
Description
Portable Agent Skills (SKILL.md) for TanStack AI with @tanstack/ai-skills. Renders a skill catalog and a load_skill tool via the withSkills middleware so any tool-calling model loads skills on demand, on any provider. Covers the SkillSource interface, inlineSkill/skillDirectory/staticSkills, the aggregate/ dedupe/filter/cache combinators, read_skill_resource, and the conformance suite. Use for provider-agnostic runtime skills — NOT hosted provider skills (codeExecutionTool/shellTool), which run in a provider sandbox.
SKILL.md
TanStack AI Skills
Builds on the
ai-coreskill in@tanstack/ai. Package:@tanstack/ai-skills.
Portable Agent Skills give a tool-calling model a library of SKILL.md skills it
can load on demand, on any provider, with no server sandbox. This is separate
from hosted Provider Skills (codeExecutionTool / shellTool), which run in
the provider's sandbox and are referenced by ID.
Two skill features, do not confuse them
| Need | Use |
|---|---|
| Model loads SKILL.md at runtime, any provider | withSkills (this package) |
| Hosted skill runs in a provider sandbox by ID | codeExecutionTool / shellTool |
| Teach a coding assistant how to use TanStack AI | Ship a SKILL.md, install via Intent |
The portable and hosted paths do not mix in one chat() call: withSkills
throws if a code_execution/shell tool in the same call carries skills.
Add skills to a chat
import { chat, toServerSentEventsResponse } from '@tanstack/ai'
import { anthropicText } from '@tanstack/ai-anthropic'
import { inlineSkill, withSkills } from '@tanstack/ai-skills'
const pptx = inlineSkill({
name: 'pptx-builder',
description: 'Build and edit PowerPoint decks with python-pptx.',
instructions: '# Building a deck\nUse python-pptx. Edit slides, then save.',
})
const stream = chat({
adapter: anthropicText('claude-sonnet-4-5'),
messages,
middleware: [withSkills(pptx)],
})
withSkills adds a catalog to the system prompt and a load_skill tool whose
name is constrained to your skill names. It renders <available_skills> XML
for Anthropic models and markdown for the rest. Re-loading a skill in the same
conversation returns a short "already loaded" marker.
Sources
A SkillSource is bytes only (no filesystem assumption), so the middleware runs
on the edge too.
inlineSkill({ name, description, instructions, resources? })— one skill in code or a DB row. Edge-safe.skillDirectory(root, { strict? })— walk a folder forSKILL.md. Import from@tanstack/ai-skills/node(usesnode:fs). Strict by default.staticSkills(catalog)— build-time bundle viaskillsCatalogPlugin(Vite). Edge-safe, and.namesis a typed union.
Combine with aggregate, dedupe, filter, cache. withSkills([a, b]) is
sugar for dedupe(aggregate([a, b])). A single source is never auto-wrapped, so
a tenant-scoped source is never cached into a shared bucket.
Resources
To let the model read a skill's bundled files, pass createResourceTool(source)
in tools. withSkills detects it and advertises read_skill_resource. Paths
that escape the skill root are rejected.
Skills that carry code
withSkills inventories a skill's scripts/ in the load_skill result but does
NOT run them (script execution is a later phase). To let a skill run code, pass
your own execution tool to chat({ tools }) alongside withSkills and write the
skill so it tells the model to call that tool. withSkills composes with any
tools you provide.
import { toolDefinition } from '@tanstack/ai'
import { z } from 'zod'
const executeShell = toolDefinition({
name: 'execute_shell',
description: 'Run a shell command and return its stdout.',
inputSchema: z.object({ command: z.string() }),
outputSchema: z.object({ stdout: z.string() }),
}).server(async ({ command }) => ({ stdout: await runSomewhere(command) }))
// chat({ tools: [executeShell], middleware: [withSkills(source)] })
The skill supplies the command; your tool supplies the ability to run it. Swap in
a provider sandbox, a Code Mode isolate, or a remote worker without changing the
skill. For hosted skills that run in the provider's own sandbox, use
codeExecutionTool / shellTool instead (see provider-skills).
Write a custom source
Implement SkillSource (list + load, optional revision/listResources/
readResource), then validate it with the shipped conformance suite:
import { runSkillSourceConformance } from '@tanstack/ai-skills/testing'
runSkillSourceConformance(() => myS3Source(fixtures), 's3')
Entry points
@tanstack/ai-skills— types,inlineSkill, combinators,withSkills,createResourceTool,validateSkill,staticSkills,SkillLimitError.@tanstack/ai-skills/node—skillDirectory,skillsCatalogPlugin(node:fs).@tanstack/ai-skills/testing—runSkillSourceConformance.
Docs
- Portable Agent Skills:
docs/skills/agent-skills.md - Skill sources:
docs/skills/skill-sources.md - Write a skill source:
docs/skills/writing-adapters.md - Provider (hosted) skills:
docs/tools/provider-skills.md
More skills from the ai repository
View all 29 skillsai-code-mode
execute sandboxed TypeScript code with LLMs
Aug 18AI SDKCode ExecutionSandboxingTanStack +1ai-core
configure TanStack AI agent features
Aug 28AgentsAIMiddlewareai-core/adapter-configuration
configure AI provider adapters
Aug 5AI SDKConfigurationLLMTanStackai-core/ag-ui-protocol
implement TanStack AI streaming protocol
Aug 5API DevelopmentLLMTanStackai-core/chat-experience
implement chat experiences with TanStack AI
Aug 28API DevelopmentFrontendLLMTanStackai-core/client-persistence
implement browser chat persistence for TanStack AI
Aug 5AIFrontendPersistenceTanStack
More from TanStack
View publisheraggregation
perform data aggregation in TanStack Table
table
Aug 28Data AnalysisFrontendTanStackapi-not-found
diagnose TanStack Table API errors
table
Aug 28DebuggingFrontendTanStackcell-selection
select rectangular cell ranges in tables
table
Aug 28Data AnalysisTanStackUI Componentscell-spanning
configure cell spanning in TanStack Table
table
Aug 28Data VisualizationFrontendTanStackUI Componentsclient-vs-server
manage TanStack Table data pipelines
table
Aug 28Data PipelineFrontendPerformanceTanStackcolumn-faceting
build faceted filter UIs
table
Aug 28Data VisualizationFrontendTanStack