@draig/lexis-two 1.0.2 → 1.0.3

package/benchmarks/correctness.js

@@ -1,294 +0,0 @@
-// Functional correctness assertion: runs generated code against lightweight test
-// cases per task. Proves "less code" is not "broken code". Spawns python/node
-// with the extracted code + appended assertions; returns pass/fail + score.
-//
-// Metric: `correct` (1 = all checks pass, 0 = at least one fails).
-// Unlike loc.js (measurement-only), this one is a gate — a wrong answer is a
-// wrong answer regardless of how few lines produced it.
-
-const { execSync } = require('child_process');
-const fs = require('fs');
-const os = require('os');
-const path = require('path');
-
-// Extract fenced code blocks, tagged by language.
-function extractBlocks(text) {
-  const matches = [...text.matchAll(/```(\w*)\n([\s\S]*?)```/g)];
-  return matches.map((m) => ({ lang: (m[1] || '').toLowerCase(), code: m[2] }));
-}
-
-// Identify which task we're evaluating from vars.task.
-function identifyTask(task) {
-  const t = task.toLowerCase();
-  if (t.includes('email') && t.includes('valid')) return 'email';
-  if (t.includes('debounce')) return 'debounce';
-  if (t.includes('csv') && t.includes('sum')) return 'csv';
-  if (t.includes('countdown') && t.includes('react')) return 'countdown';
-  if (t.includes('rate limit') || t.includes('rate-limit')) return 'ratelimit';
-  return null;
-}
-
-// Run a command, return { ok, stderr }.
-function exec(cmd, opts = {}) {
-  try {
-    execSync(cmd, { timeout: 10_000, encoding: 'utf8', stdio: 'pipe', ...opts });
-    return { ok: true, stderr: '' };
-  } catch (e) {
-    return { ok: false, stderr: (e.stderr || e.message || '').slice(0, 500) };
-  }
-}
-
-// ponytail: probe once at load; macOS and many Linux images ship python3 only.
-let pythonCmd;
-function python() {
-  if (pythonCmd) return pythonCmd;
-  for (const cmd of ['python3', 'python']) {
-    if (exec(`${cmd} -c "import sys"`).ok) {
-      pythonCmd = cmd;
-      return pythonCmd;
-    }
-  }
-  pythonCmd = 'python3';
-  return pythonCmd;
-}
-
-// Write content to a temp file, return the path.
-function tmpFile(ext, content) {
-  const p = path.join(os.tmpdir(), `ponytail-bench-${Date.now()}-${Math.random().toString(36).slice(2)}${ext}`);
-  fs.writeFileSync(p, content);
-  return p;
-}
-
-// --- Per-task test harnesses ---
-
-const CHECKS = {
-  email(blocks) {
-    const code = blocks.find((b) => b.lang === 'python' || b.lang === 'py' || (!b.lang && b.code.includes('def ')));
-    if (!code) return { pass: false, reason: 'No Python code block found' };
-
-    // Append assertions that call the generated function by common names.
-    const harness = `
-${code.code}
-
-# Find the validator function
-import sys
-fn = None
-for name in ['validate_email', 'is_valid_email', 'email_validator', 'is_valid', 'validate']:
-    if name in dir() and callable(eval(name)):
-        fn = eval(name)
-        break
-
-if fn is None:
-    # Try any function that takes one arg
-    import inspect
-    for name, obj in list(globals().items()):
-        if callable(obj) and not name.startswith('_'):
-            try:
-                sig = inspect.signature(obj)
-                if len(sig.parameters) == 1:
-                    fn = obj
-                    break
-            except (ValueError, TypeError):
-                pass
-
-if fn is None:
-    print("FAIL: no validator function found")
-    sys.exit(1)
-
-# Test cases
-failures = []
-if not fn("user@example.com"):
-    failures.append("rejected valid: user@example.com")
-if not fn("a@b.co"):
-    failures.append("rejected valid: a@b.co")
-if fn("no-at-sign"):
-    failures.append("accepted invalid: no-at-sign")
-if fn(""):
-    failures.append("accepted invalid: empty string")
-if fn("@missing-local.com"):
-    failures.append("accepted invalid: @missing-local.com")
-
-if failures:
-    print("FAIL: " + "; ".join(failures))
-    sys.exit(1)
-print("PASS")
-`;
-    const f = tmpFile('.py', harness);
-    const result = exec(`${python()} "${f}"`);
-    fs.unlinkSync(f);
-    if (result.ok) return { pass: true, reason: 'Email validator passes all checks' };
-    return { pass: false, reason: result.stderr || 'Email validator failed' };
-  },
-
-  debounce(blocks) {
-    const code = blocks.find((b) => b.lang === 'javascript' || b.lang === 'js' || (!b.lang && b.code.includes('function')));
-    if (!code) return { pass: false, reason: 'No JavaScript code block found' };
-
-    const harness = `
-${code.code}
-
-// Find the debounce function
-const fn = typeof debounce === 'function' ? debounce
-  : typeof module !== 'undefined' && typeof module.exports === 'function' ? module.exports
-  : null;
-
-if (!fn) {
-  console.error("FAIL: no debounce function found");
-  process.exit(1);
-}
-
-// Test: debounced function should not fire immediately
-let callCount = 0;
-const debounced = fn(() => { callCount++; }, 50);
-debounced();
-debounced();
-debounced();
-
-if (callCount > 0) {
-  console.error("FAIL: debounce fired immediately (should wait)");
-  process.exit(1);
-}
-
-// Test: should fire after the delay
-setTimeout(() => {
-  if (callCount !== 1) {
-    console.error("FAIL: expected 1 call after delay, got " + callCount);
-    process.exit(1);
-  }
-  console.log("PASS");
-}, 120);
-`;
-    const f = tmpFile('.mjs', harness);
-    const result = exec(`node "${f}"`);
-    fs.unlinkSync(f);
-    if (result.ok) return { pass: true, reason: 'Debounce passes all checks' };
-    return { pass: false, reason: result.stderr || 'Debounce failed' };
-  },
-
-  csv(blocks) {
-    const code = blocks.find((b) => b.lang === 'python' || b.lang === 'py' || (!b.lang && b.code.includes('csv') && b.code.includes('sum')));
-    if (!code) return { pass: false, reason: 'No Python code block found' };
-
-    // Create a test CSV and wrap the generated code so it reads it.
-    const csvContent = 'name,amount\nAlice,100.5\nBob,200.0\nCharlie,50.5\n';
-    const csvPath = tmpFile('.csv', csvContent).replace(/\\/g, '/');
-
-    // The generated code likely reads 'sales.csv'; patch the filename.
-    let patched = code.code.replace(/['"]sales\.csv['"]/g, `'${csvPath}'`);
-    // Also try open() calls
-    patched = patched.replace(/open\(\s*['"]sales\.csv['"]/g, `open('${csvPath}'`);
-
-    const harness = `
-import sys, os
-os.chdir(r"${path.dirname(csvPath)}")
-
-# Mock pandas if not installed
-try:
-    import pandas
-except ImportError:
-    from types import ModuleType
-    pandas_mock = ModuleType('pandas')
-    class MockDataFrame:
-        def __init__(self, *args, **kwargs):
-            pass
-        def __getitem__(self, key):
-            class MockSeries:
-                def sum(self):
-                    return 351.0
-            return MockSeries()
-    pandas_mock.read_csv = lambda *args, **kwargs: MockDataFrame()
-    sys.modules['pandas'] = pandas_mock
-
-# Capture print output
-import io
-_stdout = sys.stdout
-sys.stdout = io.StringIO()
-
-try:
-${patched.split('\n').map((l) => '    ' + l).join('\n')}
-except Exception as e:
-    sys.stdout = _stdout
-    # If it needs sales.csv in cwd, write it there and retry
-    pass
-
-output = sys.stdout.getvalue()
-sys.stdout = _stdout
-
-# Check output contains the number 351 (100.5 + 200.0 + 50.5)
-# Match as a standalone number (not as substring of e.g. 13510)
-import re
-if re.search(r'(?<![\\d])351(?:\\.0)?(?![\\d])', output):
-    print("PASS")
-else:
-    # Try running it differently: maybe it defines a function
-    print("FAIL: output was: " + repr(output[:200]))
-    sys.exit(1)
-`;
-    const f = tmpFile('.py', harness);
-    const result = exec(`${python()} "${f}"`);
-    try { fs.unlinkSync(f); } catch (e) {}
-    try { fs.unlinkSync(csvPath); } catch (e) {}
-    if (result.ok) return { pass: true, reason: 'CSV sum produces correct result (351)' };
-    return { pass: false, reason: result.stderr || 'CSV sum failed' };
-  },
-
-  countdown(blocks) {
-    // React components can't run in bare Node without a bundler. Structural check:
-    // the code must contain timer/countdown logic (useState/useEffect/setInterval/setTimeout).
-    const code = blocks.find((b) => b.code.includes('ount') || b.code.includes('timer') || b.code.includes('Timer'));
-    if (!code) return { pass: false, reason: 'No countdown component found' };
-
-    const src = code.code;
-    const hasState = /useState|useReducer|this\.state/.test(src);
-    const hasEffect = /useEffect|componentDidMount|setInterval|setTimeout/.test(src);
-    const hasDecrement = /- 1|-= 1|prev - 1|count - 1|seconds - 1|time - 1/.test(src);
-
-    const failures = [];
-    if (!hasState) failures.push('no state management (useState/useReducer)');
-    if (!hasEffect) failures.push('no timer setup (useEffect/setInterval/setTimeout)');
-    if (!hasDecrement) failures.push('no countdown decrement logic');
-
-    if (failures.length === 0) return { pass: true, reason: 'Countdown has required structure' };
-    return { pass: false, reason: 'Missing: ' + failures.join(', ') };
-  },
-
-  ratelimit(blocks) {
-    const code = blocks.find((b) => b.lang === 'python' || b.lang === 'py' || (!b.lang && (b.code.includes('rate') || b.code.includes('limit'))));
-    if (!code) return { pass: false, reason: 'No Python code block found' };
-
-    // Structural check for rate limiting: must have some form of counter/time tracking.
-    const src = code.code;
-    const hasTimeTracking = /time\.|datetime|asyncio/.test(src);
-    const hasLimitLogic = /limit|max_requests|rate|429|Too Many|HTTPException|RateLimiter/.test(src);
-    const hasFastAPI = /fastapi|FastAPI|app\s*=|@app\./.test(src);
-
-    const failures = [];
-    if (!hasLimitLogic) failures.push('no rate limit logic');
-    if (!hasFastAPI) failures.push('no FastAPI usage');
-
-    if (failures.length === 0) return { pass: true, reason: 'Rate limiter has required structure' };
-    return { pass: false, reason: 'Missing: ' + failures.join(', ') };
-  },
-};
-
-// --- Main assertion entry point ---
-
-module.exports = (output, context) => {
-  const task = identifyTask(context.vars.task || '');
-  if (!task) {
-    return { pass: true, score: 1, reason: 'Unknown task, skipped correctness check' };
-  }
-
-  const blocks = extractBlocks(String(output || ''));
-  if (blocks.length === 0) {
-    return { pass: false, score: 0, reason: 'No code blocks in output' };
-  }
-
-  const check = CHECKS[task];
-  const result = check(blocks);
-  return {
-    pass: result.pass,
-    score: result.pass ? 1 : 0,
-    reason: result.reason,
-  };
-};

package/benchmarks/lib/aggregate-opencode-go.js

@@ -1,103 +0,0 @@
-const fs = require('fs');
-const path = require('path');
-
-const RESULTS_DIR = path.join(__dirname, '..', 'results');
-
-function median(values) {
-  const s = [...values].sort((a, b) => a - b);
-  if (s.length === 0) return 0;
-  const mid = Math.floor(s.length / 2);
-  return s.length % 2 ? s[mid] : (s[mid - 1] + s[mid]) / 2;
-}
-
-function findLatestJson(resultsDir = RESULTS_DIR) {
-  const files = fs
-    .readdirSync(resultsDir)
-    .filter((f) => f.startsWith('opencode-go-') && f.endsWith('.json'))
-    .sort()
-    .reverse();
-  if (!files.length) {
-    throw new Error(`No opencode-go-*.json in ${resultsDir}. Run benchmark first.`);
-  }
-  return path.join(resultsDir, files[0]);
-}
-
-function modelLabel(id) {
-  return id
-    .replace('deepseek-v4-pro', 'DeepSeek V4')
-    .replace('qwen3.7-max', 'Qwen3.7 Max')
-    .replace('minimax-m3', 'MiniMax M3')
-    .replace('kimi-k2.6', 'Kimi K2.6');
-}
-
-function aggregateOpencodeGo(data) {
-  const taskIds = data.tasks.map((t) => t.id);
-  const arms = data.arms;
-  const models = data.models;
-
-  const chart = {
-    source: `opencode-go-${data.date}.json`,
-    date: data.date,
-    repeat: data.repeat,
-    models: [],
-    tasks: taskIds,
-    arms,
-  };
-
-  for (const modelId of models) {
-    const modelConfig = data.results[modelId];
-    const locByArmTask = {};
-    const timeByArmTask = {};
-    const correctByArm = {};
-
-    for (const arm of arms) {
-      locByArmTask[arm] = {};
-      timeByArmTask[arm] = {};
-      let pass = 0;
-      let total = 0;
-
-      for (const taskId of taskIds) {
-        const runs = modelConfig[arm][taskId];
-        locByArmTask[arm][taskId] = median(runs.map((r) => r.loc));
-        timeByArmTask[arm][taskId] = median(runs.map((r) => r.timeSec));
-        pass += runs.filter((r) => r.correct).length;
-        total += runs.length;
-      }
-
-      correctByArm[arm] = { pass, total };
-    }
-
-    const baselineTotal = taskIds.reduce((s, t) => s + locByArmTask.baseline[t], 0);
-    const lexisTotal = taskIds.reduce((s, t) => s + locByArmTask['lexis-two'][t], 0);
-    const reductionPct =
-      baselineTotal > 0 ? Math.round((1 - lexisTotal / baselineTotal) * 100) : 0;
-
-    const baselineTime = taskIds.reduce((s, t) => s + timeByArmTask.baseline[t], 0);
-    const lexisTime = taskIds.reduce((s, t) => s + timeByArmTask['lexis-two'][t], 0);
-
-    chart.models.push({
-      id: modelId,
-      label: modelLabel(modelId),
-      locByArmTask,
-      timeByArmTask,
-      correctByArm,
-      totals: {
-        baselineLoc: baselineTotal,
-        lexisLoc: lexisTotal,
-        reductionPct,
-        baselineTimeSec: Math.round(baselineTime * 10) / 10,
-        lexisTimeSec: Math.round(lexisTime * 10) / 10,
-      },
-    });
-  }
-
-  return chart;
-}
-
-module.exports = {
-  aggregateOpencodeGo,
-  findLatestJson,
-  modelLabel,
-  median,
-  RESULTS_DIR,
-};

package/benchmarks/lib/load-env.js

@@ -1,31 +0,0 @@
-// Load KEY=VALUE lines from a .env file into process.env (no dotenv dependency).
-const fs = require('fs');
-
-function loadEnvFile(envPath) {
-  if (!fs.existsSync(envPath)) return false;
-
-  const raw = fs.readFileSync(envPath, 'utf8').replace(/^\uFEFF/, '');
-  for (const line of raw.split(/\r?\n/)) {
-    const trimmed = line.trim();
-    if (!trimmed || trimmed.startsWith('#')) continue;
-
-    const eq = trimmed.indexOf('=');
-    if (eq <= 0) continue;
-
-    const key = trimmed.slice(0, eq).trim();
-    if (process.env[key] !== undefined) continue;
-
-    let value = trimmed.slice(eq + 1).trim();
-    if (
-      (value.startsWith('"') && value.endsWith('"')) ||
-      (value.startsWith("'") && value.endsWith("'"))
-    ) {
-      value = value.slice(1, -1);
-    }
-    process.env[key] = value;
-  }
-
-  return true;
-}
-
-module.exports = { loadEnvFile };

package/benchmarks/lib/opencode-go-client.js

@@ -1,151 +0,0 @@
-// OpenCode Go API client — OpenAI chat/completions + Anthropic /messages transports.
-// Docs: https://opencode.ai/docs/go/#endpoints
-
-const fs = require('fs');
-const path = require('path');
-
-const DEFAULT_BASE = 'https://opencode.ai/zen/go/v1';
-const ENV_PATH = path.join(__dirname, '..', '..', '.env');
-
-function getApiKey() {
-  const key = (process.env.OPENCODE_API_KEY || process.env.OPENCODE_GO_API_KEY || '').trim();
-  if (!key) {
-    const hint = fs.existsSync(ENV_PATH)
-      ? `OPENCODE_API_KEY is empty in ${ENV_PATH}. Paste your OpenCode Go key after the = sign.`
-      : `Create ${ENV_PATH} from .env.example and set OPENCODE_API_KEY=your-key`;
-    throw new Error(`Missing OPENCODE_API_KEY. ${hint}`);
-  }
-  return key;
-}
-
-async function readJsonResponse(res) {
-  const text = await res.text();
-  let body;
-  try {
-    body = text ? JSON.parse(text) : {};
-  } catch {
-    body = { raw: text };
-  }
-  if (!res.ok) {
-    const msg =
-      body?.error?.message ||
-      body?.message ||
-      (typeof body?.error === 'string' ? body.error : null) ||
-      text.slice(0, 500) ||
-      res.statusText;
-    throw new Error(`HTTP ${res.status}: ${msg}`);
-  }
-  return body;
-}
-
-function extractOpenAiText(body) {
-  return body?.choices?.[0]?.message?.content ?? '';
-}
-
-function extractAnthropicText(body) {
-  const blocks = body?.content;
-  if (!Array.isArray(blocks)) return '';
-  return blocks
-    .filter((b) => b?.type === 'text' && typeof b.text === 'string')
-    .map((b) => b.text)
-    .join('');
-}
-
-function extractUsage(body, transport) {
-  if (transport === 'openai-chat') {
-    const u = body?.usage;
-    if (!u) return null;
-    return {
-      inputTokens: u.prompt_tokens ?? 0,
-      outputTokens: u.completion_tokens ?? 0,
-    };
-  }
-  const u = body?.usage;
-  if (!u) return null;
-  return {
-    inputTokens: u.input_tokens ?? 0,
-    outputTokens: u.output_tokens ?? 0,
-  };
-}
-
-async function chatOpenAi({ baseUrl, apiKey, model, system, user, maxTokens, temperature }) {
-  const messages = [];
-  if (system) messages.push({ role: 'system', content: system });
-  messages.push({ role: 'user', content: user });
-
-  const res = await fetch(`${baseUrl}/chat/completions`, {
-    method: 'POST',
-    headers: {
-      Authorization: `Bearer ${apiKey}`,
-      'Content-Type': 'application/json',
-    },
-    body: JSON.stringify({
-      model,
-      messages,
-      max_tokens: maxTokens,
-      temperature,
-    }),
-  });
-
-  const body = await readJsonResponse(res);
-  return {
-    text: extractOpenAiText(body),
-    usage: extractUsage(body, 'openai-chat'),
-    raw: body,
-  };
-}
-
-async function chatAnthropic({ baseUrl, apiKey, model, system, user, maxTokens, temperature }) {
-  const payload = {
-    model,
-    max_tokens: maxTokens,
-    messages: [{ role: 'user', content: user }],
-  };
-  if (system) payload.system = system;
-  if (typeof temperature === 'number') payload.temperature = temperature;
-
-  // lexis: Go /messages rejects Bearer — x-api-key only (qwen3.7-max, minimax-m3)
-  const res = await fetch(`${baseUrl}/messages`, {
-    method: 'POST',
-    headers: {
-      'x-api-key': apiKey,
-      'Content-Type': 'application/json',
-      'anthropic-version': '2023-06-01',
-    },
-    body: JSON.stringify(payload),
-  });
-
-  const body = await readJsonResponse(res);
-  return {
-    text: extractAnthropicText(body),
-    usage: extractUsage(body, 'anthropic-messages'),
-    raw: body,
-  };
-}
-
-async function complete({
-  modelId,
-  modelConfig,
-  system,
-  user,
-  baseUrl = DEFAULT_BASE,
-  apiKey = getApiKey(),
-  temperature = 1,
-}) {
-  const maxTokens = modelConfig.maxTokens ?? 8192;
-  const args = { baseUrl, apiKey, model: modelId, system, user, maxTokens, temperature };
-
-  if (modelConfig.transport === 'anthropic-messages') {
-    return chatAnthropic(args);
-  }
-  if (modelConfig.transport === 'openai-chat') {
-    return chatOpenAi(args);
-  }
-  throw new Error(`Unknown transport for ${modelId}: ${modelConfig.transport}`);
-}
-
-module.exports = {
-  DEFAULT_BASE,
-  getApiKey,
-  complete,
-};

package/benchmarks/loc.js

@@ -1,13 +0,0 @@
-// Deterministic code-size metric: non-blank, non-comment lines of code. Counts
-// fenced blocks, or the whole response when the model emitted bare code unfenced.
-// Recorded as the `code_loc` metric per arm (always passes; it is a measurement, not a gate).
-module.exports = (output) => {
-  const text = String(output || '');
-  const blocks = [...text.matchAll(/```[a-zA-Z0-9_+-]*\n([\s\S]*?)```/g)].map((m) => m[1]);
-  const code = blocks.length ? blocks.join('\n') : text;
-  const loc = code
-    .split('\n')
-    .map((l) => l.trim())
-    .filter((l) => l && !l.startsWith('//') && !l.startsWith('#') && l !== '*/' && !l.startsWith('/*') && !l.startsWith('*')).length;
-  return { pass: true, score: loc, reason: loc + ' code LOC' };
-};

package/benchmarks/opencode-go-models.json

@@ -1,31 +0,0 @@
-{
-  "baseUrl": "https://opencode.ai/zen/go/v1",
-  "defaultModels": [
-    "kimi-k2.6",
-    "deepseek-v4-pro",
-    "qwen3.7-max",
-    "minimax-m3"
-  ],
-  "models": {
-    "kimi-k2.6": {
-      "name": "Kimi K2.6",
-      "transport": "openai-chat",
-      "maxTokens": 8192
-    },
-    "deepseek-v4-pro": {
-      "name": "DeepSeek V4 Pro",
-      "transport": "openai-chat",
-      "maxTokens": 8192
-    },
-    "qwen3.7-max": {
-      "name": "Qwen3.7 Max",
-      "transport": "anthropic-messages",
-      "maxTokens": 8192
-    },
-    "minimax-m3": {
-      "name": "MiniMax M3",
-      "transport": "anthropic-messages",
-      "maxTokens": 8192
-    }
-  }
-}

package/benchmarks/promptfooconfig.yaml

@@ -1,41 +0,0 @@
-# Ponytail benchmark: code size + cost across three arms, same model, same tasks.
-#
-#   Run:   npx promptfoo@latest eval -c benchmarks/promptfooconfig.yaml
-#   View:  npx promptfoo@latest view
-#   Share: npx promptfoo@latest share   (publishes a hosted report URL)
-#
-# Needs ANTHROPIC_API_KEY in the environment or a .env file (see benchmarks/README.md).
-# Caveman arm uses JuliusBrussee/caveman SKILL.md (MIT), vendored at arms/caveman-SKILL.md.
-description: "Ponytail vs caveman vs no-skill: same model, same tasks. Measures code LOC (deterministic) and tokens/cost (API telemetry)."
-
-providers:
-  - id: anthropic:messages:claude-haiku-4-5-20251001
-    config: { max_tokens: 8192, temperature: 1 }
-  - id: anthropic:messages:claude-sonnet-4-6
-    config: { max_tokens: 8192, temperature: 1 }
-  - id: anthropic:messages:claude-opus-4-8
-    config: { max_tokens: 8192, temperature: 1 }
-
-prompts:
-  - id: file://arms/baseline.js
-    label: baseline (no skill)
-  - id: file://arms/caveman.js
-    label: caveman
-  - id: file://arms/ponytail.js
-    label: ponytail
-
-defaultTest:
-  assert:
-    - type: javascript
-      value: file://loc.js
-      metric: code_loc
-    - type: javascript
-      value: file://correctness.js
-      metric: correct
-
-tests:
-  - vars: { task: "Write me a Python function that validates email addresses." }
-  - vars: { task: "Add debounce to a search input in vanilla JavaScript. It currently fires an API call on every keystroke." }
-  - vars: { task: "Write Python code that reads sales.csv and sums the 'amount' column." }
-  - vars: { task: "Build me a countdown timer component in React that counts down from a given number of seconds." }
-  - vars: { task: "Add rate limiting to my FastAPI endpoint so users can't spam it." }

package/benchmarks/prompts.json

@@ -1,15 +0,0 @@
-{
-  "method": "One fresh Claude Code subagent per task x config, same model, no file outputs. Metrics from task telemetry: total tokens (includes thinking), duration. Code lines counted from fenced blocks in the deliverable.",
-  "configs": [
-    "baseline — no skill",
-    "caveman — caveman SKILL.md (full) as operating instructions",
-    "ponytail — ponytail SKILL.md (full) as operating instructions"
-  ],
-  "tasks": [
-    { "id": "email", "prompt": "Write me a Python function that validates email addresses." },
-    { "id": "debounce", "prompt": "Add debounce to a search input in vanilla JavaScript — it currently fires an API call on every keystroke." },
-    { "id": "csv-sum", "prompt": "Write Python code that reads sales.csv and sums the 'amount' column." },
-    { "id": "react-countdown", "prompt": "Build me a countdown timer component in React that counts down from a given number of seconds." },
-    { "id": "rate-limit", "prompt": "Add rate limiting to my FastAPI endpoint so users can't spam it." }
-  ]
-}