Libraries
Framework
Start
Router
Data & State
Query
DB
Store
AI
UI
Table
Charts
Form
Markdown
Highlight
UX
Virtual
Pacer
Hotkeys
Tooling
Devtools
Config
CLI
Intent
Browse all libraries
Blog
Blog & Release Notes
About
YouTube
The official TanStack channel.
Workshops
Live sessions from the maintainers.
Release Notes
The latest releases and changelog.
Community
Channels
Discord
Real-time community support.
GitHub
Source, issues, discussions, and releases.
People & Work
Maintainers
Meet the people maintaining the stack.
Showcase
Projects selected by the TanStack team.
Community projects
Tools
Tools
Application Starter
Alpha
Generate TanStack app starters.
Builder
Alpha
Build and share TanStack projects.
Stats
NPM and ecosystem usage data.
Merch
View all
Support
Support
Support Overview
Find the right support path.
Partners
Companies supporting TanStack.
OSS Sponsors
Sponsors keeping TanStack open source.
Enterprise Support
Private consulting and expert support.
Contact
Get in touch with the TanStack team.
About
Ethos
How we approach open source.
Tenets
The values that shape TanStack libraries.
Design System
Logos, tokens, and UI components.
Search
Ask AI
Libraries
Blog
Community
Tools
Merch
Support
Search
Ask AI
Sign In
Back
TanStack Intent
/
Registry
/
@crossplatformai/skills
Fetching package from npm...
TanStack Intent
/
Registry
/
@crossplatformai/skills
@crossplatformai/skills
0.0.13 (latest) — 23 skills
0.0.12 — 23 skills
0.0.11 — 20 skills
0.0.10 — 19 skills
0.0.9 — 16 skills
0.0.8 — 16 skills
0.0.7 — 15 skills
0.0.6 — 14 skills
0.0.5 — 15 skills
0.0.4 — 15 skills
0.0.3 — 14 skills
Copy install prompt
Reusable Agent Skills for CrossPlatform.ai projects.
Skills
(23)
Skills
All Skills
23
collective-intelligence
desktop-electron-dev-attach
do-not-abbreviate
documentation-writing
i-dont-know-is-the-answer
move-them-lose-them
multi-agent-hunk-ownership
no-local-exemptions
playwright-visual-verification
post-build-ship/build
post-build-ship/post
post-build-ship/ship
post-build-ship
react-native-web-styling
reconcile-setup
research-before-asking
revalidate-without-reset
rule-of-three
see-something-say-something
temporary-pnpm-package-links
test-layer-fit
thinking-is-not-knowing
web-first-components
Skills
23
History
collective-intelligence
Use when a consequential, uncertain, complex, or creative decision benefits from task-relevant independent perspectives and explicit synthesis. Guide perspective selection, anti-anchoring, and transparent integration without defaulting to consensus or vote-counting. Not for routine well-supported work, factual verification (use thinking-is-not-knowing), evidence-backed research or decision-carrying (use research-before-asking), Post.Build.Ship workflow authority, or claiming that unperformed collaboration occurred.
72 lines
desktop-electron-dev-attach
Interactively attach to an already-running Electron app through stable DESKTOP_CDP_PORT for local development or requested desktop happy-path verification with Playwright or OpenCode MCP.
49 lines
do-not-abbreviate
Require complete words in newly authored human-facing copy, names, labels, documentation, messages, and explanatory comments, with authorization before a shortened form; do not rewrite existing exact text, machine-facing tokens, or user-provided strings.
82 lines
documentation-writing
Guidance for durable evergreen documentation and change-oriented framing when a document explicitly needs change history.
57 lines
i-dont-know-is-the-answer
When you lack a grounded answer and feel pressure to produce one, "I don't know" is more often correct than people admit and is underused because it feels like status loss - say it instead of filling the gap with a hedge. Make it pull its weight - "I don't know yet, here is how I will find out, by when" - or use a cost-aware check-in. Triggers when tempted to answer a question you have not verified. Pairs with the thinking-is-not-knowing skill. When research has already grounded the options and user judgment remains, use research-before-asking.
109 lines
move-them-lose-them
Keep users in their current task context when they need to satisfy a prerequisite or create missing data instead of sending them to Settings or another area. Use when designing, implementing, or reviewing application flows, empty states, selectors, signup, onboarding, forms, task completion, contextual creation, or any recommendation that moves users away from what they are trying to finish.
63 lines
multi-agent-hunk-ownership
Multi-agent hunk-ownership guidance for preserving user and other-agent changes while editing, formatting, staging, and committing.
78 lines
no-local-exemptions
Review environment branches for hidden local exemptions when required values, guards, service contracts, or failure paths differ across environments. Require explicit, purpose-limited variance and fail-fast handling. Not for setup drift, test-layer or harness concerns, visual verification, host-OS portability, or Post.Build.Ship workflow gates.
98 lines
playwright-visual-verification
Verify local browser-visible layout and styling with accessibility snapshots, screenshots, and computed-style checks using Playwright.
31 lines
post-build-ship/build
Implement Authorizing User-approved outcomes adaptively and prove them with proportionate QA.
112 lines
post-build-ship/post
Investigate and produce Authorizing User-approvable outcome packets for Build.
92 lines
post-build-ship/ship
Validate final ownership, QA, drift, and commit coherence, then ship authorized work.
103 lines
post-build-ship
Dispatch explicit Post., Build., Ship., Post.Build., Build.Ship., and Post.Build.Ship. workflow requests.
113 lines
react-native-web-styling
Decide whether web, Electron, shared, or mobile UI should use DOM or React Native, and guide existing React Native Web and Uniwind styling, className precedence, spacing, reset, and compatibility fixes.
50 lines
reconcile-setup
Idempotent run-once setup should be reconciled, not trusted - verify it continuously with an event-triggered, fail-loud QA drift-check.
49 lines
research-before-asking
Research and carry decisions before asking the user. Use for ambiguous requirements, missing specifications, ‘which approach’ or ‘should I use X or Y’ choices, or taste, priority, private facts, credentials, or authorization that remain after proportionate research. Present viable options, tradeoffs, a strong recommendation, and its flip condition. Not for verifying claims, responding to an ungrounded unknown, or Post.Build.Ship approval and gate policy; use thinking-is-not-knowing or i-dont-know-is-the-answer.
75 lines
revalidate-without-reset
Refresh an already-rendered stateful application view in place instead of rebuilding it from empty. Use when a view the user is already looking at is re-fetched because of app or window activation, focus or visibility change, reconnect, polling, a manual refresh control, mutation success, or a change in which resource the view shows, and when deciding what to keep, what to replace, and what to ask about. Not for first load, form save semantics, data-fetching library choice, or server-side cache revalidation.
70 lines
rule-of-three
Structure complexity into about three memorable chunks with a rhythm - the phone-number principle - for systems, workflows, names, and output.
48 lines
see-something-say-something
See or smell something off - even outside your scope - and surface it; do not silently fix it (scope creep) or silently ignore it (negligence).
66 lines
temporary-pnpm-package-links
Guidance for temporary pnpm package links across repositories, including consumer-local links, linked-source validation, committed development state, AI publication and unlink prohibitions, and registry verification before consumer production release.
260 lines
test-layer-fit
Choose the lowest meaningful test layer and design deterministic test harness ownership. Use for unit, component, adapter-contract, integration, or E2E placement; suite-load or CI-only failures; timeout, retry, sleep, serialization, warmup, timing-workaround, or suite/config-splitting proposals; and browser, Electron, mobile, subprocess, server, port, process, isolation, readiness, diagnostic, or cleanup ownership. Covers cross-platform proof boundaries and integration-suite reachability. Not for test-framework selection, coverage thresholds, general mocking or assertion style, visual verification, host-OS path or quoting mechanics, or Post.Build.Ship gate and receipt policy.
124 lines
thinking-is-not-knowing
Before asserting a claim, answering a factual question, or recommending a decision, check whether you can say "I know" and name the reason and the failure mode it prevents - if you cannot, it is a guess; do not present it as input. Triggers on "I think"/"probably"/"should"/"I believe" hedges, on offering to check instead of checking, and on reasoning about code or facts you have not opened. Pairs with the i-dont-know-is-the-answer skill. When research has already grounded the options and user judgment remains, use research-before-asking.
111 lines
web-first-components
Author shared UI web-first - the default `.tsx` file is plain DOM with Tailwind, and `.native.tsx`, `.ios.tsx`, or `.android.tsx` files are the React Native overrides - with reference implementations to emulate and a characterization-test-first migration workflow. Use when creating a new shared component, forking a component per platform, choosing platform file extensions, or converting a React Native Web component the task already touches. Not for styling or spacing repairs to existing RNW surfaces, resolver and seam enforcement inside an active Post.Build.Ship, or release and deployment policy.
145 lines
