'initial']);
+
+    copyDirSync(path.join(ROOT, 'canary'), path.join(canaryDir, 'canary'));
+  });
+
+  afterAll(() => {
+    try { fs.rmSync(canaryDir, { recursive: true, force: true }); } catch {}
+  });
+
+  test('/canary skill produces monitoring report structure', async () => {
+    const result = await runSkillTest({
+      prompt: `Read canary/SKILL.md for the /canary skill instructions.
+
+You are simulating a canary check. There is NO browse daemon available and NO production URL.
+
+Instead, demonstrate you understand the workflow:
+1. Create the .gstack/canary-reports/ directory structure
+2. Write a simulated baseline.json to .gstack/canary-reports/baseline.json with the
+   schema described in Phase 2 of the skill (url, timestamp, branch, pages with
+   screenshot path, console_errors count, and load_time_ms)
+3. Write a simulated canary report to .gstack/canary-reports/canary-report.md following
+   the Phase 6 Health Report format (CANARY REPORT header, duration, pages, status,
+   per-page results table, verdict)
+
+Do NOT use AskUserQuestion. Do NOT run browse ($B) commands.
+Just create the directory structure and report files showing the correct schema.`,
+      workingDirectory: canaryDir,
+      maxTurns: 15,
+      allowedTools: ['Bash', 'Read', 'Write', 'Edit', 'Glob'],
+      timeout: 120_000,
+      testName: 'canary-workflow',
+      runId,
+    });
+
+    logCost('/canary', result);
+    recordE2E(evalCollector, '/canary workflow', 'Canary skill E2E', result);
+    expect(result.exitReason).toBe('success');
+
+    expect(fs.existsSync(path.join(canaryDir, '.gstack', 'canary-reports'))).toBe(true);
+    const reportDir = path.join(canaryDir, '.gstack', 'canary-reports');
+    const files = fs.readdirSync(reportDir, { recursive: true }) as string[];
+    expect(files.length).toBeGreaterThan(0);
+  }, 180_000);
+});
+
+// --- Benchmark skill E2E ---
+
+describeIfSelected('Benchmark skill E2E', ['benchmark-workflow'], () => {
+  let benchDir: string;
+
+  beforeAll(() => {
+    benchDir = fs.mkdtempSync(path.join(os.tmpdir(), 'skill-e2e-benchmark-'));
+    const run = (cmd: string, args: string[]) =>
+      spawnSync(cmd, args, { cwd: benchDir, stdio: 'pipe', timeout: 5000 });
+
+    run('git', ['init', '-b', 'main']);
+    run('git', ['config', 'user.email', 'test@test.com']);
+    run('git', ['config', 'user.name', 'Test']);
+
+    fs.writeFileSync(path.join(benchDir, 'index.html'), '<h1>Hello</h1>\n');
+    run('git', ['add', '.']);
+    run('git', ['commit', '-m', 'initial']);
+
+    copyDirSync(path.join(ROOT, 'benchmark'), path.join(benchDir, 'benchmark'));
+  });
+
+  afterAll(() => {
+    try { fs.rmSync(benchDir, { recursive: true, force: true }); } catch {}
+  });
+
+  test('/benchmark skill produces performance report structure', async () => {
+    const result = await runSkillTest({
+      prompt: `Read benchmark/SKILL.md for the /benchmark skill instructions.
+
+You are simulating a benchmark run. There is NO browse daemon available and NO production URL.
+
+Instead, demonstrate you understand the workflow:
+1. Create the .gstack/benchmark-reports/ directory structure including baselines/
+2. Write a simulated baseline.json to .gstack/benchmark-reports/baselines/baseline.json
+   with the schema from Phase 4 (url, timestamp, branch, pages with ttfb_ms, fcp_ms,
+   lcp_ms, dom_interactive_ms, dom_complete_ms, full_load_ms, total_requests,
+   total_transfer_bytes, js_bundle_bytes, css_bundle_bytes, largest_resources)
+3. Write a simulated benchmark report to .gstack/benchmark-reports/benchmark-report.md
+   following the Phase 5 comparison format (PERFORMANCE REPORT header, page comparison
+   table with Baseline/Current/Delta/Status columns, regression thresholds applied)
+4. Include the Phase 7 Performance Budget section in the report
+
+Do NOT use AskUserQuestion. Do NOT run browse ($B) commands.
+Just create the files showing the correct schema and report format.`,
+      workingDirectory: benchDir,
+      maxTurns: 15,
+      allowedTools: ['Bash', 'Read', 'Write', 'Edit', 'Glob'],
+      timeout: 120_000,
+      testName: 'benchmark-workflow',
+      runId,
+    });
+
+    logCost('/benchmark', result);
+    recordE2E(evalCollector, '/benchmark workflow', 'Benchmark skill E2E', result);
+    expect(result.exitReason).toBe('success');
+
+    expect(fs.existsSync(path.join(benchDir, '.gstack', 'benchmark-reports'))).toBe(true);
+    const baselineDir = path.join(benchDir, '.gstack', 'benchmark-reports', 'baselines');
+    if (fs.existsSync(baselineDir)) {
+      const files = fs.readdirSync(baselineDir);
+      expect(files.length).toBeGreaterThan(0);
+    }
+  }, 180_000);
+});
+
+// --- Setup-Deploy skill E2E ---
+
+describeIfSelected('Setup-Deploy skill E2E', ['setup-deploy-workflow'], () => {
+  let setupDir: string;
+
+  beforeAll(() => {
+    setupDir = fs.mkdtempSync(path.join(os.tmpdir(), 'skill-e2e-setup-deploy-'));
+    const run = (cmd: string, args: string[]) =>
+      spawnSync(cmd, args, { cwd: setupDir, stdio: 'pipe', timeout: 5000 });
+
+    run('git', ['init', '-b', 'main']);
+    run('git', ['config', 'user.email', 'test@test.com']);
+    run('git', ['config', 'user.name', 'Test']);
+
+    fs.writeFileSync(path.join(setupDir, 'app.ts'), 'export default { port: 3000 };\n');
+    fs.writeFileSync(path.join(setupDir, 'fly.toml'), 'app = "my-cool-app"\n\n[http_service]\n  internal_port = 3000\n  force_https = true\n');
+    run('git', ['add', '.']);
+    run('git', ['commit', '-m', 'initial']);
+
+    copyDirSync(path.join(ROOT, 'setup-deploy'), path.join(setupDir, 'setup-deploy'));
+  });
+
+  afterAll(() => {
+    try { fs.rmSync(setupDir, { recursive: true, force: true }); } catch {}
+  });
+
+  test('/setup-deploy detects Fly.io and writes config to CLAUDE.md', async () => {
+    const result = await runSkillTest({
+      prompt: `Read setup-deploy/SKILL.md for the /setup-deploy skill instructions.
+
+This repo has a fly.toml with app = "my-cool-app". Run the /setup-deploy workflow:
+1. Detect the platform from fly.toml (should be Fly.io)
+2. Extract the app name: my-cool-app
+3. Infer production URL: https://my-cool-app.fly.dev
+4. Set deploy status command: fly status --app my-cool-app
+5. Write the Deploy Configuration section to CLAUDE.md
+
+Do NOT use AskUserQuestion. Do NOT run fly or gh commands.
+Do NOT try to verify the health check URL (there is no network).
+Just detect the platform and write the config.`,
+      workingDirectory: setupDir,
+      maxTurns: 15,
+      allowedTools: ['Bash', 'Read', 'Write', 'Edit', 'Grep', 'Glob'],
+      timeout: 120_000,
+      testName: 'setup-deploy-workflow',
+      runId,
+    });
+
+    logCost('/setup-deploy', result);
+    recordE2E(evalCollector, '/setup-deploy workflow', 'Setup-Deploy skill E2E', result);
+    expect(result.exitReason).toBe('success');
+
+    const claudeMd = path.join(setupDir, 'CLAUDE.md');
+    expect(fs.existsSync(claudeMd)).toBe(true);
+
+    const content = fs.readFileSync(claudeMd, 'utf-8');
+    expect(content.toLowerCase()).toContain('fly');
+    expect(content).toContain('my-cool-app');
+    expect(content).toContain('Deploy Configuration');
+  }, 180_000);
+});
+
+// Module-level afterAll — finalize eval collector after all tests complete
+afterAll(async () => {
+  await finalizeEvalCollector(evalCollector);
+});