Files
personamanagmentlayer__pcl/stdlib/cloud/cloudflare-expert/SKILL.md
ANGX 4e07a6a874 feat(stdlib)!: Agent Skills v1.0 conformance, resolver fix, and 17 new skills (#43)
* chore(stdlib): add conformance tooling for the skills library

The library had no gate that could express what a valid skill is, so
malformed frontmatter, over-budget files and credential literals went
unnoticed. These scripts define and enforce that contract.

- validate-skills.py: extend with Agent Skills v1.0 conformance -
  naming rules and directory agreement, an explicit activation trigger
  in the description, canonical layout, the 500-line SKILL.md budget,
  relative-link integrity, and two security rules (no unrestricted
  Bash(*) grant, no credential literals). Structural checks now read a
  skill as a whole so material moved into references/ still counts.
- split-skill-references.py: move the heaviest sections of an oversized
  SKILL.md into references/. Verifies line by line that every source
  line lands in exactly one output and refuses to write otherwise.
- generate-skill-inventory.py: derive SKILLS_INVENTORY.md and
  DIRECTORY_STRUCTURE.md from the tree so they cannot drift.
- generate-skill-catalog.py: index the canonical layout only, count
  references/ toward a skill's size, and stop truncating descriptions
  at 200 characters - the catalog is the discovery surface and must
  carry the activation trigger.
- .gitignore: Python bytecode from these scripts, and local .pcl state.

Reviewed-by: Security Analyst, Compiler Engineer, DevX Engineer

* fix(stdlib): bring all 174 skills to Agent Skills v1.0 conformance

No skill in the library was conformant. 41 of 175 failed the existing
validator outright, and none satisfied the spec. This pass fixes the
tree and records the result. See stdlib/CHANGELOG.md for the per-skill
versioning and migration notes.

BREAKING CHANGE: one skill removed, five moved, seven with a capability
withdrawn. Library version 2.0.0 -> 3.0.0.

Structure
- Convert 71 skills stored as flat files to <category>/<name>/SKILL.md,
  the layout the spec requires and the only one able to carry companion
  resources.
- Rename 5 directories that disagreed with their declared name:, so
  resolution by path and by name stop giving different answers. The
  repository docs already referenced the corrected paths.
- Merge the duplicate legal-technology skills into legaltech-expert and
  delete legal-tech-expert, carrying over everything the survivor
  lacked.

Metadata
- Repair 20 unparseable frontmatters: an H1 preceded the --- block and
  the key was skill_id: instead of name:, so any parser reading
  frontmatter at offset 0 saw no metadata at all. The objectives,
  prerequisites and outcome they carried become real body sections.
- Add the missing version: to 21 skills, fold keywords into tags, move
  expertise_level under metadata, and align 10 category: values with
  their directory.

Discoverability
- Give all 174 descriptions an explicit "Use when ..." trigger, built
  from each skill's own tags and section headings. 152 previously said
  only what the skill was about, leaving an agent nothing to match on.

Progressive disclosure
- Split 127 oversized skills, moving bulk material into references/ read
  on demand and leaving an index behind. A SKILL.md now averages 277
  lines instead of 644 and none exceeds 500. Verified lossless line by
  line against the previous revision.

Security
- Withdraw the unrestricted Bash(*) grant from 7 skills; none of the six
  non-financial ones contained a single shell command. finance-expert
  documents code that charges cards and reads bank accounts, so it now
  grants no shell at all.
- Remove credential literals: Stripe keys, two JWT signing keys, an
  Express session secret, a Redis password and WiFi credentials, all
  inlined in examples. They load from the environment now.
- finance-expert: idempotency keys were documented but absent, so a
  retry double-charged; webhook signature failures were not caught, so a
  forged event raised uncaught instead of being rejected;
  int(amount * 100) truncated fractions of a cent. All fixed, plus a
  money-movement guardrails section.
- trading-expert: place_order routed without any pre-trade risk check
  although a RiskManager sat unused in the next section. Risk validation
  now runs before routing and raises rather than returning a boolean a
  caller can ignore; live routing is opt-in.
- Correct an Ansible Vault example that showed plaintext under an
  "encrypted" label.

Also fixes 8 broken documentation links and a prematurely closed code
fence in skill-creator-expert that leaked template content into prose.

Per the repository file-organization policy, four stale progress reports
(SKILLS_MANIFEST, COMPLETE_SKILLS_LIBRARY, COMPLETE_LIBRARY_MANIFEST,
PHASE_3_DATA_ANALYTICS) move out of stdlib/ into the gitignored
.roadmap/status/stdlib/; they claimed 31 of 100 skills complete. They
appear here as deletions because .roadmap/ is not tracked.

Reviewed-by: Security Analyst, Language Designer, DevX Engineer,
             Documentation Specialist

* fix(skills): resolve standard library skills from their real layout

No stdlib skill was resolvable. SkillResolver looked for
`<stdlibDir>/<name>.md` with stdlibDir defaulting to `stdlib/skills`, a
directory that does not exist, and the path ignored the category level
the library actually uses. The two LSP providers had the same wrong
directory and scanned only one level deep, so neither completion nor
go-to-definition could see a skill either.

- skill-discovery.ts: enumerate skill entry points across the shapes in
  use - a flat `<name>.md`, `<name>/SKILL.md`, and
  `<category>/<name>/SKILL.md` - while skipping references/, scripts/
  and assets/, which hold supporting material rather than entry points.
- skill-resolver.ts: point stdlibDir at `stdlib`, and look the name up
  as a directory under any category as well as the two legacy shapes, so
  existing custom stdlib directories keep working. The name is used as a
  single path segment and rejected if it contains a separator or
  traversal, so a reference cannot escape the stdlib root.
- Rewire both LSP providers onto the shared discovery helper.

Tests: 13 new cases covering the layouts, ordering, the references/
exclusion, path-traversal rejection, and an integration test that
resolves real shipped skills by bare name.

Reviewed-by: Compiler Engineer, Runtime Architect, Security Analyst

* feat(stdlib): add 17 skills covering the library's largest gaps

Selection was driven by cross-referencing coverage against observed usage
rather than by intuition: Stack Overflow and GitHub Octoverse data for
which technologies matter, and install rankings on public agent-skill
registries for the shape of skills people actually use.

That comparison found a mismatch of form, not only of coverage. The
most-installed skills in the ecosystem are procedures - tdd, refactoring,
frontend design, browser automation - while all 174 existing skills were
domain knowledge shaped as <domain>-expert. The new workflows/ category
closes that gap and introduces the <activity>-workflow convention.

New category workflows/ (4)
- tdd-workflow, refactoring-workflow, debugging-workflow,
  code-review-workflow. code-review-workflow complements rather than
  replaces code-review-expert: procedure versus judgement. Merge them if
  the split proves confusing in use.

Applied AI (3) - the largest coverage gap
- llm-engineering-expert, rag-expert, agent-engineering-expert.
  The library referenced LLMs in tags but covered none of it: pgvector
  appeared zero times across 174 skills, LangChain once, MCP twice
  despite the repository shipping an MCP integration guide.

Capabilities (2)
- document-processing-expert (PDF, DOCX, XLSX, PPTX in one skill),
  browser-automation-expert (a client against third-party sites,
  distinct from playwright-expert which tests your own application).

Data (3)
- mysql-expert, the second most used database and previously absent
  while rarer stores had skills; analytical-databases-expert;
  stream-processing-expert.

Security (3)
- secrets-management-expert, supply-chain-security-expert (OWASP A03
  2025), identity-access-expert (OWASP A01).

Interface and meta (2)
- accessibility-expert: design/ held only design-expert, which despite
  its name covers software architecture, so WCAG had no home.
- skill-router: find and compose skills across 191, with a
  disambiguation table for overlapping pairs.

Grouping by decision context rather than by technology keeps the growth
to 17 skills for roughly 50 topics. Five vector stores live inside
rag-expert; four document formats inside document-processing-expert.
Per-tool depth sits in references/, which the progressive-disclosure work
in 3.0.0 made cheap.

Four further gaps are better served by extending existing skills -
PyTorch and TensorFlow in ml-expert, OpenTelemetry in monitoring-expert,
Pulumi and Crossplane in terraform-expert - and are not in this change.

Library 3.0.0 -> 3.1.0, additive only. Adds the workflows label to the
inventory generator; catalogue, inventory, structure and CHANGELOG
regenerated.

Reviewed-by: Product Strategist, Security Analyst, DevX Engineer,
             Documentation Specialist

* fix(test): create test directories with mkdtempSync

CodeQL flagged js/insecure-temporary-file (CWE-377) on both suites.
`join(tmpdir(), <predictable name>)` followed by mkdirSync creates a
world-readable directory at a guessable path, so another local user can
pre-create it or plant a symlink between the name being computed and the
directory being created.

mkdtempSync creates the directory atomically with a random suffix and
0700 permissions, which closes both the disclosure and the race.

One occurrence is new in this branch (skill-discovery); the other
pre-dates it in skill-resolver and is fixed in the same pass rather than
left as a known finding in a file this branch already touches.
2026-09-05 04:35:30 +02:00

9.2 KiB

name, version, description, category, tags, allowed-tools
name version description category tags allowed-tools
cloudflare-expert 1.1.0 Expert-level Cloudflare Workers, CDN, edge computing, and security services. Use when the user mentions edge computing, CDN, workers, or WAF, or when the task involves Cloudflare Services or Developer Tools. cloud
cloudflare
edge-computing
cdn
workers
waf
Read
Write
Edit
Bash(wrangler:*)

Cloudflare Expert

Expert guidance for Cloudflare Workers, edge computing, CDN optimization, and Cloudflare security services.

Core Concepts

Cloudflare Services

  • Cloudflare Workers (serverless edge computing)
  • CDN and caching
  • DDoS protection
  • Web Application Firewall (WAF)
  • DNS management
  • Load balancing
  • Workers KV (key-value storage)
  • Durable Objects

Edge Computing

  • Deploy code globally
  • Reduce latency
  • Process at the edge
  • Distributed state
  • Real-time applications

Developer Tools

  • Wrangler CLI
  • Workers Playground
  • Edge APIs
  • Analytics and logs

Cloudflare Workers

// Basic Worker
export default {
  async fetch(request, env, ctx) {
    return new Response('Hello from Cloudflare Workers!', {
      headers: { 'Content-Type': 'text/plain' }
    });
  }
};

// Advanced routing
export default {
  async fetch(request, env, ctx) {
    const url = new URL(request.url);

    // Route based on path
    switch (url.pathname) {
      case '/api/users':
        return handleUsers(request, env);
      case '/api/posts':
        return handlePosts(request, env);
      default:
        return new Response('Not Found', { status: 404 });
    }
  }
};

// API endpoint with JSON
async function handleUsers(request, env) {
  if (request.method === 'GET') {
    const users = await env.USERS_KV.get('users', { type: 'json' });
    return new Response(JSON.stringify(users), {
      headers: { 'Content-Type': 'application/json' }
    });
  }

  if (request.method === 'POST') {
    const body = await request.json();
    await env.USERS_KV.put('users', JSON.stringify(body));
    return new Response('Created', { status: 201 });
  }

  return new Response('Method Not Allowed', { status: 405 });
}

Workers KV Storage

// Workers KV operations
export default {
  async fetch(request, env, ctx) {
    // Write
    await env.MY_KV.put('key', 'value');

    // Write with metadata and expiration
    await env.MY_KV.put('key', 'value', {
      metadata: { userId: '123' },
      expirationTtl: 3600 // 1 hour
    });

    // Read
    const value = await env.MY_KV.get('key');

    // Read as JSON
    const jsonValue = await env.MY_KV.get('key', { type: 'json' });

    // Read with metadata
    const { value, metadata } = await env.MY_KV.getWithMetadata('key');

    // Delete
    await env.MY_KV.delete('key');

    // List keys
    const keys = await env.MY_KV.list({ prefix: 'user:' });

    return new Response(JSON.stringify({ value, keys }));
  }
};

// Caching pattern
class CachedAPI {
  constructor(kv) {
    this.kv = kv;
  }

  async get(key, fetcher, ttl = 3600) {
    // Try cache first
    const cached = await this.kv.get(key, { type: 'json' });
    if (cached) return cached;

    // Fetch and cache
    const data = await fetcher();
    await this.kv.put(key, JSON.stringify(data), {
      expirationTtl: ttl
    });

    return data;
  }
}

export default {
  async fetch(request, env, ctx) {
    const cache = new CachedAPI(env.MY_KV);

    const data = await cache.get('api:users', async () => {
      const response = await fetch('https://api.example.com/users');
      return response.json();
    }, 3600);

    return new Response(JSON.stringify(data));
  }
};

Caching Strategies

// Cache API
async function cacheFirst(request) {
  const cache = caches.default;
  let response = await cache.match(request);

  if (!response) {
    response = await fetch(request);
    // Cache for 1 hour
    response = new Response(response.body, response);
    response.headers.set('Cache-Control', 'max-age=3600');
    await cache.put(request, response.clone());
  }

  return response;
}

// Stale-while-revalidate
async function staleWhileRevalidate(request, ctx) {
  const cache = caches.default;
  let response = await cache.match(request);

  // Background refresh
  ctx.waitUntil(
    fetch(request).then((freshResponse) => {
      const clonedResponse = freshResponse.clone();
      cache.put(request, clonedResponse);
    })
  );

  if (response) {
    return response;
  }

  return fetch(request);
}

// Custom cache keys
function customCacheKey(request) {
  const url = new URL(request.url);

  // Ignore query parameters for caching
  url.search = '';

  // Add custom cache key based on headers
  const userAgent = request.headers.get('User-Agent');
  const isMobile = /mobile/i.test(userAgent);
  url.searchParams.set('device', isMobile ? 'mobile' : 'desktop');

  return new Request(url.toString(), request);
}

export default {
  async fetch(request, env, ctx) {
    const cacheKey = customCacheKey(request);

    if (request.url.includes('/api/')) {
      // API routes: stale-while-revalidate
      return staleWhileRevalidate(cacheKey, ctx);
    }

    // Static assets: cache first
    return cacheFirst(cacheKey);
  },
};

Edge Functions

// HTML rewriting
export default {
  async fetch(request, env, ctx) {
    const response = await fetch(request);

    // Inject analytics script
    return new HTMLRewriter()
      .on('head', new HeadInjector())
      .transform(response);
  }
};

class HeadInjector {
  element(element) {
    element.append(
      '<script>console.log("Injected at edge!");</script>',
      { html: true }
    );
  }
}

// Geolocation-based routing
export default {
  async fetch(request, env, ctx) {
    const country = request.cf.country;

    // Route based on country
    const apiEndpoint = {
      'US': 'https://us-api.example.com',
      'EU': 'https://eu-api.example.com',
      'default': 'https://global-api.example.com'
    }[country] || 'https://global-api.example.com';

    const url = new URL(request.url);
    const apiUrl = new URL(url.pathname, apiEndpoint);

    return fetch(apiUrl, request);
  }
};

// A/B testing
export default {
  async fetch(request, env, ctx) {
    const url = new URL(request.url);

    // Determine variant
    let variant = request.headers.get('Cookie')?.match(/variant=(\w+)/)?.[1];

    if (!variant) {
      variant = Math.random() < 0.5 ? 'A' : 'B';
    }

    // Fetch appropriate version
    const response = await fetch(`${url.origin}/variant-${variant}${url.pathname}`);

    // Set cookie
    const newResponse = new Response(response.body, response);
    newResponse.headers.set('Set-Cookie', `variant=${variant}; Path=/; Max-Age=86400`);

    return newResponse;
  }
};

Wrangler CLI

# Initialize project
wrangler init my-worker

# Development server
wrangler dev

# Deploy to production
wrangler publish

# Deploy to specific environment
wrangler publish --env production

# Tail logs
wrangler tail

# KV operations
wrangler kv:namespace create "MY_KV"
wrangler kv:key put --namespace-id=<id> "key" "value"
wrangler kv:key get --namespace-id=<id> "key"

# Durable Objects
wrangler publish --new-class Counter

# Secrets
wrangler secret put SECRET_NAME

wrangler.toml Configuration

name = "my-worker"
main = "src/index.js"
compatibility_date = "2024-01-01"

# KV bindings
kv_namespaces = [
  { binding = "MY_KV", id = "xxxxxxxx" },
  { binding = "CACHE_KV", id = "yyyyyyyy" }
]

# Durable Objects
[durable_objects]
bindings = [
  { name = "COUNTER", class_name = "Counter" },
  { name = "CHAT_ROOM", class_name = "ChatRoom" }
]

[[migrations]]
tag = "v1"
new_classes = ["Counter", "ChatRoom"]

# Environment variables
[vars]
ENVIRONMENT = "production"

# Routes
routes = [
  { pattern = "example.com/*", zone_name = "example.com" }
]

# Cron triggers
[triggers]
crons = ["0 */6 * * *"]

Best Practices

Performance

  • Cache aggressively at the edge
  • Minimize worker execution time
  • Use Workers KV for global data
  • Implement connection pooling
  • Optimize cache keys
  • Use stale-while-revalidate
  • Minimize external requests

Security

  • Validate all inputs
  • Implement rate limiting
  • Use secrets for sensitive data
  • Set security headers
  • Implement CORS properly
  • Use HTTPS everywhere
  • Log security events

Development

  • Use TypeScript for type safety
  • Test locally with wrangler dev
  • Implement proper error handling
  • Monitor worker metrics
  • Use environment variables
  • Version your workers
  • Document API endpoints

Anti-Patterns

❌ Storing large data in KV frequently ❌ Long-running computations in workers ❌ Not implementing caching ❌ Hardcoding secrets ❌ Ignoring rate limits ❌ No error handling ❌ Excessive external API calls

Reference Documentation

Detailed material lives alongside this skill and is read on demand:

Resources