@hasna/skills 0.1.62 → 0.1.64

package/skills/diff-viewer/src/index.ts

@@ -1,164 +0,0 @@
-#!/usr/bin/env bun
-import { readFile } from "fs/promises";
-import { diffLines } from "diff";
-import chalk from "chalk";
-import { resolve, normalize, isAbsolute } from "path";
-
-// ============================================================================
-// Path Security
-// ============================================================================
-
-// Sensitive paths that should never be read
-const BLOCKED_PATHS = [
-  '/etc/passwd',
-  '/etc/shadow',
-  '/etc/hosts',
-  '/etc/sudoers',
-  '/etc/ssh',
-  '/root',
-  '/.ssh',
-  '/.aws',
-  '/.config',
-  '/.env',
-  '/proc',
-  '/sys',
-  '/dev',
-  '/var/log',
-  '/var/run',
-  '/tmp',
-  '/private/etc',
-  '/private/var',
-];
-
-// File patterns that should be blocked
-const BLOCKED_PATTERNS = [
-  /\.env($|\.)/i,               // .env, .env.local, .env.production
-  /\.pem$/i,                    // Private keys
-  /\.key$/i,                    // Private keys
-  /\.crt$/i,                    // Certificates
-  /id_rsa/i,                    // SSH keys
-  /id_ed25519/i,                // SSH keys
-  /\.secrets?/i,                // Secrets directories/files
-  /credentials/i,               // Credential files
-  /password/i,                  // Password files
-  /\.git\/config$/i,            // Git config with potential tokens
-  /\.npmrc$/i,                  // npm config with tokens
-  /\.pypirc$/i,                 // PyPI config with tokens
-  /kubeconfig/i,                // Kubernetes configs
-  /\.docker\/config\.json$/i,   // Docker configs with auth
-];
-
-function isPathBlocked(filePath: string): { blocked: boolean; reason?: string } {
-  const normalizedPath = normalize(filePath).toLowerCase();
-  const resolvedPath = isAbsolute(filePath) ? resolve(filePath) : resolve(process.cwd(), filePath);
-  const resolvedLower = resolvedPath.toLowerCase();
-
-  // Check for path traversal attempts
-  if (filePath.includes('..')) {
-    // Allow .. only if it doesn't escape the current working directory
-    const cwd = process.cwd();
-    if (!resolvedPath.startsWith(cwd)) {
-      return { blocked: true, reason: 'Path traversal outside working directory is not allowed' };
-    }
-  }
-
-  // Check against blocked paths
-  for (const blockedPath of BLOCKED_PATHS) {
-    if (resolvedLower.startsWith(blockedPath.toLowerCase()) ||
-        resolvedLower.includes(blockedPath.toLowerCase())) {
-      return { blocked: true, reason: `Access to ${blockedPath} is restricted for security reasons` };
-    }
-  }
-
-  // Check against blocked patterns
-  for (const pattern of BLOCKED_PATTERNS) {
-    if (pattern.test(normalizedPath) || pattern.test(resolvedPath)) {
-      return { blocked: true, reason: `Access to files matching ${pattern} is restricted for security reasons` };
-    }
-  }
-
-  return { blocked: false };
-}
-
-function validateFilePath(filePath: string, argName: string): string {
-  if (!filePath || filePath.trim() === '') {
-    throw new Error(`${argName} cannot be empty`);
-  }
-
-  // Check for null bytes (path traversal attack vector)
-  if (filePath.includes('\0')) {
-    throw new Error(`${argName} contains invalid characters`);
-  }
-
-  const blockCheck = isPathBlocked(filePath);
-  if (blockCheck.blocked) {
-    throw new Error(`Security: ${blockCheck.reason}`);
-  }
-
-  return filePath;
-}
-
-// ============================================================================
-// Main
-// ============================================================================
-
-const args = process.argv.slice(2);
-
-if (args.includes("-h") || args.includes("--help")) {
-  console.log(`
-diff-viewer - Compare two files and show differences
-
-Usage:
-  skills run diff-viewer -- file1=<path> file2=<path>
-
-Options:
-  -h, --help           Show this help message
-  file1=<path>         First file to compare (required)
-  file2=<path>         Second file to compare (required)
-
-Output:
-  Green text: Lines added in file2
-  Red text: Lines removed from file1
-  Grey text: Unchanged lines
-
-Examples:
-  skills run diff-viewer -- file1=old.txt file2=new.txt
-  skills run diff-viewer -- file1=src/v1.ts file2=src/v2.ts
-`);
-  process.exit(0);
-}
-
-const file1Arg = args.find(a => a.startsWith("file1="))?.split("=")[1];
-const file2Arg = args.find(a => a.startsWith("file2="))?.split("=")[1];
-
-async function main() {
-  if (!file1Arg || !file2Arg) {
-    console.log("Usage: skills run diff-viewer -- file1=... file2=...");
-    process.exit(1);
-  }
-
-  try {
-    // Validate file paths before reading
-    const validatedPath1 = validateFilePath(file1Arg, "file1");
-    const validatedPath2 = validateFilePath(file2Arg, "file2");
-
-    const content1 = await readFile(validatedPath1, "utf-8");
-    const content2 = await readFile(validatedPath2, "utf-8");
-
-    const diff = diffLines(content1, content2);
-
-    diff.forEach(part => {
-      const color = part.added ? chalk.green :
-                    part.removed ? chalk.red :
-                    chalk.grey;
-      process.stdout.write(color(part.value));
-    });
-    console.log(); // Newline at end
-
-  } catch (error: any) {
-    console.error("Error:", error.message);
-    process.exit(1);
-  }
-}
-
-main();

package/skills/diff-viewer/tsconfig.json

@@ -1,10 +0,0 @@
-{
-  "extends": "../tsconfig.base.json",
-  "compilerOptions": {
-    "outDir": "dist"
-  },
-  "include": [
-    "src/**/*",
-    "bin/**/*"
-  ]
-}

package/skills/doc-read/SKILL.md

@@ -1,45 +0,0 @@
----
-name: doc-read
-version: 0.1.0
-description: Read and extract text from DOCX files with section parsing, metadata extraction, and multiple file support
-category: Data & Analysis
-tags:
-  - docx
-  - documents
-  - extraction
-  - reader
-  - word
----
-
-# Doc Read
-
-Read and extract content from DOCX files. Supports multiple files at once, preserves document structure (headings, paragraphs, lists, tables), and extracts metadata. Outputs plain text, JSON with structure, or markdown.
-
-## Features
-
-- **Multiple Files**: Process many DOCX files in a single command
-- **Structure Preservation**: Extracts headings, paragraphs, lists, and tables
-- **Metadata Extraction**: Get title, author, creation date, word count
-- **Parallel Processing**: Process multiple files concurrently
-- **Output Formats**: Plain text, JSON with document structure, or markdown
-
-## Usage
-
-```bash
-# Read a single DOCX file
-doc-read read document.docx
-
-# Read multiple files
-doc-read read file1.docx file2.docx file3.docx
-
-# Output as JSON with structure
-doc-read read document.docx --format json --output result.json
-
-# Get metadata only
-doc-read info document.docx
-```
-
-## Requirements
-
-- Bun runtime
-- mammoth (auto-installed)

package/skills/doc-read/package.json

@@ -1,29 +0,0 @@
-{
-  "name": "doc-read",
-  "version": "0.1.0",
-  "description": "Read and extract text from DOCX files with section parsing and metadata extraction",
-  "type": "module",
-  "bin": {
-    "doc-read": "./src/index.ts"
-  },
-  "scripts": {
-    "dev": "bun run src/index.ts",
-    "build": "bun build src/index.ts --outdir dist --target node",
-    "typecheck": "tsc --noEmit"
-  },
-  "dependencies": {
-    "jszip": "^3.10.1"
-  },
-  "devDependencies": {
-    "@types/bun": "latest",
-    "typescript": "^5.7.0"
-  },
-  "publishConfig": {
-    "access": "restricted",
-    "registry": "https://registry.npmjs.org/"
-  },
-  "files": [
-    "src",
-    "tsconfig.json"
-  ]
-}

package/skills/doc-read/src/index.ts

@@ -1,324 +0,0 @@
-#!/usr/bin/env bun
-
-import { readFile, writeFile, stat, mkdir } from 'fs/promises';
-import { existsSync } from 'fs';
-import { basename, extname, dirname, resolve } from 'path';
-import { parseArgs } from 'util';
-
-async function loadJSZip() {
-  try {
-    return (await import('jszip')).default;
-  } catch {
-    throw new Error("Missing dependency 'jszip'. Run bun install in this skill directory.");
-  }
-}
-
-interface DocResult {
-  file: string;
-  text: string;
-  sections: DocSection[];
-  metadata: DocMetadata;
-  wordCount: number;
-}
-
-interface DocSection {
-  type: 'heading' | 'paragraph' | 'list' | 'table';
-  level?: number;
-  text: string;
-  items?: string[];
-  rows?: string[][];
-}
-
-interface DocMetadata {
-  title?: string;
-  author?: string;
-  lastModifiedBy?: string;
-  created?: string;
-  modified?: string;
-  description?: string;
-}
-
-async function extractDocxText(buffer: Buffer): Promise<{ text: string; sections: DocSection[] }> {
-  const JSZip = await loadJSZip();
-  const zip = await JSZip.loadAsync(buffer);
-
-  const documentXml = await zip.file('word/document.xml')?.async('string');
-  if (!documentXml) throw new Error('Invalid DOCX: missing word/document.xml');
-
-  const sections: DocSection[] = [];
-  let fullText = '';
-
-  const paragraphs = documentXml.match(/<w:p[\s>][\s\S]*?<\/w:p>/g) || [];
-
-  for (const para of paragraphs) {
-    const textParts = para.match(/<w:t[^>]*>([\s\S]*?)<\/w:t>/g) || [];
-    const text = textParts
-      .map(t => t.replace(/<w:t[^>]*>/, '').replace(/<\/w:t>/, ''))
-      .join('');
-
-    if (!text.trim()) continue;
-
-    const headingMatch = para.match(/<w:pStyle w:val="Heading(\d)"/);
-    if (headingMatch) {
-      const level = parseInt(headingMatch[1]);
-      sections.push({ type: 'heading', level, text: text.trim() });
-    } else if (para.includes('<w:numPr>')) {
-      const lastSection = sections[sections.length - 1];
-      if (lastSection?.type === 'list') {
-        lastSection.items!.push(text.trim());
-      } else {
-        sections.push({ type: 'list', text: text.trim(), items: [text.trim()] });
-      }
-    } else {
-      sections.push({ type: 'paragraph', text: text.trim() });
-    }
-
-    fullText += text.trim() + '\n';
-  }
-
-  const tables = documentXml.match(/<w:tbl>[\s\S]*?<\/w:tbl>/g) || [];
-  for (const table of tables) {
-    const rows: string[][] = [];
-    const tableRows = table.match(/<w:tr[\s>][\s\S]*?<\/w:tr>/g) || [];
-    for (const row of tableRows) {
-      const cells = row.match(/<w:tc[\s>][\s\S]*?<\/w:tc>/g) || [];
-      const rowData = cells.map(cell => {
-        const cellTexts = cell.match(/<w:t[^>]*>([\s\S]*?)<\/w:t>/g) || [];
-        return cellTexts.map(t => t.replace(/<w:t[^>]*>/, '').replace(/<\/w:t>/, '')).join(' ');
-      });
-      rows.push(rowData);
-    }
-    if (rows.length > 0) {
-      sections.push({ type: 'table', text: '', rows });
-    }
-  }
-
-  return { text: fullText, sections };
-}
-
-async function extractDocxMetadata(buffer: Buffer): Promise<DocMetadata> {
-  const JSZip = await loadJSZip();
-  const zip = await JSZip.loadAsync(buffer);
-
-  const coreXml = await zip.file('docProps/core.xml')?.async('string');
-  if (!coreXml) return {};
-
-  const getTag = (xml: string, tag: string): string | undefined => {
-    const match = xml.match(new RegExp(`<${tag}[^>]*>([\\s\\S]*?)</${tag}>`));
-    return match?.[1]?.trim() || undefined;
-  };
-
-  return {
-    title: getTag(coreXml, 'dc:title'),
-    author: getTag(coreXml, 'dc:creator'),
-    lastModifiedBy: getTag(coreXml, 'cp:lastModifiedBy'),
-    created: getTag(coreXml, 'dcterms:created'),
-    modified: getTag(coreXml, 'dcterms:modified'),
-    description: getTag(coreXml, 'dc:description'),
-  };
-}
-
-async function readSingleDocx(filePath: string): Promise<DocResult> {
-  const buffer = await readFile(filePath);
-  const { text, sections } = await extractDocxText(buffer);
-  const metadata = await extractDocxMetadata(buffer);
-  const wordCount = text.split(/\s+/).filter(w => w.length > 0).length;
-
-  return { file: filePath, text, sections, metadata, wordCount };
-}
-
-async function readMultipleDocx(files: string[], concurrency = 4): Promise<DocResult[]> {
-  const results: DocResult[] = [];
-  const queue = [...files];
-
-  async function processNext(): Promise<void> {
-    while (queue.length > 0) {
-      const file = queue.shift()!;
-      console.log(`Reading: ${basename(file)}`);
-      const result = await readSingleDocx(file);
-      results.push(result);
-      console.log(`  ${result.sections.length} sections, ${result.wordCount} words`);
-    }
-  }
-
-  const workers = Array.from({ length: Math.min(concurrency, files.length) }, () => processNext());
-  await Promise.all(workers);
-
-  return results;
-}
-
-function formatText(results: DocResult[]): string {
-  return results.map(r => {
-    const header = `=== ${basename(r.file)} (${r.wordCount} words) ===\n`;
-    return header + r.text;
-  }).join('\n\n');
-}
-
-function formatJson(results: DocResult[]): string {
-  return JSON.stringify(results.map(r => ({
-    file: basename(r.file),
-    wordCount: r.wordCount,
-    metadata: r.metadata,
-    sections: r.sections,
-  })), null, 2);
-}
-
-function formatMarkdown(results: DocResult[]): string {
-  return results.map(r => {
-    const lines: string[] = [];
-    lines.push(`# ${basename(r.file)}`);
-    lines.push('');
-    if (r.metadata.title) lines.push(`**Title:** ${r.metadata.title}`);
-    if (r.metadata.author) lines.push(`**Author:** ${r.metadata.author}`);
-    lines.push(`**Words:** ${r.wordCount}`);
-    lines.push('');
-
-    for (const section of r.sections) {
-      switch (section.type) {
-        case 'heading':
-          lines.push(`${'#'.repeat((section.level || 1) + 1)} ${section.text}`);
-          lines.push('');
-          break;
-        case 'paragraph':
-          lines.push(section.text);
-          lines.push('');
-          break;
-        case 'list':
-          for (const item of section.items || []) {
-            lines.push(`- ${item}`);
-          }
-          lines.push('');
-          break;
-        case 'table':
-          if (section.rows && section.rows.length > 0) {
-            lines.push('| ' + section.rows[0].join(' | ') + ' |');
-            lines.push('| ' + section.rows[0].map(() => '---').join(' | ') + ' |');
-            for (const row of section.rows.slice(1)) {
-              lines.push('| ' + row.join(' | ') + ' |');
-            }
-            lines.push('');
-          }
-          break;
-      }
-    }
-    return lines.join('\n');
-  }).join('\n---\n\n');
-}
-
-async function main() {
-  const { values, positionals } = parseArgs({
-    args: Bun.argv.slice(2),
-    options: {
-      format: { type: 'string', default: 'text' },
-      output: { type: 'string', short: 'o' },
-      concurrency: { type: 'string', default: '4' },
-      help: { type: 'boolean', short: 'h' },
-    },
-    allowPositionals: true,
-  });
-
-  const command = positionals[0];
-  const files = positionals.slice(1);
-
-  if (values.help || !command) {
-    console.log(`
-Doc Read - Extract text from DOCX files
-
-Usage:
-  doc-read read <files...> [options]
-  doc-read info <files...>
-
-Commands:
-  read          Extract text and structure from DOCX files
-  info          Show document metadata
-
-Read Options:
-  --format <fmt>       Output format: text, json, markdown (default: text)
-  --output, -o <path>  Write output to file
-  --concurrency <n>    Parallel file processing (default: 4)
-
-Examples:
-  doc-read read document.docx
-  doc-read read *.docx --format json --output extracted.json
-  doc-read read report.docx --format markdown
-  doc-read info document.docx
-`);
-    process.exit(0);
-  }
-
-  if (files.length === 0) {
-    console.error('Error: At least one DOCX file is required');
-    process.exit(1);
-  }
-
-  for (const file of files) {
-    if (!existsSync(file)) {
-      console.error(`File not found: ${file}`);
-      process.exit(1);
-    }
-    const ext = extname(file).toLowerCase();
-    if (ext !== '.docx' && ext !== '.doc') {
-      console.error(`Not a DOCX file: ${file}`);
-      process.exit(1);
-    }
-  }
-
-  switch (command) {
-    case 'read': {
-      const concurrency = parseInt(values.concurrency as string) || 4;
-
-      console.log(`\nReading ${files.length} DOCX file(s)...\n`);
-
-      const results = await readMultipleDocx(files, concurrency);
-
-      let output: string;
-      switch (values.format) {
-        case 'json': output = formatJson(results); break;
-        case 'markdown': case 'md': output = formatMarkdown(results); break;
-        default: output = formatText(results); break;
-      }
-
-      if (values.output) {
-        const outputPath = resolve(values.output as string);
-        await mkdir(dirname(outputPath), { recursive: true });
-        await writeFile(outputPath, output);
-        console.log(`\nOutput saved to: ${outputPath}`);
-      } else {
-        console.log('\n' + output);
-      }
-
-      const totalWords = results.reduce((s, r) => s + r.wordCount, 0);
-      console.log(`\nProcessed: ${files.length} files, ${totalWords.toLocaleString()} words`);
-      break;
-    }
-
-    case 'info': {
-      for (const file of files) {
-        const buffer = await readFile(file);
-        const metadata = await extractDocxMetadata(buffer);
-        const { text } = await extractDocxText(buffer);
-        const wordCount = text.split(/\s+/).filter(w => w.length > 0).length;
-        const fileStats = await stat(file);
-
-        console.log(`\n${basename(file)}:`);
-        console.log(`  Size: ${(fileStats.size / 1024).toFixed(1)} KB`);
-        console.log(`  Words: ${wordCount.toLocaleString()}`);
-        if (metadata.title) console.log(`  Title: ${metadata.title}`);
-        if (metadata.author) console.log(`  Author: ${metadata.author}`);
-        if (metadata.lastModifiedBy) console.log(`  Last Modified By: ${metadata.lastModifiedBy}`);
-        if (metadata.created) console.log(`  Created: ${metadata.created}`);
-        if (metadata.modified) console.log(`  Modified: ${metadata.modified}`);
-      }
-      break;
-    }
-
-    default:
-      console.error(`Unknown command: ${command}`);
-      process.exit(1);
-  }
-}
-
-main().catch(err => {
-  console.error('Error:', err.message);
-  process.exit(1);
-});

package/skills/doc-read/tsconfig.json

@@ -1,8 +0,0 @@
-{
-  "extends": "../tsconfig.base.json",
-  "compilerOptions": {
-    "outDir": "dist",
-    "rootDir": "src"
-  },
-  "include": ["src"]
-}