umairinayat/Specter-AI / .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.
| File | Kind | Size |
|---|---|---|
| .env.example | other | 171 B |
| .github/workflows/skill-docs.yml | config | 365 B |
| .gitignore | other | 127 B |
| ARCHITECTURE.md | markdown | 13.9 KB |
| BROWSER.md | markdown | 13.8 KB |
| CHANGELOG.md | markdown | 14.0 KB |
| CONTRIBUTING.md | markdown | 10.2 KB |
| LICENSE | other | 1.0 KB |
| README.md | markdown | 29.2 KB |
| SKILL.md | skill md | 12.5 KB |
| SKILL.md.tmpl | other | 6.1 KB |
| TODO.md | markdown | 6.9 KB |
| TODOS.md | markdown | 1.8 KB |
| VERSION | other | 6 B |
| bin/dev-setup | other | 1.9 KB |
| bin/dev-teardown | other | 946 B |
| bin/gstack-update-check | other | 3.0 KB |
| conductor.json | config | 87 B |
| package.json | manifest | 1.6 KB |
| scripts/dev-skill.ts | script | 2.4 KB |
| scripts/gen-skill-docs.ts | script | 7.6 KB |
| scripts/skill-check.ts | script | 3.7 KB |
| setup | other | 2.8 KB |
| test/gen-skill-docs.test.ts | script | 6.2 KB |
| test/helpers/session-runner.ts | script | 5.0 KB |
| test/helpers/skill-parser.ts | script | 3.4 KB |
| test/skill-e2e.test.ts | script | 6.2 KB |
| test/skill-llm-eval.test.ts | script | 8.2 KB |
| test/skill-parser.test.ts | script | 5.3 KB |
| test/skill-validation.test.ts | script | 5.9 KB |
test/helpers/session-runner.ts
View on GitHub/**
* Agent SDK wrapper for skill E2E testing.
*
* Spawns a Claude Code session, runs a prompt, collects messages,
* scans tool_result messages for browse errors.
*/
import { query } from '@anthropic-ai/claude-agent-sdk';
import * as fs from 'fs';
import * as path from 'path';
export interface SkillTestResult {
messages: any[];
toolCalls: Array<{ tool: string; input: any; output: string }>;
browseErrors: string[];
exitReason: string;
duration: number;
}
const BROWSE_ERROR_PATTERNS = [
/Unknown command: \w+/,
/Unknown snapshot flag: .+/,
/Exit code 1/,
/ERROR: browse binary not found/,
/Server failed to start/,
/no such file or directory.*browse/i,
];
export async function runSkillTest(options: {
prompt: string;
workingDirectory: string;
maxTurns?: number;
allowedTools?: string[];
timeout?: number;
}): Promise<SkillTestResult> {
// Fail fast if running inside an Agent SDK session — nested sessions hang
if (process.env.CLAUDECODE || process.env.CLAUDE_CODE_ENTRYPOINT) {
throw new Error(
'Cannot run E2E skill tests inside a Claude Code session. ' +
'Run from a plain terminal: SKILL_E2E=1 bun test test/skill-e2e.test.ts'
);
}
const {
prompt,
workingDirectory,
maxTurns = 15,
allowedTools = ['Bash', 'Read', 'Write'],
timeout = 120_000,
} = options;
const messages: any[] = [];
const toolCalls: SkillTestResult['toolCalls'] = [];
const browseErrors: string[] = [];
let exitReason = 'unknown';
const startTime = Date.now();
// Strip all Claude-related env vars to allow nested sessions.
// Without this, the child claude process thinks it's an SDK child
// and hangs waiting for parent IPC instead of running independently.
const env: Record<string, string | undefined> = {};
for (const [key] of Object.entries(process.env)) {
if (key.startsWith('CLAUDE') || key.startsWith('CLAUDECODE')) {
env[key] = undefined;
}
}
const q = query({
prompt,
options: {
cwd: workingDirectory,
allowedTools,
permissionMode: 'bypassPermissions',
allowDangerouslySkipPermissions: true,
maxTurns,
env,
},
});
const timeoutPromise = new Promise<never>((_, reject) => {
setTimeout(() => reject(new Error(`Skill test timed out after ${timeout}ms`)), timeout);
});
try {
const runner = (async () => {
for await (const msg of q) {
messages.push(msg);
// Extract tool calls from assistant messages
if (msg.type === 'assistant' && msg.message?.content) {
for (const block of msg.message.content) {
if (block.type === 'tool_use') {
toolCalls.push({
tool: block.name,
input: block.input,
output: '', // will be filled from tool_result
});
}
// Scan tool_result blocks for browse errors
if (block.type === 'tool_result' || (typeof block === 'object' && 'text' in block)) {
const text = typeof block === 'string' ? block : (block as any).text || '';
for (const pattern of BROWSE_ERROR_PATTERNS) {
if (pattern.test(text)) {
browseErrors.push(text.slice(0, 200));
}
}
}
}
}
// Also scan user messages (which contain tool results)
if (msg.type === 'user' && msg.message?.content) {
const content = Array.isArray(msg.message.content) ? msg.message.content : [msg.message.content];
for (const block of content) {
const text = typeof block === 'string' ? block : (block as any)?.text || (block as any)?.content || '';
if (typeof text === 'string') {
for (const pattern of BROWSE_ERROR_PATTERNS) {
if (pattern.test(text)) {
browseErrors.push(text.slice(0, 200));
}
}
}
}
}
// Capture result
if (msg.type === 'result') {
exitReason = msg.subtype || 'success';
}
}
})();
await Promise.race([runner, timeoutPromise]);
} catch (err: any) {
exitReason = err.message?.includes('timed out') ? 'timeout' : `error: ${err.message}`;
}
const duration = Date.now() - startTime;
// Save transcript on failure
if (browseErrors.length > 0 || exitReason !== 'success') {
try {
const transcriptDir = path.join(workingDirectory, '.gstack', 'test-transcripts');
fs.mkdirSync(transcriptDir, { recursive: true });
const timestamp = new Date().toISOString().replace(/[:.]/g, '-');
const transcriptPath = path.join(transcriptDir, `e2e-${timestamp}.json`);
fs.writeFileSync(transcriptPath, JSON.stringify({
prompt,
exitReason,
browseErrors,
duration,
messages: messages.map(m => ({ type: m.type, subtype: m.subtype })),
}, null, 2));
} catch {
// Transcript save failures are non-fatal
}
}
return { messages, toolCalls, browseErrors, exitReason, duration };
}
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| finishing-a-development-branchobra/superpowersUse when implementation is complete, all tests pass, and you need to decide how to integrate the work | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| systematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| test-driven-developmentobra/superpowersUse when implementing any feature or bugfix, before writing implementation code | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| skill-creatoranthropics/skillsCreate new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |