Skip to content

umairinayat/Specter-AI / .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.

FileKindSize
.env.exampleother171 B
.github/workflows/skill-docs.ymlconfig365 B
.gitignoreother127 B
ARCHITECTURE.mdmarkdown13.9 KB
BROWSER.mdmarkdown13.8 KB
CHANGELOG.mdmarkdown14.0 KB
CONTRIBUTING.mdmarkdown10.2 KB
LICENSEother1.0 KB
README.mdmarkdown29.2 KB
SKILL.mdskill md12.5 KB
SKILL.md.tmplother6.1 KB
TODO.mdmarkdown6.9 KB
TODOS.mdmarkdown1.8 KB
VERSIONother6 B
bin/dev-setupother1.9 KB
bin/dev-teardownother946 B
bin/gstack-update-checkother3.0 KB
conductor.jsonconfig87 B
package.jsonmanifest1.6 KB
scripts/dev-skill.tsscript2.4 KB
scripts/gen-skill-docs.tsscript7.6 KB
scripts/skill-check.tsscript3.7 KB
setupother2.8 KB
test/gen-skill-docs.test.tsscript6.2 KB
test/helpers/session-runner.tsscript5.0 KB
test/helpers/skill-parser.tsscript3.4 KB
test/skill-e2e.test.tsscript6.2 KB
test/skill-llm-eval.test.tsscript8.2 KB
test/skill-parser.test.tsscript5.3 KB
test/skill-validation.test.tsscript5.9 KB

test/skill-validation.test.ts

View on GitHub
import { describe, test, expect } from 'bun:test';
import { validateSkill } from './helpers/skill-parser';
import { ALL_COMMANDS, COMMAND_DESCRIPTIONS, READ_COMMANDS, WRITE_COMMANDS, META_COMMANDS } from '../browse/src/commands';
import { SNAPSHOT_FLAGS } from '../browse/src/snapshot';
import * as fs from 'fs';
import * as path from 'path';

const ROOT = path.resolve(import.meta.dir, '..');

describe('SKILL.md command validation', () => {
  test('all $B commands in SKILL.md are valid browse commands', () => {
    const result = validateSkill(path.join(ROOT, 'SKILL.md'));
    expect(result.invalid).toHaveLength(0);
    expect(result.valid.length).toBeGreaterThan(0);
  });

  test('all snapshot flags in SKILL.md are valid', () => {
    const result = validateSkill(path.join(ROOT, 'SKILL.md'));
    expect(result.snapshotFlagErrors).toHaveLength(0);
  });

  test('all $B commands in browse/SKILL.md are valid browse commands', () => {
    const result = validateSkill(path.join(ROOT, 'browse', 'SKILL.md'));
    expect(result.invalid).toHaveLength(0);
    expect(result.valid.length).toBeGreaterThan(0);
  });

  test('all snapshot flags in browse/SKILL.md are valid', () => {
    const result = validateSkill(path.join(ROOT, 'browse', 'SKILL.md'));
    expect(result.snapshotFlagErrors).toHaveLength(0);
  });

  test('all $B commands in qa/SKILL.md are valid browse commands', () => {
    const qaSkill = path.join(ROOT, 'qa', 'SKILL.md');
    if (!fs.existsSync(qaSkill)) return; // skip if missing
    const result = validateSkill(qaSkill);
    expect(result.invalid).toHaveLength(0);
  });

  test('all snapshot flags in qa/SKILL.md are valid', () => {
    const qaSkill = path.join(ROOT, 'qa', 'SKILL.md');
    if (!fs.existsSync(qaSkill)) return;
    const result = validateSkill(qaSkill);
    expect(result.snapshotFlagErrors).toHaveLength(0);
  });
});

describe('Command registry consistency', () => {
  test('COMMAND_DESCRIPTIONS covers all commands in sets', () => {
    const allCmds = new Set([...READ_COMMANDS, ...WRITE_COMMANDS, ...META_COMMANDS]);
    const descKeys = new Set(Object.keys(COMMAND_DESCRIPTIONS));
    for (const cmd of allCmds) {
      expect(descKeys.has(cmd)).toBe(true);
    }
  });

  test('COMMAND_DESCRIPTIONS has no extra commands not in sets', () => {
    const allCmds = new Set([...READ_COMMANDS, ...WRITE_COMMANDS, ...META_COMMANDS]);
    for (const key of Object.keys(COMMAND_DESCRIPTIONS)) {
      expect(allCmds.has(key)).toBe(true);
    }
  });

  test('ALL_COMMANDS matches union of all sets', () => {
    const union = new Set([...READ_COMMANDS, ...WRITE_COMMANDS, ...META_COMMANDS]);
    expect(ALL_COMMANDS.size).toBe(union.size);
    for (const cmd of union) {
      expect(ALL_COMMANDS.has(cmd)).toBe(true);
    }
  });

  test('SNAPSHOT_FLAGS option keys are valid SnapshotOptions fields', () => {
    const validKeys = new Set([
      'interactive', 'compact', 'depth', 'selector',
      'diff', 'annotate', 'outputPath', 'cursorInteractive',
    ]);
    for (const flag of SNAPSHOT_FLAGS) {
      expect(validKeys.has(flag.optionKey)).toBe(true);
    }
  });
});

describe('Usage string consistency', () => {
  // Normalize a usage string to its structural skeleton for comparison.
  // Replaces <param-names> with <>, [optional] with [], strips parenthetical hints.
  // This catches format mismatches (e.g., <name>:<value> vs <name> <value>)
  // without tripping on abbreviation differences (e.g., <sel> vs <selector>).
  function skeleton(usage: string): string {
    return usage
      .replace(/\(.*?\)/g, '')        // strip parenthetical hints like (e.g., Enter, Tab)
      .replace(/<[^>]*>/g, '<>')      // normalize <param-name> → <>
      .replace(/\[[^\]]*\]/g, '[]')   // normalize [optional] → []
      .replace(/\s+/g, ' ')           // collapse whitespace
      .trim();
  }

  // Cross-check Usage: patterns in implementation against COMMAND_DESCRIPTIONS
  test('implementation Usage: structural format matches COMMAND_DESCRIPTIONS', () => {
    const implFiles = [
      path.join(ROOT, 'browse', 'src', 'write-commands.ts'),
      path.join(ROOT, 'browse', 'src', 'read-commands.ts'),
      path.join(ROOT, 'browse', 'src', 'meta-commands.ts'),
    ];

    // Extract "Usage: browse <pattern>" from throw new Error(...) calls
    const usagePattern = /throw new Error\(['"`]Usage:\s*browse\s+(.+?)['"`]\)/g;
    const implUsages = new Map<string, string>();

    for (const file of implFiles) {
      const content = fs.readFileSync(file, 'utf-8');
      let match;
      while ((match = usagePattern.exec(content)) !== null) {
        const usage = match[1].split('\\n')[0].trim();
        const cmd = usage.split(/\s/)[0];
        implUsages.set(cmd, usage);
      }
    }

    // Compare structural skeletons
    const mismatches: string[] = [];
    for (const [cmd, implUsage] of implUsages) {
      const desc = COMMAND_DESCRIPTIONS[cmd];
      if (!desc) continue;
      if (!desc.usage) continue;
      const descSkel = skeleton(desc.usage);
      const implSkel = skeleton(implUsage);
      if (descSkel !== implSkel) {
        mismatches.push(`${cmd}: docs "${desc.usage}" (${descSkel}) vs impl "${implUsage}" (${implSkel})`);
      }
    }

    expect(mismatches).toEqual([]);
  });
});

describe('Generated SKILL.md freshness', () => {
  test('no unresolved {{placeholders}} in generated SKILL.md', () => {
    const content = fs.readFileSync(path.join(ROOT, 'SKILL.md'), 'utf-8');
    const unresolved = content.match(/\{\{\w+\}\}/g);
    expect(unresolved).toBeNull();
  });

  test('no unresolved {{placeholders}} in generated browse/SKILL.md', () => {
    const content = fs.readFileSync(path.join(ROOT, 'browse', 'SKILL.md'), 'utf-8');
    const unresolved = content.match(/\{\{\w+\}\}/g);
    expect(unresolved).toBeNull();
  });

  test('generated SKILL.md has AUTO-GENERATED header', () => {
    const content = fs.readFileSync(path.join(ROOT, 'SKILL.md'), 'utf-8');
    expect(content).toContain('AUTO-GENERATED');
  });
});
finishing-a-development-branchobra/superpowersUse when implementation is complete, all tests pass, and you need to decide how to integrate the workStars: 322kUpdated Claude CodeCodexVerifiedInstall
systematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixesStars: 322kUpdated Claude CodeCodexVerifiedInstall
test-driven-developmentobra/superpowersUse when implementing any feature or bugfix, before writing implementation codeStars: 322kUpdated Claude CodeCodexVerifiedInstall
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: 198kUpdated Claude CodeCodexVerifiedInstall