[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7CCC8684PQTARCBCQR0A6S2":3,"skill-same:01M7CCC8684PQTARCBCQR0A6S2":55},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":33,"commitSha":34,"skillDirectory":35,"forksCount":36,"repositoryHtmlUrl":37,"repositoryHomepageUrl":6,"ownerHtmlUrl":38,"ownerBlogUrl":6,"ownerDescription":39,"updatedAt":40,"install":41,"resources":54},"01M7CCC8684PQTARCBCQR0A6S2","secure-code-guardian",null,"Use when implementing authentication\u002Fauthorization, securing user input, or preventing OWASP Top 10 vulnerabilities — including custom security implementations such as hashing passwords with bcrypt\u002Fargon2, sanitizing SQL queries with parameterized statements, configuring CORS\u002FCSP headers, validating input with Zod, and setting up JWT tokens. Invoke for authentication, authorization, input validation, encryption, OWASP Top 10 prevention, secure session management, and security hardening. For pre-built OAuth\u002FSSO integrations or standalone security audits, consider a more specialized skill.","om-scogo\u002Fskillsh-scraper","om-scogo","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F160466840?v=4","01M79AWB6DFVCQ7RK70CS34B96","Om Achrekar","01M79AWB6ZM9SKR8KDH1WSSM22",0,"MIT","https:\u002F\u002Fgithub.com\u002Fom-scogo\u002Fskillsh-scraper\u002Fblob\u002Fmain\u002Fdata\u002Fskills\u002Fjeffallan-claude-skills\u002Fsecure-code-guardian\u002Fskills\u002Fsecure-code-guardian\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: secure-code-guardian\ndescription: Use when implementing authentication\u002Fauthorization, securing user input, or preventing OWASP Top 10 vulnerabilities — including custom security implementations such as hashing passwords with bcrypt\u002Fargon2, sanitizing SQL queries with parameterized statements, configuring CORS\u002FCSP headers, validating input with Zod, and setting up JWT tokens. Invoke for authentication, authorization, input validation, encryption, OWASP Top 10 prevention, secure session management, and security hardening. For pre-built OAuth\u002FSSO integrations or standalone security audits, consider a more specialized skill.\nlicense: MIT\nmetadata:\n  author: https:\u002F\u002Fgithub.com\u002FJeffallan\n  version: \"1.1.0\"\n  domain: security\n  triggers: security, authentication, authorization, encryption, OWASP, vulnerability, secure coding, password, JWT, OAuth\n  role: specialist\n  scope: implementation\n  output-format: code\n  related-skills: fullstack-guardian, security-reviewer, architecture-designer\n---\n\n# Secure Code Guardian\n\n## Core Workflow\n\n1. **Threat model** — Identify attack surface and threats\n2. **Design** — Plan security controls\n3. **Implement** — Write secure code with defense in depth; see code examples below\n4. **Validate** — Test security controls with explicit checkpoints (see below)\n5. **Document** — Record security decisions\n\n### Validation Checkpoints\n\nAfter each implementation step, verify:\n\n- **Authentication**: Test brute-force protection (lockout\u002Frate limit triggers), session fixation resistance, token expiration, and invalid-credential error messages (must not leak user existence).\n- **Authorization**: Verify horizontal and vertical privilege escalation paths are blocked; test with tokens belonging to different roles\u002Fusers.\n- **Input handling**: Confirm SQL injection payloads (`' OR 1=1--`) are rejected; confirm XSS payloads (`\u003Cscript>alert(1)\u003C\u002Fscript>`) are escaped or rejected.\n- **Headers\u002FCORS**: Validate with a security scanner (e.g., `curl -I`, Mozilla Observatory) that security headers are present and CORS origin allowlist is correct.\n\n## Reference Guide\n\nLoad detailed guidance based on context:\n\n| Topic | Reference | Load When |\n|-------|-----------|-----------|\n| OWASP | `references\u002Fowasp-prevention.md` | OWASP Top 10 patterns |\n| Authentication | `references\u002Fauthentication.md` | Password hashing, JWT |\n| Input Validation | `references\u002Finput-validation.md` | Zod, SQL injection |\n| XSS\u002FCSRF | `references\u002Fxss-csrf.md` | XSS prevention, CSRF |\n| Headers | `references\u002Fsecurity-headers.md` | Helmet, rate limiting |\n\n## Constraints\n\n### MUST DO\n- Hash passwords with bcrypt\u002Fargon2 (never MD5\u002FSHA-1\u002Funsalted hashes)\n- Use parameterized queries (never string-interpolated SQL)\n- Validate and sanitize all user input before use\n- Implement rate limiting on auth endpoints\n- Set security headers (CSP, HSTS, X-Frame-Options)\n- Log security events (failed auth, privilege escalation attempts)\n- Store secrets in environment variables or secret managers (never in source code)\n\n### MUST NOT DO\n- Store passwords in plaintext or reversibly encrypted form\n- Trust user input without validation\n- Expose sensitive data in logs or error responses\n- Use weak or deprecated algorithms (MD5, SHA-1, DES, ECB mode)\n- Hardcode secrets or credentials in code\n\n## Code Examples\n\n### Password Hashing (bcrypt)\n\n```typescript\nimport bcrypt from 'bcrypt';\n\nconst SALT_ROUNDS = 12; \u002F\u002F minimum 10; 12 balances security and performance\n\nexport async function hashPassword(plaintext: string): Promise\u003Cstring> {\n  return bcrypt.hash(plaintext, SALT_ROUNDS);\n}\n\nexport async function verifyPassword(plaintext: string, hash: string): Promise\u003Cboolean> {\n  return bcrypt.compare(plaintext, hash);\n}\n```\n\n### Parameterized SQL Query (Node.js \u002F pg)\n\n```typescript\n\u002F\u002F NEVER: `SELECT * FROM users WHERE email = '${email}'`\n\u002F\u002F ALWAYS: use positional parameters\nimport { Pool } from 'pg';\nconst pool = new Pool();\n\nexport async function getUserByEmail(email: string) {\n  const { rows } = await pool.query(\n    'SELECT id, email, role FROM users WHERE email = $1',\n    [email]  \u002F\u002F value passed separately — never interpolated\n  );\n  return rows[0] ?? null;\n}\n```\n\n### Input Validation with Zod\n\n```typescript\nimport { z } from 'zod';\n\nconst LoginSchema = z.object({\n  email: z.string().email().max(254),\n  password: z.string().min(8).max(128),\n});\n\nexport function validateLoginInput(raw: unknown) {\n  const result = LoginSchema.safeParse(raw);\n  if (!result.success) {\n    \u002F\u002F Return generic error — never echo raw input back\n    throw new Error('Invalid credentials format');\n  }\n  return result.data;\n}\n```\n\n### JWT Validation\n\n```typescript\nimport jwt from 'jsonwebtoken';\n\nconst JWT_SECRET = process.env.JWT_SECRET!; \u002F\u002F never hardcode\n\nexport function verifyToken(token: string): jwt.JwtPayload {\n  \u002F\u002F Throws if expired, tampered, or wrong algorithm\n  const payload = jwt.verify(token, JWT_SECRET, {\n    algorithms: ['HS256'],   \u002F\u002F explicitly allowlist algorithm\n    issuer: 'your-app',\n    audience: 'your-app',\n  });\n  if (typeof payload === 'string') throw new Error('Invalid token payload');\n  return payload;\n}\n```\n\n### Securing an Endpoint — Full Flow\n\n```typescript\nimport express from 'express';\nimport rateLimit from 'express-rate-limit';\nimport helmet from 'helmet';\n\nconst app = express();\napp.use(helmet()); \u002F\u002F sets CSP, HSTS, X-Frame-Options, etc.\napp.use(express.json({ limit: '10kb' })); \u002F\u002F limit payload size\n\nconst authLimiter = rateLimit({\n  windowMs: 15 * 60 * 1000, \u002F\u002F 15 minutes\n  max: 10,                   \u002F\u002F 10 attempts per window per IP\n  standardHeaders: true,\n  legacyHeaders: false,\n});\n\napp.post('\u002Fapi\u002Flogin', authLimiter, async (req, res) => {\n  \u002F\u002F 1. Validate input\n  const { email, password } = validateLoginInput(req.body);\n\n  \u002F\u002F 2. Authenticate — parameterized query, constant-time compare\n  const user = await getUserByEmail(email);\n  if (!user || !(await verifyPassword(password, user.passwordHash))) {\n    \u002F\u002F Generic message — do not reveal whether email exists\n    return res.status(401).json({ error: 'Invalid credentials' });\n  }\n\n  \u002F\u002F 3. Authorize — issue scoped, short-lived token\n  const token = jwt.sign(\n    { sub: user.id, role: user.role },\n    JWT_SECRET,\n    { algorithm: 'HS256', expiresIn: '15m', issuer: 'your-app', audience: 'your-app' }\n  );\n\n  \u002F\u002F 4. Secure response — token in httpOnly cookie, not body\n  res.cookie('token', token, { httpOnly: true, secure: true, sameSite: 'strict' });\n  return res.json({ message: 'Authenticated' });\n});\n```\n\n## Output Templates\n\nWhen implementing security features, provide:\n1. Secure implementation code\n2. Security considerations noted\n3. Configuration requirements (env vars, headers)\n4. Testing recommendations\n\n## Knowledge Reference\n\nOWASP Top 10, bcrypt\u002Fargon2, JWT, OAuth 2.0, OIDC, CSP, CORS, rate limiting, input validation, output encoding, encryption (AES, RSA), TLS, security headers\n\n[Documentation](https:\u002F\u002Fjeffallan.github.io\u002Fclaude-skills\u002Fskills\u002Fsecurity\u002Fsecure-code-guardian\u002F)\n","# Secure Code Guardian\n\n## Core Workflow\n\n1. **Threat model** — Identify attack surface and threats\n2. **Design** — Plan security controls\n3. **Implement** — Write secure code with defense in depth; see code examples below\n4. **Validate** — Test security controls with explicit checkpoints (see below)\n5. **Document** — Record security decisions\n\n### Validation Checkpoints\n\nAfter each implementation step, verify:\n\n- **Authentication**: Test brute-force protection (lockout\u002Frate limit triggers), session fixation resistance, token expiration, and invalid-credential error messages (must not leak user existence).\n- **Authorization**: Verify horizontal and vertical privilege escalation paths are blocked; test with tokens belonging to different roles\u002Fusers.\n- **Input handling**: Confirm SQL injection payloads (`' OR 1=1--`) are rejected; confirm XSS payloads (`\u003Cscript>alert(1)\u003C\u002Fscript>`) are escaped or rejected.\n- **Headers\u002FCORS**: Validate with a security scanner (e.g., `curl -I`, Mozilla Observatory) that security headers are present and CORS origin allowlist is correct.\n\n## Reference Guide\n\nLoad detailed guidance based on context:\n\n| Topic | Reference | Load When |\n|-------|-----------|-----------|\n| OWASP | `references\u002Fowasp-prevention.md` | OWASP Top 10 patterns |\n| Authentication | `references\u002Fauthentication.md` | Password hashing, JWT |\n| Input Validation | `references\u002Finput-validation.md` | Zod, SQL injection |\n| XSS\u002FCSRF | `references\u002Fxss-csrf.md` | XSS prevention, CSRF |\n| Headers | `references\u002Fsecurity-headers.md` | Helmet, rate limiting |\n\n## Constraints\n\n### MUST DO\n- Hash passwords with bcrypt\u002Fargon2 (never MD5\u002FSHA-1\u002Funsalted hashes)\n- Use parameterized queries (never string-interpolated SQL)\n- Validate and sanitize all user input before use\n- Implement rate limiting on auth endpoints\n- Set security headers (CSP, HSTS, X-Frame-Options)\n- Log security events (failed auth, privilege escalation attempts)\n- Store secrets in environment variables or secret managers (never in source code)\n\n### MUST NOT DO\n- Store passwords in plaintext or reversibly encrypted form\n- Trust user input without validation\n- Expose sensitive data in logs or error responses\n- Use weak or deprecated algorithms (MD5, SHA-1, DES, ECB mode)\n- Hardcode secrets or credentials in code\n\n## Code Examples\n\n### Password Hashing (bcrypt)\n\n```typescript\nimport bcrypt from 'bcrypt';\n\nconst SALT_ROUNDS = 12; \u002F\u002F minimum 10; 12 balances security and performance\n\nexport async function hashPassword(plaintext: string): Promise\u003Cstring> {\n  return bcrypt.hash(plaintext, SALT_ROUNDS);\n}\n\nexport async function verifyPassword(plaintext: string, hash: string): Promise\u003Cboolean> {\n  return bcrypt.compare(plaintext, hash);\n}\n```\n\n### Parameterized SQL Query (Node.js \u002F pg)\n\n```typescript\n\u002F\u002F NEVER: `SELECT * FROM users WHERE email = '${email}'`\n\u002F\u002F ALWAYS: use positional parameters\nimport { Pool } from 'pg';\nconst pool = new Pool();\n\nexport async function getUserByEmail(email: string) {\n  const { rows } = await pool.query(\n    'SELECT id, email, role FROM users WHERE email = $1',\n    [email]  \u002F\u002F value passed separately — never interpolated\n  );\n  return rows[0] ?? null;\n}\n```\n\n### Input Validation with Zod\n\n```typescript\nimport { z } from 'zod';\n\nconst LoginSchema = z.object({\n  email: z.string().email().max(254),\n  password: z.string().min(8).max(128),\n});\n\nexport function validateLoginInput(raw: unknown) {\n  const result = LoginSchema.safeParse(raw);\n  if (!result.success) {\n    \u002F\u002F Return generic error — never echo raw input back\n    throw new Error('Invalid credentials format');\n  }\n  return result.data;\n}\n```\n\n### JWT Validation\n\n```typescript\nimport jwt from 'jsonwebtoken';\n\nconst JWT_SECRET = process.env.JWT_SECRET!; \u002F\u002F never hardcode\n\nexport function verifyToken(token: string): jwt.JwtPayload {\n  \u002F\u002F Throws if expired, tampered, or wrong algorithm\n  const payload = jwt.verify(token, JWT_SECRET, {\n    algorithms: ['HS256'],   \u002F\u002F explicitly allowlist algorithm\n    issuer: 'your-app',\n    audience: 'your-app',\n  });\n  if (typeof payload === 'string') throw new Error('Invalid token payload');\n  return payload;\n}\n```\n\n### Securing an Endpoint — Full Flow\n\n```typescript\nimport express from 'express';\nimport rateLimit from 'express-rate-limit';\nimport helmet from 'helmet';\n\nconst app = express();\napp.use(helmet()); \u002F\u002F sets CSP, HSTS, X-Frame-Options, etc.\napp.use(express.json({ limit: '10kb' })); \u002F\u002F limit payload size\n\nconst authLimiter = rateLimit({\n  windowMs: 15 * 60 * 1000, \u002F\u002F 15 minutes\n  max: 10,                   \u002F\u002F 10 attempts per window per IP\n  standardHeaders: true,\n  legacyHeaders: false,\n});\n\napp.post('\u002Fapi\u002Flogin', authLimiter, async (req, res) => {\n  \u002F\u002F 1. Validate input\n  const { email, password } = validateLoginInput(req.body);\n\n  \u002F\u002F 2. Authenticate — parameterized query, constant-time compare\n  const user = await getUserByEmail(email);\n  if (!user || !(await verifyPassword(password, user.passwordHash))) {\n    \u002F\u002F Generic message — do not reveal whether email exists\n    return res.status(401).json({ error: 'Invalid credentials' });\n  }\n\n  \u002F\u002F 3. Authorize — issue scoped, short-lived token\n  const token = jwt.sign(\n    { sub: user.id, role: user.role },\n    JWT_SECRET,\n    { algorithm: 'HS256', expiresIn: '15m', issuer: 'your-app', audience: 'your-app' }\n  );\n\n  \u002F\u002F 4. Secure response — token in httpOnly cookie, not body\n  res.cookie('token', token, { httpOnly: true, secure: true, sameSite: 'strict' });\n  return res.json({ message: 'Authenticated' });\n});\n```\n\n## Output Templates\n\nWhen implementing security features, provide:\n1. Secure implementation code\n2. Security considerations noted\n3. Configuration requirements (env vars, headers)\n4. Testing recommendations\n\n## Knowledge Reference\n\nOWASP Top 10, bcrypt\u002Fargon2, JWT, OAuth 2.0, OIDC, CSP, CORS, rate limiting, input validation, output encoding, encryption (AES, RSA), TLS, security headers\n\n[Documentation](https:\u002F\u002Fjeffallan.github.io\u002Fclaude-skills\u002Fskills\u002Fsecurity\u002Fsecure-code-guardian\u002F)\n",{"name":5,"license":15,"metadata":24,"description":7},{"role":25,"scope":26,"author":27,"domain":28,"version":29,"triggers":30,"output-format":31,"related-skills":32},"specialist","implementation","https:\u002F\u002Fgithub.com\u002FJeffallan","security","1.1.0","security, authentication, authorization, encryption, OWASP, vulnerability, secure coding, password, JWT, OAuth","code","fullstack-guardian, security-reviewer, architecture-designer","main","8859218955d9504cd18b59e7892100718039d3b4","data\u002Fskills\u002Fjeffallan-claude-skills\u002Fsecure-code-guardian\u002Fskills\u002Fsecure-code-guardian",1,"https:\u002F\u002Fgithub.com\u002Fom-scogo\u002Fskillsh-scraper","https:\u002F\u002Fgithub.com\u002Fom-scogo","SDE-1 @ Scogo ","2026-07-18 12:22:46",{"source":8,"skillName":5,"commands":42,"prompt":52,"zipAvailable":53},[43,46,49],{"tool":44,"command":45},"npx","npx skills add om-scogo\u002Fskillsh-scraper --skill secure-code-guardian",{"tool":47,"command":48},"bunx","bunx skills add om-scogo\u002Fskillsh-scraper --skill secure-code-guardian",{"tool":50,"command":51},"pnpm","pnpm dlx skills add om-scogo\u002Fskillsh-scraper --skill secure-code-guardian","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fom-scogo\u002Fskillsh-scraper\u002Fblob\u002Fmain\u002Fdata\u002Fskills\u002Fjeffallan-claude-skills\u002Fsecure-code-guardian\u002Fskills\u002Fsecure-code-guardian\u002FSKILL.md",true,[],[56,63,68,75,80,87],{"skillNo":57,"name":58,"nameZh":6,"description":59,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":60,"categories":61,"keywords":62,"publishedAt":19},"01M7D6MC9FAAEV4CMNYX8W7JTG","arxiv-search","Search arXiv physics, math, and computer science preprints using natural language queries. Powered by Valyu semantic search.","https:\u002F\u002Fgithub.com\u002Fom-scogo\u002Fskillsh-scraper\u002Fblob\u002Fmain\u002Fdata\u002Fskills\u002Fyorkeccak-scientific-skills\u002Farxiv-search\u002Fskills\u002Farxiv-search\u002FSKILL.md",[],[],{"skillNo":64,"name":58,"nameZh":6,"description":59,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":65,"categories":66,"keywords":67,"publishedAt":19},"01M7D6M85CKKN87TA98VCQV4H7","https:\u002F\u002Fgithub.com\u002Fom-scogo\u002Fskillsh-scraper\u002Fblob\u002Fmain\u002Fdata\u002Fskills\u002Fyorkeccak-scientific-skills\u002Farxiv-search\u002FSkill.md",[],[],{"skillNo":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":74,"publishedAt":19},"01M7D4ZTCS4DR3CE4JY06X84T2","working-with-legacy-code","Safely change and test untested codebases using Feathers' \"Working Effectively with Legacy Code\". Use when the user mentions \"legacy code\", \"no tests\", \"untested codebase\", \"how do I test this\", \"seams\", \"characterization tests\", \"golden master\", \"sprout method\", \"afraid to change this code\", \"monster method\", \"dependency breaking\", or \"inherited a messy codebase\". Also trigger when changing code without tests safely, getting a class under test when constructors, statics, or singletons block it, adding features to tangled modules, or planning incremental test coverage for an old codebase. Covers the legacy-code change algorithm, seams, characterization tests, sprout\u002Fwrap, and dependency-breaking techniques. For refactoring code that already has tests, see refactoring-patterns. For day-to-day code quality, see clean-code.","https:\u002F\u002Fgithub.com\u002Fom-scogo\u002Fskillsh-scraper\u002Fblob\u002Fmain\u002Fdata\u002Fskills\u002Fwondelai-skills\u002Fworking-with-legacy-code\u002Fworking-with-legacy-code\u002FSKILL.md",[],[],{"skillNo":76,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":79,"publishedAt":19},"01M7D4ZHZKJD2RSNGAF63V14P4","https:\u002F\u002Fgithub.com\u002Fom-scogo\u002Fskillsh-scraper\u002Fblob\u002Fmain\u002Fdata\u002Fskills\u002Fwondelai-skills\u002Fworking-with-legacy-code\u002FSkill.md",[],[],{"skillNo":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":86,"publishedAt":19},"01M7D4ZB4CJBFW5JE67CPH2QRV","web-typography","Select, pair, and implement typefaces for web projects. Use when the user mentions \"font pairing\", \"which typeface\", \"line height\", \"responsive typography\", \"web font loading\", \"type hierarchy\", \"variable fonts\", \"FOUT\u002FFOIT\", \"typographic scale\", or \"the text is hard to read\". Also trigger when choosing between system fonts and web fonts, optimizing font-loading performance, or designing readable long-form content. Covers readability evaluation, CSS implementation, and performance optimization. For overall UI design systems, see refactoring-ui. For dramatic typographic experiences, see top-design.","https:\u002F\u002Fgithub.com\u002Fom-scogo\u002Fskillsh-scraper\u002Fblob\u002Fmain\u002Fdata\u002Fskills\u002Fwondelai-skills\u002Fweb-typography\u002Fweb-typography\u002FSKILL.md",[],[],{"skillNo":88,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":89,"categories":90,"keywords":91,"publishedAt":19},"01M7D4Z4MVYVY3NMJ18BNV6WNA","https:\u002F\u002Fgithub.com\u002Fom-scogo\u002Fskillsh-scraper\u002Fblob\u002Fmain\u002Fdata\u002Fskills\u002Fwondelai-skills\u002Fweb-typography\u002FSkill.md",[],[]]