Follow Discord
Sweep 10 Nov 2026 · 02:18Z Build v2.1.322 539 read Stable v2.1.311 Latest v2.1.322 Next v2.1.322 Feeds RSS JSON llms.txt llms-full.txt Unofficial
HomeDocsClaude Developer Platform 11 Nov 2026
One change · api

claude-api-skill changedagents-and-tools/agent-skills/claude-api-skill

Recorded here
Lines+19added
Lines−1removed
From line 138 where the diff opens
First seen 14 Aug 2026 this site's first read of the page
Recorded edits22to this page, all time

The whole hunk

from line 138, old and new numbered
/
lines
from line 138
138138The skill handles:
139139 
140140* **Model ID swaps**, including typed SDK constants (`Model.CLAUDE_OPUS_4_8` → `Model.CLAUDE_OPUS_5_5`) across all supported languages, and classifying each file as a caller, a model definer, or an opaque string reference before editing
141 
141142* **Cloud platform detection**, preserving platform-specific model ID formats (for example, the `anthropic.` prefix on Amazon Bedrock) and skipping changes for features that are unavailable on partner-operated platforms
143 
142144* **Breaking parameter changes**, such as removing `temperature`, `top_p`, and `top_k` for Claude Opus 4.8 and Claude Opus 4.7, and converting `thinking: {type: "enabled", budget_tokens: N}` to `thinking: {type: "adaptive"}`
145 
143146* **Prefill replacement**, converting assistant-message prefill patterns to [structured outputs](https://platform.claude.com/docs/en/build-with-claude/structured-outputs) where applicable
147 
144148* **Beta header cleanup**, removing beta headers that the target model doesn’t require (for example, `effort-2025-11-24`, `fine-grained-tool-streaming-2025-05-14`, `interleaved-thinking-2025-05-14`) and switching back from `client.beta.messages.create()` (go: `client.Beta.Messages.New()`; java: `client.beta().messages().create()`; csharp: `client.Beta.Messages.Create()`; php: `$client->beta->messages->create()`) to `client.messages.create()` (go: `client.Messages.New()`; java: `client.messages().create()`; csharp: `client.Messages.Create()`; php: `$client->messages->create()`)
149 
145150* **Effort calibration**, recommending an `output_config.effort` starting point for the target model (for example, the default `high` on Claude Opus 5, and `xhigh` for coding and agentic use cases on Claude Opus 4.8 and Claude Opus 4.7)
151 
146152* **Prompt-behavior tuning**, flagging length-control, tool-triggering, subagent, and instruction-following prompts that might behave differently on the target model
153 
147154* **Silent default handling**, opting back into thinking summarization (`thinking.display: "summarized"`) when reasoning is surfaced to users on Claude Opus 4.8 and Claude Opus 4.7
148* **Refusal fallback configuration**, adding `stop_reason: "refusal"` handling before reading response content and setting up a [fallback retry path](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback) when the target is Claude Fable 5.2, Claude Fable 5.1, Claude Fable 5, Claude Opus 5.5, Claude Opus 5, or Claude Sonnet 5.5 (the server-side `fallbacks` parameter, typically in its `"default"` mode, the SDK refusal-fallback middleware, or a fallback-credit retry), and updating fallback code written against earlier preview shapes
155 
156* **Refusal fallback configuration**, in three parts:
157 
158 * Adding `stop_reason: "refusal"` handling before reading response content.
159 
160 * Updating fallback code written against earlier preview shapes.
161 
162 * Setting up a [fallback retry path](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback) for six target models. They are Claude Fable 5.2, Claude Fable 5.1, Claude Fable 5, Claude Opus 5.5, Claude Opus 5, and Claude Sonnet 5.5. The path uses one of these:
163 
164 * [Server-side fallback](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#server-side-fallback): the `fallbacks` parameter, typically in its `"default"` mode.
165 * [Client-side fallback with the SDK middleware](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#client-side-fallback).
166 * A retry that redeems a [fallback credit](https://platform.claude.com/docs/en/build-with-claude/fallback-credit).
149167 
150168As it edits, the skill explains each change and its motivation inline. On completion, it produces a checklist of items that require manual verification (typically integration tests, length-control prompt tuning, and cost/rate-limit re-baselining).
151169 
Feedback