Build apps with the Claude API / Anthropic SDKs (TypeScript, Python, Agent SDK), choosing the right surface and language-specific patterns; not for OpenAI or other providers. USE WHEN code imports anthropic/@anthropic-ai/sdk/claude_agent_sdk or a user asks to use the Claude API or Anthropic Agent SDK.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
A direct command skips the review prompt. Inspect the source before running it.
Build apps with the Claude API / Anthropic SDKs (TypeScript, Python, Agent SDK), choosing the right surface and language-specific patterns; not for OpenAI or other providers. USE WHEN code imports anthropic/@anthropic-ai/sdk/claude_agent_sdk or a user asks to use the Claude API or Anthropic Agent SDK.
cluster
ai-agents-meta
version
1.0.0
origin
antigravity-awesome-skills (MIT)
risk
unknown
source
https://github.com/anthropics/skills
date_added
2026-03-21
license
Complete terms in LICENSE.txt
Building LLM-Powered Applications with Claude
This skill helps you build LLM-powered applications with Claude. Choose the right surface based on your needs, detect the project language, then read the relevant language-specific documentation.
When to Use
Use when building with the Claude API, Anthropic SDKs, or the Agent SDK.
Use when code imports anthropic, @anthropic-ai/sdk, or related Claude SDK packages.
Do not use for general coding work unrelated to Claude integrations.
Defaults
Unless the user requests otherwise:
For the Claude model version, please use Claude Opus 4.6, which you can access via the exact model string claude-opus-4-6. Please default to using adaptive thinking (thinking: {type: "adaptive"}) for anything remotely complicated. And finally, please default to streaming for any request that may involve long input, long output, or high max_tokens โ it prevents hitting request timeouts. Use the SDK's .get_final_message() / .finalMessage() helper to get the complete response if you don't need to handle individual stream events
Language Detection
Before reading code examples, determine which language the user is working in:
*.ts, *.tsx, package.json, tsconfig.json โ TypeScript โ read from typescript/
*.js, *.jsx (no .ts files present) โ TypeScript โ JS uses the same SDK, read from typescript/
*.java, pom.xml, build.gradle โ Java โ read from java/
*.kt, *.kts, build.gradle.kts โ Java โ Kotlin uses the Java SDK, read from java/
, โ โ Scala uses the Java SDK, read from
*.scala
build.sbt
Java
java/
*.go, go.mod โ Go โ read from go/
*.rb, Gemfile โ Ruby โ read from ruby/
*.cs, *.csproj โ C# โ read from csharp/
*.php, composer.json โ PHP โ read from php/
If multiple languages detected (e.g., both Python and TypeScript files):
Check which language the user's current file or question relates to
If still ambiguous, ask: "I detected both Python and TypeScript files. Which language are you using for the Claude API integration?"
If language can't be inferred (empty project, no source files, or unsupported language):
Use AskUserQuestion with options: Python, TypeScript, Java, Go, Ruby, cURL/raw HTTP, C#, PHP
If AskUserQuestion is unavailable, default to Python examples and note: "Showing Python examples. Let me know if you need a different language."
If unsupported language detected (Rust, Swift, C++, Elixir, etc.):
Suggest cURL/raw HTTP examples from curl/ and note that community SDKs may exist
Offer to show Python or TypeScript examples as reference implementations
If user needs cURL/raw HTTP examples, read from curl/.
Language-Specific Feature Support
Language
Tool Runner
Agent SDK
Notes
Python
Yes (beta)
Yes
Full support โ @beta_tool decorator
TypeScript
Yes (beta)
Yes
Full support โ betaZodTool + Zod
Java
Yes (beta)
No
Beta tool use with annotated classes
Go
Yes (beta)
No
BetaToolRunner in toolrunner pkg
Ruby
Yes (beta)
No
BaseTool + tool_runner in beta
cURL
N/A
N/A
Raw HTTP, no SDK features
C#
No
No
Official SDK
PHP
No
No
Official SDK
Which Surface Should I Use?
Start simple. Default to the simplest tier that meets your needs. Single API calls and workflows handle most use cases โ only reach for agents when the task genuinely requires open-ended, model-driven exploration.
Use Case
Tier
Recommended Surface
Why
Classification, summarization, extraction, Q&A
Single LLM call
Claude API
One request, one response
Batch processing or embeddings
Single LLM call
Claude API
Specialized endpoints
Multi-step pipelines with code-controlled logic
Workflow
Claude API + tool use
You orchestrate the loop
Custom agent with your own tools
Agent
Claude API + tool use
Maximum flexibility
AI agent with file/web/terminal access
Agent
Agent SDK
Built-in tools, safety, and MCP support
Agentic coding assistant
Agent
Agent SDK
Designed for this use case
Want built-in permissions and guardrails
Agent
Agent SDK
Safety features included
Note: The Agent SDK is for when you want built-in file/web/terminal tools, permissions, and MCP out of the box. If you want to build an agent with your own tools, Claude API is the right choice โ use the tool runner for automatic loop handling, or the manual loop for fine-grained control (approval gates, custom logging, conditional execution).
Decision Tree
What does your application need?
1. Single LLM call (classification, summarization, extraction, Q&A)
โโโ Claude API โ one request, one response
2. Does Claude need to read/write files, browse the web, or run shell commands
as part of its work? (Not: does your app read a file and hand it to Claude โ
does Claude itself need to discover and access files/web/shell?)
โโโ Yes โ Agent SDK โ built-in tools, don't reimplement them
Examples: "scan a codebase for bugs", "summarize every file in a directory",
"find bugs using subagents", "research a topic via web search"
3. Workflow (multi-step, code-orchestrated, with your own tools)
โโโ Claude API with tool use โ you control the loop
4. Open-ended agent (model decides its own trajectory, your own tools)
โโโ Claude API agentic loop (maximum flexibility)
Should I Build an Agent?
Before choosing the agent tier, check all four criteria:
Complexity โ Is the task multi-step and hard to fully specify in advance? (e.g., "turn this design doc into a PR" vs. "extract the title from this PDF")
Value โ Does the outcome justify higher cost and latency?
Viability โ Is Claude capable at this task type?
Cost of error โ Can errors be caught and recovered from? (tests, review, rollback)
If the answer is "no" to any of these, stay at a simpler tier (single call or workflow).
Architecture
Everything goes through POST /v1/messages. Tools and output constraints are features of this single endpoint โ not separate APIs.
User-defined tools โ You define tools (via decorators, Zod schemas, or raw JSON), and the SDK's tool runner handles calling the API, executing your functions, and looping until Claude is done. For full control, you can write the loop manually.
Server-side tools โ Anthropic-hosted tools that run on Anthropic's infrastructure. Code execution is fully server-side (declare it in tools, Claude runs code automatically). Computer use can be server-hosted or self-hosted.
Structured outputs โ Constrains the Messages API response format (output_config.format) and/or tool parameter validation (strict: true). The recommended approach is client.messages.parse() which validates responses against your schema automatically. Note: the old output_format parameter is deprecated; use output_config: {format: {...}} on messages.create().
Supporting endpoints โ Batches (POST /v1/messages/batches), Files (POST /v1/files), and Token Counting feed into or support Messages API requests.
Current Models (cached: 2026-02-17)
Model
Model ID
Context
Input $/1M
Output $/1M
Claude Opus 4.6
claude-opus-4-6
200K (1M beta)
$5.00
$25.00
Claude Sonnet 4.6
claude-sonnet-4-6
200K (1M beta)
$3.00
$15.00
Claude Haiku 4.5
claude-haiku-4-5
200K
$1.00
$5.00
ALWAYS use claude-opus-4-6 unless the user explicitly names a different model. This is non-negotiable. Do not use claude-sonnet-4-6, claude-sonnet-4-5, or any other model unless the user literally says "use sonnet" or "use haiku". Never downgrade for cost โ that's the user's decision, not yours.
CRITICAL: Use only the exact model ID strings from the table above โ they are complete as-is. Do not append date suffixes. For example, use claude-sonnet-4-5, never claude-sonnet-4-5-20250514 or any other date-suffixed variant you might recall from training data. If the user requests an older model not in the table (e.g., "opus 4.5", "sonnet 3.7"), read shared/models.md for the exact ID โ do not construct one yourself.
A note: if any of the model strings above look unfamiliar to you, that's to be expected โ that just means they were released after your training data cutoff. Rest assured they are real models; we wouldn't mess with you like that.
Thinking & Effort (Quick Reference)
Opus 4.6 โ Adaptive thinking (recommended): Use thinking: {type: "adaptive"}. Claude dynamically decides when and how much to think. No budget_tokens needed โ budget_tokens is deprecated on Opus 4.6 and Sonnet 4.6 and must not be used. Adaptive thinking also automatically enables interleaved thinking (no beta header needed). When the user asks for "extended thinking", a "thinking budget", or budget_tokens: always use Opus 4.6 with thinking: {type: "adaptive"}. The concept of a fixed token budget for thinking is deprecated โ adaptive thinking replaces it. Do NOT use budget_tokens and do NOT switch to an older model.
Effort parameter (GA, no beta header): Controls thinking depth and overall token spend via output_config: {effort: "low"|"medium"|"high"|"max"} (inside output_config, not top-level). Default is high (equivalent to omitting it). max is Opus 4.6 only. Works on Opus 4.5, Opus 4.6, and Sonnet 4.6. Will error on Sonnet 4.5 / Haiku 4.5. Combine with adaptive thinking for the best cost-quality tradeoffs. Use low for subagents or simple tasks; max for the deepest reasoning.
Sonnet 4.6: Supports adaptive thinking (thinking: {type: "adaptive"}). budget_tokens is deprecated on Sonnet 4.6 โ use adaptive thinking instead.
Older models (only if explicitly requested): If the user specifically asks for Sonnet 4.5 or another older model, use thinking: {type: "enabled", budget_tokens: N}. budget_tokens must be less than max_tokens (minimum 1024). Never choose an older model just because the user mentions budget_tokens โ use Opus 4.6 with adaptive thinking instead.
Compaction (Quick Reference)
Beta, Opus 4.6 only. For long-running conversations that may exceed the 200K context window, enable server-side compaction. The API automatically summarizes earlier context when it approaches the trigger threshold (default: 150K tokens). Requires beta header compact-2026-01-12.
Critical: Append response.content (not just the text) back to your messages on every turn. Compaction blocks in the response must be preserved โ the API uses them to replace the compacted history on the next request. Extracting only the text string and appending that will silently lose the compaction state.
See {lang}/claude-api/README.md (Compaction section) for code examples. Full docs via WebFetch in shared/live-sources.md.
Reading Guide
After detecting the language, read the relevant files based on what the user needs:
Quick Task Reference
Single text classification/summarization/extraction/Q&A:
โ Read only {lang}/claude-api/README.md
File uploads across multiple requests:
โ Read {lang}/claude-api/README.md + {lang}/claude-api/files-api.md
Agent with built-in tools (file/web/terminal):
โ Read {lang}/agent-sdk/README.md + {lang}/agent-sdk/patterns.md
Claude API (Full File Reference)
Read the language-specific Claude API folder ({language}/claude-api/):
{language}/claude-api/README.md โ Read this first. Installation, quick start, common patterns, error handling.
shared/tool-use-concepts.md โ Read when the user needs function calling, code execution, memory, or structured outputs. Covers conceptual foundations.
{language}/claude-api/tool-use.md โ Read for language-specific tool use code examples (tool runner, manual loop, code execution, memory, structured outputs).
{language}/claude-api/streaming.md โ Read when building chat UIs or interfaces that display responses incrementally.
{language}/claude-api/batches.md โ Read when processing many requests offline (not latency-sensitive). Runs asynchronously at 50% cost.
{language}/claude-api/files-api.md โ Read when sending the same file across multiple requests without re-uploading.
shared/error-codes.md โ Read when debugging HTTP errors or implementing error handling.
shared/live-sources.md โ WebFetch URLs for fetching the latest official documentation.
Note: For Java, Go, Ruby, C#, PHP, and cURL โ these have a single file each covering all basics. Read that file plus shared/tool-use-concepts.md and shared/error-codes.md as needed.
Agent SDK
Read the language-specific Agent SDK folder ({language}/agent-sdk/). Agent SDK is available for Python and TypeScript only.
shared/live-sources.md โ WebFetch URLs for current Agent SDK docs.
When to Use WebFetch
Use WebFetch to get the latest documentation when:
User asks for "latest" or "current" information
Cached data seems incorrect
User asks about features not covered here
Live documentation URLs are in shared/live-sources.md.
Common Pitfalls
Don't truncate inputs when passing files or content to the API. If the content is too long to fit in the context window, notify the user and discuss options (chunking, summarization, etc.) rather than silently truncating.
Opus 4.6 / Sonnet 4.6 thinking: Use thinking: {type: "adaptive"} โ do NOT use budget_tokens (deprecated on both Opus 4.6 and Sonnet 4.6). For older models, budget_tokens must be less than max_tokens (minimum 1024). This will throw an error if you get it wrong.
Opus 4.6 prefill removed: Assistant message prefills (last-assistant-turn prefills) return a 400 error on Opus 4.6. Use structured outputs (output_config.format) or system prompt instructions to control response format instead.
128K output tokens: Opus 4.6 supports up to 128K max_tokens, but the SDKs require streaming for large max_tokens to avoid HTTP timeouts. Use .stream() with .get_final_message() / .finalMessage().
Tool call JSON parsing (Opus 4.6): Opus 4.6 may produce different JSON string escaping in tool call input fields (e.g., Unicode or forward-slash escaping). Always parse tool inputs with json.loads() / JSON.parse() โ never do raw string matching on the serialized input.
Structured outputs (all models): Use output_config: {format: {...}} instead of the deprecated output_format parameter on messages.create(). This is a general API change, not 4.6-specific.
Don't reimplement SDK functionality: The SDK provides high-level helpers โ use them instead of building from scratch. Specifically: use stream.finalMessage() instead of wrapping .on() events in new Promise(); use typed exception classes (Anthropic.RateLimitError, etc.) instead of string-matching error messages; use SDK types (Anthropic.MessageParam, Anthropic.Tool, Anthropic.Message, etc.) instead of redefining equivalent interfaces.
Don't define custom types for SDK data structures: The SDK exports types for all API objects. Use Anthropic.MessageParam for messages, Anthropic.Tool for tool definitions, Anthropic.ToolUseBlock / Anthropic.ToolResultBlockParam for tool results, Anthropic.Message for responses. Defining your own interface ChatMessage { role: string; content: unknown } duplicates what the SDK already provides and loses type safety.
Report and document output: For tasks that produce reports, documents, or visualizations, the code execution sandbox has python-docx, python-pptx, matplotlib, pillow, and pypdf pre-installed. Claude can generate formatted files (DOCX, PDF, charts) and return them via the Files API โ consider this for "report" or "document" type requests instead of plain stdout text.
Limitations
Use this skill only when the task clearly matches the scope described above.
Do not treat the output as a substitute for environment-specific validation, testing, or expert review.
Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.
