winapp CLI is a command-line tool for Windows application development that manages SDKs, app identity, manifests, certificates, packaging, and build tools. It helps developers using frameworks such as .NET, Win32, CMake, Electron, or Rust access Windows-native development capabilities. The catalogue add-ons provide agent workflows for using the CLI.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add microsoft/winappCli --skill winapp-find-uigit clone --depth 1 https://github.com/microsoft/winappCliWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/microsoft/winappcli/winapp-find-ui)<a href="https://agentmods.dev/skills/microsoft/winappcli/winapp-find-ui"><img src="https://agentmods.dev/badge/skills/microsoft/winappcli/winapp-find-ui/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/microsoft/winappcli/winapp-find-ui"><img src="https://agentmods.dev/badge/skills/microsoft/winappcli/winapp-find-ui.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00075 | $0.02954 |
| Opus 5.5 | $0.00030 | $0.01182 |
| Sonnet 5.5 | $0.00015 | $0.00591 |
| Haiku 4.5 | $0.00007 | $0.00295 |
Grade A, and why
winapp-find-ui scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 215 lines — stays where its author put it; the contents beside it link to each section on GitHub.
If you can't run winapp yourself (no shell, or the command is denied), give the user the exact winapp command(s) for their project instead of only describing the steps.
This is an agent-first command
find-ui was designed for you, the agent — not primarily for a human browsing a
gallery. It exists because the failure mode it prevents is an agent-specific one:
writing plausible-looking XAML for a control whose real markup, properties, or
namespace differ from what you recall. Treat it as the source of truth for WinUI
markup:
- Fetch a real sample before writing WinUI markup. If you are about to hand-write
XAML for a control you have not just looked at, search for it first and fetch the
scenario with
--id. The returned code comes from the shipping WinUI 3 Gallery and Windows Community Toolkit, so it compiles. - Prefer it over recall and over web search. It returns code from a pinned, cached corpus of the real galleries rather than a blog post of unknown vintage.
- Use
--json. Search,--id, and--listall emit stable structured shapes, and every failure — including parser errors — is a flat{"error": "..."}on stdout with a non-zero exit code, so you can branch on the result on every path. - Pair it with
winapp find-api.find-uigives you working markup;find-apiverifies any property you then change or add.
Humans can and do run it directly, and everything below works fine typed by hand. But
the ergonomics (compact search → --id fetch, --json, exit codes) are tuned for
agent loops.
When to use
Use this skill when building a WinUI 3 UI and you need to discover which control fits an intent and get a real, working code example — without leaving the CLI or guessing at control names and APIs.
winapp find-ui searches the WinUI 3 Gallery and the Windows Community
Toolkit (plus a few curated core patterns) and returns a working code
snippet plus where it came from. A third source, the microsoft-ui-reactor
ReactorGallery, is opt-in: it is excluded from a normal search and is only
searched when you pass --source reactor.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 3d ago Changed · +7 lines 3c680924dfe1
- 23d ago Changed · +17 lines c6fbfb2b1978
- 24d ago Changed · +2 lines · -129 tokens per session 6e931b3f9131
- 1mo ago Changed · +4 lines 1df335041641
- 1mo ago Changed c4f06cfcb6fe
- 1mo ago Changed · +2 lines e382bce26c7e
- 1mo ago Changed · +49 lines · +56 tokens per session d6c71e681a4d
- 1mo ago Changed · +6 lines e084788e8f8c
- 2mo ago First seen · 128 lines · 148 tokens per session scan A 96e9c726e2d2
winapp-find-ui is a skill published in the GitHub repository microsoft/winappCli (1,357 stars, last pushed 2d ago), licensed MIT. It adds 75 tokens to every session and 2,954 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
brand-identity
Use when a project needs its visual foundation built or consolidated into one system: logo brief, color system in HEX/RGB/CMYK/OKLCH with proven AA contrast, type system, usage rules, and an exported W3C design-tokens.json that later skills consume. NOT the applied UI pixels (that is design), NOT the words or tone…
portpilot
Start, stop and check local dev servers through PortPilot instead of bare shell commands. Use whenever you are about to run a dev server (npm run dev, next dev, vite, uvicorn, flask run, python -m http.server), free a port, or find out what is listening on a port.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
interview
Ask one useful structured question at a time only when material product/implementation choices are genuinely missing; remember answers and produce a brief/spec. Discoverable facts should be investigated instead of asked.
refocusing
Use when a long-running agent may have lost the product outcome, when context was compacted, when work has crossed a major boundary, or when a fresh path-based trace is needed before the next consequential action. Not for fresh-session orientation, waking an idle seat, or checkpoints.
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.