chore(.agents/skills): update existing skills

.agents/skills/xsai/SKILL.md

@@ -28,7 +28,7 @@ Use this skill for `xsai` code, package selection, API selection, canonical exam
 - If the user has not chosen xsAI yet, confirm the task fits an OpenAI-compatible surface before recommending it.
 - Prefer the smallest package that solves the task. Use the umbrella `xsai` package only when the user needs several features at once or explicitly wants one dependency.
 - When writing or editing code, read `references/recipes.md` first and start from the closest canonical example.
-- Keep examples minimal and runnable. Include `baseURL` and `model` explicitly. Include `apiKey` for hosted providers; omit it only when the target endpoint truly does not need one.
+- Keep examples minimal and runnable. Include `baseURL` and `model` explicitly. For hosted providers, show `apiKey` wired from `process.env` in Node.js and from `localStorage` in the browser; omit it only when the target endpoint truly does not need one. Do not recommend hardcoding secrets.
 - Preserve the project's existing schema library and provider wiring unless there is a clear reason to change them.
 - Keep recommendations aligned with xsAI's scope: OpenAI-compatible, Fetch-based, runtime-portable, and intentionally narrow.
 - If the user is optimizing for bundle or install size, explicitly prefer granular packages such as `@xsai/generate-text` over `xsai`.
@@ -56,11 +56,11 @@ Use this skill for `xsai` code, package selection, API selection, canonical exam
 ## Key constraints
 
 - `baseURL` and `model` are usually required in practice for xsAI calls.
-- `apiKey` is provider-dependent. Most hosted providers need it; local or proxy endpoints may not.
+- `apiKey` is provider-dependent. Most hosted providers need it; local or proxy endpoints may not. In Node.js, prefer `process.env`. In browsers, prefer reading from `localStorage`. Do not recommend hardcoding API keys.
 - xsAI is OpenAI-compatible-first. Do not imply support for non-compatible provider APIs.
 - `streamText()` returns immediately; callers consume `textStream`, `fullStream`, and result promises asynchronously.
 - `streamObject()` is async because schema conversion happens before streaming starts.
-- `maxSteps` controls repeated tool-use loops by issuing additional API calls with tool results appended.
+- `stopWhen` controls repeated tool-use loops with explicit stop predicates such as `stepCountAtLeast()` and `hasToolCall()`.
 - `generateObject()`, `streamObject()`, and `tool()` rely on `xsschema`; some schema vendors need extra JSON Schema converter packages.
 - xsAI is designed to stay small. Avoid recommending the umbrella package when a smaller package is enough.
 

.agents/skills/xsai/agents/openai.yaml

@@ -1,7 +1,7 @@
 interface:
-  display_name: 'xsAI'
-  short_description: 'Use xsAI for minimal OpenAI-compatible code'
-  default_prompt: 'Use $xsai to choose the smallest xsAI package and build a runnable OpenAI-compatible example.'
+  display_name: xsAI
+  short_description: Use xsAI for minimal OpenAI-compatible code
+  default_prompt: Use $xsai to choose the smallest xsAI package and build a runnable OpenAI-compatible example.
 
 policy:
   allow_implicit_invocation: true

.agents/skills/xsai/references/recipes.md

@@ -7,7 +7,7 @@ Use this reference when the user wants code, when you are editing xsAI code, or
 - Prefer granular `@xsai/*` imports in new examples.
 - Switch to the umbrella `xsai` package only when the repo already uses it or the user explicitly wants one dependency.
 - Keep `baseURL` and `model` explicit.
-- Include `apiKey` for hosted providers. For local or proxy endpoints, only include it if the target actually requires one.
+- Include `apiKey` for hosted providers. In Node.js examples, prefer `process.env`. In browser examples, prefer `localStorage`. For local or proxy endpoints, only include it if the target actually requires one. Do not hardcode secrets.
 - Preserve the repo's existing schema library instead of swapping between Zod, Valibot, ArkType, or Effect without a reason.
 
 ## Minimal text generation
@@ -36,12 +36,15 @@ const { text } = await generateText({
 
 Use this as the default starting point for simple scripts, tests, and one-shot helpers.
 
+These examples use `node:process` because they target Node.js. For browser examples, prefer reading the API key from `localStorage` instead of hardcoding it.
+
 ## Streaming text with tools
 
 ```ts
 import { env } from 'node:process'
 
 import { streamText } from '@xsai/stream-text'
+import { stepCountAtLeast } from '@xsai/stream-text/shared-chat'
 import { tool } from '@xsai/tool'
 
 import * as v from 'valibot'
@@ -59,7 +62,6 @@ const add = await tool({
 const { fullStream } = streamText({
   apiKey: env.OPENAI_API_KEY!,
   baseURL: 'https://api.openai.com/v1/',
-  maxSteps: 2,
   messages: [
     {
       content: 'You are a helpful assistant.',
@@ -71,6 +73,7 @@ const { fullStream } = streamText({
     },
   ],
   model: 'gpt-4o',
+  stopWhen: stepCountAtLeast(2),
   toolChoice: 'required',
   tools: [add],
 })

.agents/skills/xsai/references/text-stream-tools.md

@@ -20,7 +20,7 @@ For chat-style APIs, expect common options such as:
 - `seed`
 - `toolChoice`
 - `tools`
-- `maxSteps`
+- `stopWhen`
 
 ## `generateText`
 
@@ -64,7 +64,9 @@ It returns immediately and exposes:
 
 ## Tool loops
 
-- `maxSteps` enables repeated tool-use loops.
+- `stopWhen` enables repeated tool-use loops with explicit predicates.
+- Reach for `stepCountAtLeast(n)` as the default loop bound.
+- Combine conditions with `and()`, `or()`, and `not()` when the stop logic is more specific.
 - Each step appends assistant output and tool results, then makes another API call if needed.
 - Use `toolChoice: 'required'` when the model must call a tool.