Llm Patterns

What the source does

• FilesystemNone observedNo reads or writes in the source
• NetworkNone observedNo outbound calls in the source
• ShellNone observedNo commands run in the source
• DependenciesPinnedNothing floats
• SecretsNone foundNo keys in source

Five audit layers

Gates applied: no behavioural pass.

Audit 0.4.1 · source sha ea59a0c53d79 · 14 Oct 2026Report an issue or request a re-scan

• Publisheralinaqi GitHub userOwner of the repository this skill is read from
• Source folderalinaqi/claude-bootstrap/skills/llm-patternsThe exact folder we audited
• LicenceMITAs the repository states it
• Commit pinned for this verdictea59a0c53d79A new audit runs when the source changes
• Repository statusNot archivedPushed today
• Sandboxed runNot runSkills are read, not executed; layer L4 is skipped

Its description: AI-first application patterns, LLM testing, prompt management

---
name: llm-patterns
description: AI-first application patterns, LLM testing, prompt management
when-to-use: When building apps where LLMs handle core logic - classification, extraction, generation
user-invocable: false
effort: medium
---

# LLM Patterns Skill


For AI-first applications where LLMs handle logical operations.

---

## Core Principle

**LLM for logic, code for plumbing.**

Use LLMs for:
- Classification, extraction, summarization
- Decision-making with natural language reasoning
- Content generation and transformation
- Complex conditional logic that would be brittle in code

Use traditional code for:
- Data validation (Zod/Pydantic)
- API routing and HTTP handling
- Database operations
- Authentication/authorization
- Orchestration and error handling

---

## Project Structure

```
project/
├── src/
│   ├── core/
│   │   ├── prompts/           # Prompt templates
│   │   │   ├── classify.ts
│   │   │   └── extract.ts
│   │   ├── llm/               # LLM client and utilities
│   │   │   ├── client.ts      # LLM client wrapper
│   │   │   ├── schemas.ts     # Response schemas (Zod)
│   │   │   └── index.ts
│   │   └── services/          # Business logic using LLM
│   ├── infra/
│   └── ...
├── tests/
│   ├── unit/
│   ├── integration/
│   └── llm/                   # LLM-specific tests
│       ├── fixtures/          # Saved responses for deterministic tests
│       ├── evals/             # Evaluation test suites
│       └── mocks/             # Mock LLM responses
└── _project_specs/
    └── prompts/               # Prompt specifications
```

---

## LLM Client Pattern

### Typed LLM Wrapper
```typescript
// core/llm/client.ts
import Anthropic from '@anthropic-ai/sdk';
import { z } from 'zod';

const client = new Anthropic();

interface LLMCallOptions<T> {
  prompt: string;
  schema: z.ZodSchema<T>;
  model?: string;
  maxTokens?: number;
}

export async function llmCall<T>({
  prompt,
  schema,
  model = 'claude-sonnet-4-6',
  maxTokens = 1024,
}: LLMCallOptions<T>): Promise<T> {
  const response = await client.messages.create({
    model,
    max_tokens: maxTokens,
    messages: [{ role: 'user', content: prompt }],
  });

  const text = response.content[0].type === 'text'
    ? response.content[0].text
    : '';

  // Parse and validate response
  const parsed = JSON.parse(text);
  return schema.parse(parsed);
}
```

### Structured Outputs
```typescript
// core/llm/schemas.ts
import { z } from 'zod';

export const ClassificationSchema = z.object({
  category: z.enum(['support', 'sales', 'feedback', 'other']),
  confidence: z.number().min(0).max(1),
  reasoning: z.string(),
});

export type Classification = z.infer<typeof ClassificationSchema>;
```

---

## Prompt Patterns

### Template Functions
```typescript
// core/prompts/classify.ts
export function classifyTicketPrompt(ticket: string): string {
  return `Classify this support ticket into one of these categories:
- support: Technical issues or help requests
- sales: Pricing, plans, or purchase inquiries
- feedback: Suggestions or complaints
- other: Anything else

Respond with JSON:
{
  "category": "...",
  "confidence": 0.0-1.0,
  "reasoning": "brief explanation"
}

Ticket:
${ticket}`;
}
```

### Prompt Versioning
```typescript
// core/prompts/index.ts
export const PROMPTS = {
  classify: {
    v1: classifyTicketPromptV1,
    v2: classifyTicketPromptV2,  // improved accuracy
    current: classifyTicketPromptV2,
  },
} as const;
```

---

## Testing LLM Calls

### 1. Unit Tests with Mocks (Fast, Deterministic)
```typescript
// tests/llm/mocks/classify.mock.ts
export const mockClassifyResponse = {
  category: 'support',
  confidence: 0.95,
  reasoning: 'User is asking for help with login',
};

// tests/unit/services/ticket.test.ts
import { classifyTicket } from '../../../src/core/services/ticket';
import { mockClassifyResponse } from '../../llm/mocks/classify.mock';

// Mock the LLM client
vi.mock('../../../src/core/llm/client', () => ({
  llmCall: vi.fn().mockResolvedValue(mockClassifyResponse),
}));

describe('classifyTicket', () => {
  it('returns classification for ticket', async () => {
    const result = await classifyTicket('I cannot log in');

    expect(result.category).toBe('support');
    expect(result.confidence).toBeGreaterThan(0.9);
  });
});
```

### 2. Fixture Tests (Deterministic, Tests Parsing)
```typescript
// tests/llm/fixtures/classify.fixtures.json
{
  "support_ticket": {
    "input": "I can't reset my password",
    "expected_category": "support",
    "raw_response": "{\"category\":\"support\",\"confidence\":0.98,\"reasoning\":\"Password reset is a support issue\"}"
  }
}

// tests/llm/classify.fixture.test.ts
import fixtures from './fixtures/classify.fixtures.json';
import { ClassificationSchema } from '../../src/core/llm/schemas';

describe('Classification Response Parsing', () => {
  Object.entries(fixtures).forEach(([name, fixture]) => {
    it(`parses ${name} correctly`, () => {
      const parsed = JSON.parse(fixture.raw_response);
      const result = ClassificationSchema.parse(parsed);

      expect(result.category).toBe(fixture.expected_category);
    });
  });
});
```

### 3. Evaluation Tests (Slow, Run in CI nightly)
```typescript
// tests/llm/evals/classify.eval.test.ts
import { classifyTicket } from '../../../src/core/services/ticket';

const TEST_CASES = [
  { input: 'How much does the pro plan cost?', expected: 'sales' },
  { input: 'The app crashes when I click save', expected: 'support' },
  { input: 'You should add dark mode', expected: 'feedback' },
  { input: 'What time is it in Tokyo?', expected: 'other' },
];

describe('Classification Accuracy (Eval)', () => {
  // Skip in regular CI, run nightly
  const runEvals = process.env.RUN_LLM_EVALS === 'true';

  it.skipIf(!runEvals)('achieves >90% accuracy on test set', async () => {
    let correct = 0;

    for (const testCase of TEST_CASES) {
      const result = await classifyTicket(testCase.input);
      if (result.category ===

Excerpt, first 6,000 characters of SKILL.md, verbatim from the audited commit. It is text from someone else’s repository, quoted so you can judge it before your agent reads it.

git clone https://github.com/alinaqi/claude-bootstrap
git -C claude-bootstrap checkout ea59a0c53d79

Works in

1. 2026-10-14
   ✓SAFE B 89 / 100

   first audit · source ea59a0c53d79

Questions about Llm Patterns

• github.com/alinaqi/claude-bootstrap/tree/main/skills/llm-pattern — the audited source at commit ea59a0c53d79 and every finding aboveObserved · 14 Oct 2026

Spotted something wrong? Report a correction · Methodology