claude-api
Build with Claude Messages API using structured outputs (v0.69.0+, Nov 2025) for guaranteed JSON schema validation.
Skill by ovachiever
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/ovachiever-claude-api
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: backend, agent-building
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
- Runs as
- Node.js package
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/claude-api
What's inside
- Skill name
claude-api- Description
- Build with Claude Messages API using structured outputs (v0.69.0+, Nov 2025) for guaranteed JSON schema validation. Covers prompt caching (90% savings), streaming SSE, tool use, model deprecations (3.5/3.7 retired Oct 2025). Use when: building chatbots/agents with validated JSON responses, or troubleshooting rate_limit_error, structured output validation, prompt caching not activating, streaming SSE parsing.
- License
- MIT
- Metadata
- version: 2.0.0 · sdk_version: 0.70.1 · last_verified: 2025-11-22 · token_savings: ~48% · breaking_changes: Oct 2025 - Claude 3.5/3.7 models retired, Nov 2025 - Structured outputs beta · errors_prevented: 12
- Instructions
- 488 lines in SKILL.md · view on GitHub
Before installing
- Ships executable scripts
Files (23)
- plugin.json · .claude-plugin/
- README.md
- SKILL.md
- api-reference.md · references/
- prompt-caching-guide.md · references/
- rate-limits.md · references/
- tool-use-patterns.md · references/
- top-errors.md · references/
- vision-capabilities.md · references/
- check-versions.sh · scripts/
- basic-chat.ts · templates/
- cloudflare-worker.ts · templates/
- error-handling.ts · templates/
- extended-thinking.ts · templates/
- nextjs-api-route.ts · templates/
- nodejs-example.ts · templates/
- package.json · templates/
- prompt-caching.ts · templates/
- streaming-chat.ts · templates/
- tool-use-advanced.ts · templates/
- tool-use-basic.ts · templates/
- vision-image.ts · templates/
- wrangler.jsonc · templates/
SKILL.md (first lines)
# Claude API - Structured Outputs & Error Prevention Guide
**Package**: @anthropic-ai/sdk@0.70.1 (Nov 20, 2025)
**Breaking Changes**: Oct 2025 - Claude 3.5/3.7 models retired, Nov 2025 - Structured outputs beta
**Last Updated**: 2025-11-22
---
## What's New in v0.69.0+ (Nov 2025)
**Major Features:**
### 1. Structured Outputs (v0.69.0, Nov 14, 2025) - CRITICAL ⭐
**Guaranteed JSON schema conformance** - Claude's responses strictly follow your JSON schema with two modes:
**JSON Outputs (`output_format`)** - For data extraction and formatting:
```typescript
import Anthropic from '@anthropic-ai/sdk';
const anthropic = new Anthropic({
apiKey: process.env.ANTHROPIC_API_KEY,
});
const message = await anthropic.messages.create({
model: 'claude-sonnet-4-5-20250929',
max_tokens: 1024,
messages: [{ role: 'user', content: 'Extract contact info: John Doe, john@example.com, 555-1234' }],
betas: ['structured-outputs-2025-11-13'],
output_format: {
type: 'json_schema',
json_schema: {
name: 'Contact',
strict: true,
schema: {
type: 'object',
properties: {
name: { type: 'string' },
email: { type: 'string' },
phone: { type: 'string' }
},
required: ['name', 'email', 'phone'],
additionalProperties: false
}
}
}
});
// Guaranteed valid JSON matching schema
const contact = JSON.parse(message.content[0].text);
console.log(contact.name); // "John Doe"
```
**Strict Tool Use (`strict: true`)** - For validated function parameters:
```typescript
const message = await anthropic.messages.create({
model: 'claude-sonnet-4-5-20250929',
max_tokens: 1024,
messages: [{ role: 'user', content: 'Get weather for San Francisco' }],
betas: ['structured-outputs-2025-11-13'],
tools: [{
name: 'get_weather',
description: 'Get current weather',
input_schema: {
type: 'object',
properties: {
location: { type: 'string' },
unit: { type: 'string', enum: ['celsius', 'fahrenheit'] }
},
required: ['location'],
additionalProperties: false
},
strict: true // ← Guarantees schema compliance
}]
});
```
**Requirements:**
- **Beta header**: `structured-outputs-2025-11-13` (via `betas` array)
- **Models**: Claude Sonnet 4.5, Claude Opus 4.1 only
- **SDK**: v0.69.0+ required
**Limitations:**
- ❌ No recursive schemas
- ❌ No numerical constraints (`minimum`, `maximum`)
- ❌ Limited regex support (no backreferences/lookahead)
- ❌ Incompatible with citations and message prefilling
- ⚠️ Grammar compilation adds latency on first request (cached 24hrs)
**When to Use:**
- Data extraction from unstructured text
- API response formatting
- Agentic workflows requiring validated tool inputs
- Eliminating JSON parse errors
### 2. Model Changes (Oct 2025) - BREAKING
**Retired (return errors):**
- ❌ Claude 3.5 Sonnet (all versions)
- ❌ Claude 3.7 Sonnet - DEPRECATED (Oct 28, 2025)
**Active Models (Nov 2025):**
| Model | ID | Context | Best For | Cost (per MTok) |
|-------|-----|---------|----------|-----------------|
| **Claude Sonnet 4.5** | claude-sonnet-4-5-20250929 | 200k | Balanced performance | $3/$15 (in/out) |
| **Claude Opus 4** | claude-opus-4-20250514 | 200k | Highest capability | $15/$75 |
| **Claude Haiku 4.5** | claude-3-5-haiku-20241022 | 200k | Near-frontier, fast | $1/$5 |
### 3. Context Management (Oct 28, 2025)
**Clear Thinking Blocks** - Automatic thinking block cleanup:
```typescript
const message = await anthropic.messages.create({
model: 'claude-sonnet-4-5-20250929',
max_tokens: 4096,
messages: [{ role: 'user', content: 'Solve complex problem' }],
betas: ['clear_thinking_20251015']
});From ovachiever/droid-tings, MIT.
More from ovachiever/droid-tings
- 0.514score
auto-animate
ovachiever
Zero-config animations for React, Vue, Solid, Svelte, Preact with @formkit/auto-animate (3.28kb).
SkillDFreshness: D★ 55Claude Code +9 - 0.514score
clerk-auth
ovachiever
Clerk auth with API version 2025-11-10 breaking changes (billing endpoints, payment_source→payment_method), Next.js v6 async auth(), PKCE for custom OAuth…
SkillDFreshness: D★ 55Claude Code +9 - 0.514score
ai-sdk-ui
ovachiever
Build React chat interfaces with Vercel AI SDK v5/v6.
SkillDFreshness: D★ 55Claude Code +9 - 0.509score
capa-officer
ovachiever
Senior CAPA Officer specialist for managing Corrective and Preventive Actions within Quality Management Systems.
SkillDFreshness: D★ 55Claude Code +9 - 0.506score
biopython
ovachiever
Primary Python toolkit for molecular biology.
SkillDFreshness: D★ 55Claude Code +9 - 0.506score
agile-product-owner
ovachiever
Agile product ownership toolkit for Senior Product Owner including INVEST-compliant user story generation, sprint planning, backlog management, and velocity…
SkillDFreshness: D★ 55Claude Code +9 - 0.506score
bioservices
ovachiever
Primary Python tool for 40+ bioinformatics services.
SkillDFreshness: D★ 55Claude Code +9 - 0.506score
chembl-database
ovachiever
Query ChEMBL's bioactive molecules and drug discovery data.
SkillDFreshness: D★ 55Claude Code +9 - 0.505score
ai-sdk-core
ovachiever
Build backend AI with Vercel AI SDK v5/v6.
SkillDFreshness: D★ 55Claude Code +9 - 0.504score
api-documenter
ovachiever
Auto-generate API documentation from code and comments.
SkillDFreshness: D★ 55Claude Code +9 - 0.501score
claude-agent-sdk
ovachiever
Build autonomous AI agents with Claude Agent SDK.
SkillDFreshness: D★ 55Claude Code +9 - 0.501score
better-auth
ovachiever
Build authentication systems for TypeScript/Cloudflare Workers with social auth, 2FA, passkeys, organizations, and RBAC.
SkillDFreshness: D★ 55Claude Code +9
Signals
- Stars
- 55
- Forks
- 5
- Open issues
- 1
- Last commit (this folder)
- Nov 24, 2025 (11 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- Version
- 2.0.0
- License
- MIT
- Repository
- github.com/ovachiever/droid-tings
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from ovachiever
- 0.514score
auto-animate
ovachiever
Zero-config animations for React, Vue, Solid, Svelte, Preact with @formkit/auto-animate (3.28kb).
SkillDFreshness: D★ 55Claude Code +9 - 0.514score
clerk-auth
ovachiever
Clerk auth with API version 2025-11-10 breaking changes (billing endpoints, payment_source→payment_method), Next.js v6 async auth(), PKCE for custom OAuth…
SkillDFreshness: D★ 55Claude Code +9 - 0.514score
ai-sdk-ui
ovachiever
Build React chat interfaces with Vercel AI SDK v5/v6.
SkillDFreshness: D★ 55Claude Code +9 - 0.509score
capa-officer
ovachiever
Senior CAPA Officer specialist for managing Corrective and Preventive Actions within Quality Management Systems.
SkillDFreshness: D★ 55Claude Code +9 - 0.506score
biopython
ovachiever
Primary Python toolkit for molecular biology.
SkillDFreshness: D★ 55Claude Code +9 - 0.506score
bioservices
ovachiever
Primary Python tool for 40+ bioinformatics services.
SkillDFreshness: D★ 55Claude Code +9
Cite this page
claude-api skill. Agent Mart. https://agentmart.dev/skills/ovachiever-claude-api (last updated 2026-10-24)