Repository
TanStack/ai agent skills
- skills
- 24
- GitHub stars
- 3.2k
GitHub description: “🤖 Type-safe, provider-agnostic TypeScript AI SDK for streaming chat, tool calling, agents, and multimodal apps across OpenAI, Anthropic, Gemini, React, Vue, Svelte, and Solid.”
- Stars
- 3,169 (356 forks)
- Licence
- MIT
- Last push
- Oct 2026
- Created
- Oct 2025
- Homepage
- tanstack.com/ai/latest
- Source
- github.com/TanStack/ai
- ai
- ai-agents
- ai-sdk
- anthropic
- chatbot
- function-calling
- gemini
- llm
- multimodal
- openai
- react
- solidjs
- streaming
- svelte
- tanstack
- tool-calling
Install all skills
npx skills add TanStack/aiAdd --skill <name> for a single skill and -a <agent> to choose the agent (see the agent guides).
Skills in TanStack/ai, ranked
Ranked by score. Sort bymost stars,trending,newest,recently updated
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 1 | A skill your agent uses when the user invokes /i-have-adhd, says they have ADHD, or asks for ADHD-friendly output. | TanStack/ | 3.2k | 5 repos | ~1.8k | Automated safety check: Pass | MIT | today |
| 2 | 2.PR Sweep Sweep open (or listed) PRs with up to 100 parallel agents: security-scan outside contributors, rebase onto main when behind (push --force-with-lease), approve pending first-time-contributor CI when… | TanStack/ | 3.2k | — | ~4.6k | Automated safety check: Pass | MIT | today |
| 3 | A skill your agent uses when wiring honcho() from @tanstack/ai-memory/honcho — a hosted memory adapter where recall is a dialectic answer over the user's representation (no discrete fragments). | TanStack/ | 3.2k | 1 repo | ~457 | Automated safety check: Pass | MIT | today |
| 4 | A skill your agent uses when wiring inMemory() from @tanstack/ai-memory/in-memory — explains setup, options (embedder, extract, topK/minScore), when to pick it (dev/tests/single-process demos), and… | TanStack/ | 3.2k | 1 repo | ~448 | Automated safety check: Pass | MIT | today |
| 5 | A skill your agent uses when wiring redis() from @tanstack/ai-memory/redis in production — covers client setup (ioredis or node-redis via fromNodeRedis), the storage model, client-side ranking… | TanStack/ | 3.2k | 1 repo | ~840 | Automated safety check: Pass | MIT | today |
| 6 | A skill your agent uses when adding a public teaching example or a docs tutorial. | TanStack/ | 3.2k | — | ~1.4k | Automated safety check: Pass | MIT | today |
| 7 | Durability and state persistence for TanStack AI chats with @tanstack/ai-persistence. | TanStack/ | 3.2k | — | ~3.3k | Automated safety check: Pass | MIT | today |
| 8 | Portable Agent Skills (SKILL.md) for TanStack AI with @tanstack/ai-skills. | TanStack/ | 3.2k | — | ~1.5k | Automated safety check: Pass | MIT | today |
| 9 | Treats bug-fix pull requests as invasive and untrusted. An agent skill from TanStack/ai. | TanStack/ | 3.2k | — | ~4.8k | Automated safety check: Pass | MIT | today |
| 10 | 10.Ponytail Forces the laziest solution that actually works, simplest, shortest, most minimal. | TanStack/ | 3.2k | 2 repos | ~1.4k | Automated safety check: Pass | MIT | today |
| 11 | A skill your agent uses when wiring memoryMiddleware from @tanstack/ai-memory into a chat() call — covers the recall/save adapter contract, scope shape and server-side scope security, the… | TanStack/ | 3.2k | — | ~1.2k | Automated safety check: Pass | MIT | today |
| 12 | A skill your agent uses when wiring mem0() from @tanstack/ai-memory/mem0 — a hosted memory adapter that talks to a mem0 server over plain HTTP (no SDK peer). | TanStack/ | 3.2k | 1 repo | ~419 | Automated safety check: Pass | MIT | today |
| 13 | A skill your agent uses when wiring hindsight() from @tanstack/ai-memory/hindsight — a hosted memory adapter that buckets memory per conversation and exposes retain/recall/reflect tools to the model. | TanStack/ | 3.2k | — | ~477 | Automated safety check: Pass | MIT | today |
| 14 | 14.AI Code Mode LLM-generated TypeScript execution in sandboxed environments: createCodeModeTool() with isolate drivers (createNodeIsolateDriver, createQuickJSIsolateDriver, createQuickJSBunIsolateDriver… | TanStack/ | 3.2k | 1 repo | ~5.6k | Automated safety check: Pass | MIT | today |
| 15 | Move an app to TanStack AI from the Vercel AI SDK or raw provider SDKs, or move it off a deprecated TanStack AI API. | TanStack/ | 3.2k | — | ~680 | Automated safety check: Pass | MIT | today |
| 16 | A skill your agent uses when writing a pull request title or body, when about to run gh pr create, when about to git push on a branch that already has an open PR, or when the user says… | TanStack/ | 3.2k | — | ~2.2k | Automated safety check: Warn | MIT | today |
| 17 | 17.Docs A skill your agent uses when writing, editing, or organizing documentation, when planning what docs a feature needs, and whenever planning or implementing a new feature or change in a repo (docs… | TanStack/ | 3.2k | — | ~6k | Automated safety check: Pass | MIT | today |
| 18 | Triage all open GitHub issues, PRs, and discussions in the current repository by fanning out up to 100 parallel subagents (one per item), then produce a single prioritized report ranking which PRs… | TanStack/ | 3.2k | — | ~5.2k | Automated safety check: Pass | MIT | today |
| 19 | 19.AI Core Entry point for TanStack AI skills. An agent skill from TanStack/ai. | TanStack/ | 3.2k | — | ~1.8k | Automated safety check: Pass | MIT | today |
| 20 | 20.Gap Analysis Audit TanStack AI provider adapters for feature parity gaps and outdated model lists. | TanStack/ | 3.2k | — | ~1.9k | Automated safety check: Pass | MIT | today |
| 21 | 21.AI MCP Host-side Model Context Protocol (MCP) for TanStack AI: connect to external MCP servers, host your own tools with createMCPServer, discover and run tools inside any adapter's chat() loop, read… | TanStack/ | 3.2k | — | ~11k | Automated safety check: Pass | MIT | today |
| 22 | A skill your agent uses when an agent in this TanStack AI monorepo needs a playground app to try a new feature. | TanStack/ | 3.2k | — | ~266 | Automated safety check: Notes | MIT | today |
| 23 | 23.Pirate Speak Answer entirely as a boisterous pirate, with nautical slang and "arrr". | TanStack/ | 3.2k | — | ~159 | Automated safety check: Pass | MIT | today |
| 24 | Retell the answer as a short story told mostly in emoji. An agent skill from TanStack/ai. | TanStack/ | 3.2k | — | ~109 | Automated safety check: Pass | MIT | today |
Questions, answered from the data.
What is the best skill in TanStack/ai?
I Have Adhd from TanStack/ai ranks first of the 24 skills in TanStack/ai listed here, with the highest score: its repository has 3.2k GitHub stars, 5 other GitHub owners carry a copy, its SKILL.md loads about 1.8k tokens and it passes the automated safety check with no findings. Next come PR Sweep and Tanstack AI Memory Honcho.
Are the skills in TanStack/ai official?
None yet. All 24 skills in TanStack/ai listed here come from community repositories; a skill counts as official when the product's own GitHub organization publishes it.
How do I install all skills from TanStack/ai?
Run npx skills add TanStack/ai in your project: the open-source skills CLI installs the repository's skills into your coding agent's skills folder. To install a single skill, open its page here for the exact command.
How are these skills ranked?
By Skill Navigator score, which combines the GitHub stars of the skill's repository (shared across that repo's skills and discounted for large collections), how many other GitHub owners carry a copy of the skill, and automated SKILL.md quality checks, minus penalties for safety-check warnings and for each further skill from the same repository. Skills that fail the safety check are not listed.