Skip to content

feat: add @tanstack/intent agent skills #432

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
AlemTuzlak wants to merge 2 commits into
base: main
Choose a base branch
from
Open

feat: add @tanstack/intent agent skills #432

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
c53288e
feat: add @tanstack/intent agent skills for AI coding assistants
AlemTuzlak Apr 8, 2026
fbfc00e
ci: apply automated fixes
autofix-ci[bot] Apr 8, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
11 changes: 11 additions & 0 deletions .changeset/intent-skills.md
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,11 @@
---
'@tanstack/ai': patch
'@tanstack/ai-code-mode': patch
---

Add @tanstack/intent agent skills for AI coding assistants

Adds 10 skill files covering chat-experience, tool-calling, media-generation,
code-mode, structured-outputs, adapter-configuration, ag-ui-protocol,
middleware, and custom-backend-integration. Skills guide AI agents to generate
correct TanStack AI code patterns and avoid common mistakes.
845 changes: 845 additions & 0 deletions _artifacts/domain_map.yaml
View file
Open in desktop

Large diffs are not rendered by default.

193 changes: 193 additions & 0 deletions _artifacts/skill_spec.md
View file
Open in desktop

Large diffs are not rendered by default.

251 changes: 251 additions & 0 deletions _artifacts/skill_tree.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,251 @@
# skills/_artifacts/skill_tree.yaml
library:
name: '@tanstack/ai'
version: '0.10.0'
repository: 'https://github.com/TanStack/ai'
description: 'Type-safe, provider-agnostic AI SDK for building chat, tool calling, media generation, and code execution features.'
generated_from:
domain_map: '_artifacts/domain_map.yaml'
skill_spec: '_artifacts/skill_spec.md'
generated_at: '2026-04-08'

skills:
# ── Core skills (in @tanstack/ai package) ──

- name: 'TanStack AI — Core'
slug: 'ai-core'
type: 'core'
domain: 'chat-experiences'
path: 'skills/ai-core/SKILL.md'
package: 'packages/typescript/ai'
description: >
Entry point for TanStack AI skills. Routes to chat-experience,
tool-calling, media-generation, structured-outputs, adapter-configuration,
ag-ui-protocol, middleware, and custom-backend-integration based on
developer task. Covers chat(), toolDefinition(), generateImage(),
outputSchema, openaiText(), toServerSentEventsResponse(), middleware hooks.
requires: []

- name: 'Chat Experience'
slug: 'ai-core/chat-experience'
type: 'sub-skill'
domain: 'chat-experiences'
path: 'skills/ai-core/chat-experience/SKILL.md'
package: 'packages/typescript/ai'
description: >
End-to-end chat implementation: server endpoint with chat() and
toServerSentEventsResponse(), client-side useChat hook with
fetchServerSentEvents(), message rendering with UIMessage parts,
multimodal content, thinking/reasoning display. Covers streaming
states, connection adapters, and message format conversions.
NOT Vercel AI SDK — uses chat() not streamText().
requires:
- 'ai-core'
sources:
- 'TanStack/ai:docs/getting-started/quick-start.md'
- 'TanStack/ai:docs/chat/streaming.md'
- 'TanStack/ai:docs/chat/connection-adapters.md'
- 'TanStack/ai:docs/chat/thinking-content.md'
- 'TanStack/ai:docs/advanced/multimodal-content.md'
- 'TanStack/ai:packages/typescript/ai/src/core/chat.ts'
- 'TanStack/ai:packages/typescript/ai-client/src/chat-client.ts'

- name: 'Tool Calling'
slug: 'ai-core/tool-calling'
type: 'sub-skill'
domain: 'tool-system'
path: 'skills/ai-core/tool-calling/SKILL.md'
package: 'packages/typescript/ai'
description: >
Isomorphic tool system: toolDefinition() with Zod schemas,
.server() and .client() implementations, passing tools to both
chat() on server and useChat/clientTools on client, tool approval
flows with needsApproval and addToolApprovalResponse(), lazy tool
discovery with lazy:true, rendering ToolCallPart and ToolResultPart
in UI. Requires @standard-schema/spec for type inference.
Copy link
Copy Markdown
Contributor

@coderabbitai coderabbitai bot Apr 8, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

⚠️ Potential issue | 🟠 Major

Remove stale @standard-schema/spec requirement from Tool Calling skill text.

This line contradicts the PR objective that no @standard-schema/spec references remain. Keeping it in generated artifacts will reintroduce the exact confusion this PR is trying to prevent.

🤖 Prompt for AI Agents 
Verify each finding against the current code and only fix it if needed.

In `@_artifacts/skill_tree.yaml` at line 65, The generated Tool Calling skill text
in _artifacts/skill_tree.yaml still references "@standard-schema/spec"; remove
that stale requirement string from the Tool Calling skill description so no
"@standard-schema/spec" tokens remain in the artifact, update the Tool Calling
skill's description field (the skill text/description entry) to omit or replace
that phrase, and run the generation/test that produced this artifact to ensure
the reference is not reintroduced.

requires:
- 'ai-core'
sources:
- 'TanStack/ai:docs/tools/tools.md'
- 'TanStack/ai:docs/tools/server-tools.md'
- 'TanStack/ai:docs/tools/client-tools.md'
- 'TanStack/ai:docs/tools/tool-approval.md'
- 'TanStack/ai:docs/tools/lazy-tool-discovery.md'
- 'TanStack/ai:docs/tools/tool-architecture.md'
- 'TanStack/ai:packages/typescript/ai/src/tools/'

- name: 'Media Generation'
slug: 'ai-core/media-generation'
type: 'sub-skill'
domain: 'media-generation'
path: 'skills/ai-core/media-generation/SKILL.md'
package: 'packages/typescript/ai'
description: >
Image, video, speech (TTS), and transcription generation using
activity-specific adapters: generateImage() with openaiImage/geminiImage,
generateVideo() with async polling, generateSpeech() with openaiSpeech,
generateTranscription() with openaiTranscription. React hooks:
useGenerateImage, useGenerateSpeech, useTranscription, useGenerateVideo.
TanStack Start server function integration with toServerSentEventsResponse.
requires:
- 'ai-core'
sources:
- 'TanStack/ai:docs/media/generations.md'
- 'TanStack/ai:docs/media/generation-hooks.md'
- 'TanStack/ai:docs/media/image-generation.md'
- 'TanStack/ai:docs/media/video-generation.md'
- 'TanStack/ai:docs/media/text-to-speech.md'
- 'TanStack/ai:docs/media/transcription.md'
subsystems:
- 'image-generation'
- 'video-generation'
- 'text-to-speech'
- 'transcription'

- name: 'Structured Outputs'
slug: 'ai-core/structured-outputs'
type: 'sub-skill'
domain: 'chat-experiences'
path: 'skills/ai-core/structured-outputs/SKILL.md'
package: 'packages/typescript/ai'
description: >
Type-safe JSON schema responses from LLMs using outputSchema on chat().
Supports Zod, ArkType, and Valibot schemas. The adapter handles
provider-specific strategies transparently — never configure structured
output at the provider level. convertSchemaToJsonSchema() for manual
schema conversion.
requires:
- 'ai-core'
sources:
- 'TanStack/ai:docs/chat/structured-outputs.md'
- 'TanStack/ai:packages/typescript/ai/src/tools/schema-converter.ts'

- name: 'Adapter Configuration'
slug: 'ai-core/adapter-configuration'
type: 'sub-skill'
domain: 'adapter-management'
path: 'skills/ai-core/adapter-configuration/SKILL.md'
package: 'packages/typescript/ai'
description: >
Provider adapter selection and configuration: openaiText, anthropicText,
geminiText, ollamaText, grokText, groqText, openRouterText. Per-model
type safety with modelOptions, reasoning/thinking configuration,
runtime adapter switching, extendAdapter() for custom models, createModel().
API key env vars: OPENAI_API_KEY, ANTHROPIC_API_KEY, GOOGLE_API_KEY/GEMINI_API_KEY,
XAI_API_KEY, GROQ_API_KEY, OPENROUTER_API_KEY, OLLAMA_HOST.
requires:
- 'ai-core'
sources:
- 'TanStack/ai:docs/adapters/openai.md'
- 'TanStack/ai:docs/adapters/anthropic.md'
- 'TanStack/ai:docs/adapters/gemini.md'
- 'TanStack/ai:docs/adapters/ollama.md'
- 'TanStack/ai:docs/adapters/grok.md'
- 'TanStack/ai:docs/adapters/groq.md'
- 'TanStack/ai:docs/adapters/openrouter.md'
- 'TanStack/ai:docs/advanced/per-model-type-safety.md'
- 'TanStack/ai:docs/advanced/runtime-adapter-switching.md'
- 'TanStack/ai:docs/advanced/extend-adapter.md'
subsystems:
- 'openai'
- 'anthropic'
- 'gemini'
- 'ollama'
- 'grok'
- 'groq'
- 'openrouter'
references:
- 'references/openai-adapter.md'
- 'references/anthropic-adapter.md'
- 'references/gemini-adapter.md'
- 'references/ollama-adapter.md'
- 'references/grok-adapter.md'
- 'references/groq-adapter.md'
- 'references/openrouter-adapter.md'

- name: 'AG-UI Protocol'
slug: 'ai-core/ag-ui-protocol'
type: 'sub-skill'
domain: 'transport-protocol'
path: 'skills/ai-core/ag-ui-protocol/SKILL.md'
package: 'packages/typescript/ai'
description: >
Server-side AG-UI streaming protocol implementation: StreamChunk event
types (RUN_STARTED, TEXT_MESSAGE_START/CONTENT/END, TOOL_CALL_START/ARGS/END,
RUN_FINISHED, RUN_ERROR, STEP_STARTED/STEP_FINISHED, STATE_SNAPSHOT/DELTA,
CUSTOM), toServerSentEventsStream() for SSE format, toHttpStream() for
NDJSON format. For backends serving AG-UI events without client packages.
requires:
- 'ai-core'
sources:
- 'TanStack/ai:docs/protocol/chunk-definitions.md'
- 'TanStack/ai:docs/protocol/sse-protocol.md'
- 'TanStack/ai:docs/protocol/http-stream-protocol.md'

- name: 'Middleware'
slug: 'ai-core/middleware'
type: 'sub-skill'
domain: 'extensibility'
path: 'skills/ai-core/middleware/SKILL.md'
package: 'packages/typescript/ai'
description: >
Chat lifecycle middleware hooks: onConfig, onStart, onChunk,
onBeforeToolCall, onAfterToolCall, onUsage, onFinish, onAbort, onError.
Use for analytics, event firing, tool caching (toolCacheMiddleware),
logging, and tracing. Middleware array in chat() config, left-to-right
execution order. NOT onEnd/onFinish callbacks on chat() — use middleware.
requires:
- 'ai-core'
sources:
- 'TanStack/ai:docs/advanced/middleware.md'
- 'TanStack/ai:packages/typescript/ai/src/middlewares/'

- name: 'Custom Backend Integration'
slug: 'ai-core/custom-backend-integration'
type: 'composition'
domain: 'transport-protocol'
path: 'skills/ai-core/custom-backend-integration/SKILL.md'
package: 'packages/typescript/ai'
description: >
Connect useChat to a non-TanStack-AI backend through custom connection
adapters. ConnectConnectionAdapter (single async iterable) vs
SubscribeConnectionAdapter (separate subscribe/send). Customize
fetchServerSentEvents() and fetchHttpStream() with auth headers,
custom URLs, and request options. Import from framework package,
not @tanstack/ai-client.
requires:
- 'ai-core'
- 'ai-core/chat-experience'
sources:
- 'TanStack/ai:docs/chat/connection-adapters.md'
- 'TanStack/ai:packages/typescript/ai-client/src/connection-adapters.ts'

# ── Code Mode skills (in @tanstack/ai-code-mode package) ──

- name: 'Code Mode'
slug: 'ai-code-mode'
type: 'core'
domain: 'code-execution'
path: 'skills/ai-code-mode/SKILL.md'
package: 'packages/typescript/ai-code-mode'
description: >
LLM-generated TypeScript execution in sandboxed environments:
createCodeModeTool() with isolate drivers (createNodeIsolateDriver,
createQuickJSIsolateDriver, createCloudflareIsolateDriver),
codeModeWithSkills() for persistent skill libraries, trust strategies,
skill storage (FileSystem, LocalStorage, InMemory, Mongo), client-side
execution progress via code_mode:* custom events in useChat.
requires:
- 'ai-core'
- 'ai-core/chat-experience'
sources:
- 'TanStack/ai:docs/code-mode/code-mode.md'
- 'TanStack/ai:docs/code-mode/code-mode-isolates.md'
- 'TanStack/ai:docs/code-mode/code-mode-with-skills.md'
- 'TanStack/ai:docs/code-mode/client-integration.md'
- 'TanStack/ai:packages/typescript/ai-code-mode/src/'
- 'TanStack/ai:packages/typescript/ai-code-mode-skills/src/'
subsystems:
- 'node-isolate'
- 'quickjs-isolate'
- 'cloudflare-isolate'
6 changes: 4 additions & 2 deletions packages/typescript/ai-code-mode/package.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -24,7 +24,8 @@
},
"files": [
"dist",
"src"
"src",
"skills"
],
"scripts": {
"build": "vite build",
Expand All @@ -42,7 +43,8 @@
"code-mode",
"llm",
"sandbox",
"isolate"
"isolate",
"tanstack-intent"
],
"dependencies": {
"esbuild": "^0.25.12"
Expand Down
Loading
Loading