start-dev
Skill1 starsChanged 25 days agoMITView on GitHub
Launch one of the user's local-dev apps (nebi, nebari-landing, nebari-chat-pack, jhub-apps, nebari-llm-serving-pack, provenance-collector-pack, nebari-apps-pack, collab-hub-pack, analytics-pack, nebari-local) in its fast inner-loop mode; for nebari-local, brings up the local cluster and its gateway port-forward. Triggers on /start-dev, "start dev for <app>", "run <app> locally", "spin up <app>", "launch <app> for local development".
4 other projects use a version of this.
Adopted by
Most recently taken up by
- StormAIDE/stormai_ClaudeCode_LabCamp_workshoptheir own version, first seen Oct 25, 2026
- Tamircohen28/tamirs-superpowerstheir own version, first seen Aug 3, 2026
- kompiro/hanetheir own version, first seen May 12, 2026
- StormAIDE/ClaudeCodeLabCamptheir own version, first seen May 6, 2026
Other versions4 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 4
- Tamircohen28/tamirs-superpowers★ 2same name
- StormAIDE/ClaudeCodeLabCamp★ 1same name
- StormAIDE/stormai_ClaudeCode_LabCamp_workshop★ 1same name
- kompiro/hane★ 0same name
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.
In this repository12 other files it gives its agents.
- a11y-auditSkill
- backend-conventionsSkill
- decision-deckSkill
- frontend-conventionsSkill
- github-issueSkill
- k8s-conventionsSkill
- new-nebari-appSkill
- new-projectSkill
- pr-reviewSkill
- talk-deckSkill
- tool-evalSkill
- web-app-auditSkill
The file
We split this skill into the rules it gives an agent
3 rules. 0 are common, 2 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 3 edited versions we read keep these.
2
Distinctive
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 29
If no app is named or the match is ambiguous, list the apps and ask which one.
- Distinctive: line 45
Always end with the app's URLs list (from its recipe, corrected for what actually started — e.g.
- Very specific: line 52
Write references/apps/<app>.md in the same shape as the others (heading with repo path, one-line summary, the local-mode commands, URLs, …
“Common” is measured: kept by at least 6 in 10 of the 3 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
start-dev
Starts a named app in its lightweight local mode (fast inner loop), not the full Kubernetes cluster mode. Cluster mode is documented per app but only used when the user explicitly asks for it ("full cluster", "k8s", "minikube", "k3d", "Tilt").
Usage
The user names an app (e.g. /start-dev nebi, "spin up the chat pack"). Match loosely:
| Alias / mention | App | Repo |
nebi | nebi | ~/repos/nebi |
nebari-landing, landing | nebari-landing | ~/repos/nebari-landing |
nebari-chat-pack, chat, chat-pack | nebari-chat-pack | ~/repos/nebari-chat-pack |
jhub-apps, jhub, jupyterhub | jhub-apps | ~/repos/jhub-apps |
nebari-llm-serving-pack, llm-serving, llm-pack, key-manager | nebari-llm-serving-pack | ~/repos/nebari-llm-serving-pack |
provenance-collector-pack, provenance, provenance-collector, pc | provenance-collector-pack | ~/repos/provenance-collector-pack |
nebari-apps-pack, apps-pack, apps, nebari-apps | nebari-apps-pack | ~/repos/nebari-apps-pack |
collab-hub-pack, collab-hub, collab, hub | collab-hub-pack | ~/repos/collab-hub-pack |
analytics-pack, analytics, umami, analytics pack | analytics-pack | ~/repos/analytics-pack |
nebari-local, local, cluster, port-forward, gateway | nebari-local | ~/repos/nebari-local |
If no app is named or the match is ambiguous, list the apps and ask which one.
How to run
Each app's recipe — commands, ports, env vars, URLs, gotchas, and cluster mode — lives in
references/apps/<app>.md (named after the App column above). Read only the matched
app's file, then follow it.
Dev servers are long-running. Start each server with run_in_background: true, then
report the URL(s) the user should open. After starting, briefly tail the background output
to confirm it came up (no immediate crash) before reporting success. If a documented command
fails, check that repo's README.md / Makefile — these commands may drift. When you find
drift, offer to fix the app's recipe file.
After launching
Always end with the app's URLs list (from its recipe, corrected for what actually started — e.g. the real Vite port, or only the processes that were launched), plus: which command was run and any env var the user still needs to set. Note that the server is running in the background and how to stop it (Ctrl+C / the background-task controls).
Adding an app
Write references/apps/<app>.md in the same shape as the others (heading with repo path,
one-line summary, the local-mode commands, URLs, notes, then cluster mode), add a row to
the table above, and add the app name to the description so it triggers.
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.