dev
Skill34 starsChanged 4 months agoMITView on GitHub
Runs a Microsoft App locally with hot reload via `ms app dev`. Use when starting or restarting local development and surfacing the App Player URL.
We split this skill into the rules it gives an agent
6 rules. 0 are common, 0 are distinctive, and 6 are very specific to this project.
0
Common
Most of the 28 edited versions we read keep these.
0
Distinctive
This author's own choices. Worth a look.
6
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 25
Read memory-bank.md from the project root (the project the user has cd'd into, or the path captured from a prior skill invocation) for …
- Very specific: line 42
If auth status reports the wrong UPN or is signed out, prompt the user to fix it before continuing (ms auth login).
- Very specific: line 60
If the user invoked /dev without arguments, run plain $BIN app dev first.
- Very specific: line 85
When the user signals readiness, follow the Ready-to-Ship Gate in shared-instructions.md — commit, push, preview, then ask about /deploy.
- Very specific: line 87
If the dev server prints an error during startup (port conflict, missing ms.config.json, expired auth), stop the background task, surface …
- Very specific: line 96
Do NOT push or deploy from this skill, even if the user mentions it mid-session — bounce them to /deploy (which requires explicit …
“Common” is measured: kept by at least 6 in 10 of the 28 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
📋 Shared Instructions: shared-instructions.md — Cross-cutting concerns.
Local Dev
Starts ms app dev in the project's working directory. The CLI runs two servers — a dev script (Vite or equivalent, default port 8080) and a config server — and prints the App Player URL the user opens in their browser.
This skill does NOT deploy to the cloud. For that, use /deploy.
Workflow
- Memory Bank → 2. Verify Project + Env → 3. Start Dev Server → 4. Hand Off URL
Step 1: Check Memory Bank
Read memory-bank.md from the project root (the project the user has cd'd into, or the path captured from a prior skill invocation) for context — the app slug/GUID and which environment this project targets — so you can confirm you're starting the right app.
ms app dev does not need environmentId or appId passed to it: it runs in the project working directory and reads ms.config.json itself. The memory bank is only for orienting yourself; if it's missing, that's fine — skip straight to Step 2.
Step 2: Verify Project + Env
test -f ms.config.json || { echo "Not in a Microsoft App workspace (no ms.config.json)."; exit 1; }Probe the CLI binary and confirm auth:
BIN=ms
$BIN auth statusIf auth status reports the wrong UPN or is signed out, prompt the user to fix it before continuing (ms auth login). Don't try to repair auth silently — wrong-account dev sessions waste time downstream.
Step 3: Start the Dev Server
Default invocation:
$BIN app devFlags worth surfacing (only when the user mentions a need):
| Flag | When to use |
--port <n> (-p) | Port 8080 is busy. Pick another (e.g., --port 8081). |
--local-app-url <url> (-l) | The user's Vite/dev script is on a non-default URL (default http://localhost:3000). |
--config-only (-C) | Only run the config server. Useful when the user runs npm run dev separately. |
If the user invoked /dev without arguments, run plain $BIN app dev first; surface flags only if the run fails.
Run in the background (run_in_background: true) so the session can continue. Stream stdout via Monitor until the line Ready. You can play your app locally at: <URL> appears — that's the App Player URL.
Step 4: Open the Browser and Hand Off the URL
Open the browser automatically — run Start-Process "<captured URL>" (Windows) or open "<captured URL>" (macOS) / xdg-open "<captured URL>" (Linux) so the user sees their app immediately without copy-pasting. If the open command fails, fall back to printing the URL.
Print the App Player URL as a markdown link so it stays clickable even in narrow terminals. Also show the URL on its own line — markdown links can render as plain label text in some environments (e.g. tables), hiding the actual URL from the user.
Local dev running — opened the app in your default browser.
Local URL: [Open app in browser](<captured URL>)
<captured URL>
Stop: Ctrl+C in the dev terminal (or kill the background task).
Restart: /dev (from this project folder)Do not show the git remote URL in the dev summary — it's an internal detail that confuses users who expect a browser-openable link. The only URL to surface is the App Player URL printed by ms app dev (the domain varies by cloud/region — always use the exact URL the CLI outputs, never hardcode the host).
Then add a one-liner reminder of the iterate → preview → deploy loop:
"The browser tab hot-reloads as I edit code — tell me what to change. When you're happy with it, I'll commit + push your changes, run
ms app play --mode previewfor a cloud preview URL in your environment, and then ask if you want me to/deploy."
When the user signals readiness, follow the Ready-to-Ship Gate in shared-instructions.md — commit, push, preview, then ask about /deploy.
If the dev server prints an error during startup (port conflict, missing ms.config.json, expired auth), stop the background task, surface the error verbatim, and propose the targeted fix:
| Error | Fix |
EADDRINUSE on 8080 | Re-run with $BIN app dev --port 8081 (or kill whatever's on 8080). |
ms.config.json not found | The user is in the wrong directory, or this isn't a Microsoft App workspace. Verify and stop. |
Authentication failed (token expired) | Run $BIN auth login (interactive) and retry. |
Failed to fetch app metadata for <app-id> | App was deleted in the service. Confirm with $BIN app list --json and restore or recreate. |
Do NOT push or deploy from this skill, even if the user mentions it mid-session — bounce them to /deploy (which requires explicit confirmation).
Sharing a cloud preview: The App Player URL from
ms app devis local-only. Once code is pushed to main, use/play(ms app play --mode preview) to open a cloud-hosted preview URL that works for others without a deploy.
Other versions46 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 46
- slopus/happy★ 24ksame name
- microsoft/playwright-cli★ 15ksame name
- atopile/atopile★ 4ksame name
- cexll/myclaude★ 2.8ksame name
- waynesutton/markdown-site★ 628same name
- Automattic/wordpress-activitypub★ 583same name
- justrach/merjs★ 357same name
- stella/stella★ 274same name
- serithemage/serverless-openclaw★ 196same name
- vanillagreencom/kendex★ 76same name
36 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
Used alongsideProjects with it also use metrics-graphana, control-flow and 9 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
slopusSkillmetrics-graphana
Query and manage Grafana dashboards and Prometheus metrics for Happy infrastructure. Covers grafanactl CLI usage, direct Prometheus queries through Grafana proxy, and dashboard-as-code workflows. Use when user asks about metrics, dashboards, monitoring, Grafana, Prometheus, or wants to add/modify panels.
Also in 3 projects that use this
slopusSkillcontrol-flow
Analyze and design control flows and data structures. Produces compact ASCII tree diagrams showing triggers, call chains, payload shapes, state mutations, and re-render effects. Use when user asks to diagram, trace, visualize, or design a flow or data structure.
Also in 3 projects that use this
MicrosoftSkillsessions
Core principles and workflow router for changes to the Agents Window under src/vs/sessions.
Also in 3 projects that use this
ramybarsoumSkilloffice-hours
YC Office Hours -- two modes. Startup mode: six forcing questions that expose demand reality, status quo, desperate specificity, narrowest wedge, observation, and future-fit. Builder mode: design thinking brainstorming for side projects, hackathons, learning, and open source. Saves a design doc. Use when asked to "brainstorm this", "I have an idea", "help me think through this", "office hours", or "is this worth building". Proactively suggest when the user describes a new product idea or is exploring whether something is worth building -- before any code is written.
Also in 3 projects that use this
Microsoft AzureSkilltest
Also in 5 projects that use this
Microsoft AzureSkilldesign
Design rules and conventions for the API Center Portal. Use when editing detail pages, card components, badges, layout, navigation, sidebars, or headers. Covers badge styling, metadata placement, page navigation patterns, and layout alignment.
Also in 6 projects that use this
In this repository23 other files it gives its agents.
- github-actions/AGENTS.mdAGENTS.md
- plugins/microsoft-managed-apps/AGENTS.mdAGENTS.md
- add-azuredevopsSkill
- add-backendSkill
- add-data-sourceSkill
- add-dataverseSkill
- add-excelSkill
- add-mcscopilotSkill
- add-office365Skill
- add-office365-usersSkill
- add-onedriveSkill
- add-sharepointSkill
- add-teamsSkill
- add-workiqSkill
- create-appSkill
- delete-appSkill
- deploySkill
- list-appsSkill
- list-connectorsSkill
- playSkill
- share-linkSkill
- shareSkill
- stateSkill
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

