finish-with-dev-server
Skill0 starsChanged 2 months agoMITView on GitHub
After implementation or UI fixes, ensure local dev servers are running on documented ports, resolve port conflicts, validate health or title, and report test URLs. Use when finishing a coding task on a runnable app.
- Reads credentials
In this repository26 other files it gives its agents.
- AGENTS.mdAGENTS.md
- .cursor/rules/automate-before-manual.mdcCursor rule
- .cursor/rules/finish-task-dev-server.mdcCursor rule
- brainstormingSkill
- caveman-commitSkill
- find-skillsSkill
- semantic-versionSkill
- systematic-debuggingSkill
- verification-before-completionSkill
- writing-plansSkill
- ask-before-architectureSkill
- automate-before-manualSkill
- caveman-commitSkill
- diagrams-mermaidSkill
- dont-be-lazySkill
- dont-forgetSkill
- find-jobSkill
- google-calendar-mcpSkill
- init-fmzSkill
- instagram-chrome-postSkill
- project-initSkill
- recapSkill
- semantic-versionSkill
- skills-sh-maintainerSkill
- ui-change-e2eSkill
- validate-before-shareSkill
The file
We split this skill into the rules it gives an agent
6 rules. About 0 are common, 4 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 12
When a task changed runnable code (UI, API, config), before closing:
- Distinctive: line 16
Read project docs first — prefer ports already written somewhere:
- Distinctive: line 22
Do not invent a port if the repo documents one.
- Distinctive: line 30
When the preferred port is taken:
- Very specific: line 35
If no fallback is documented, pick the next free port, note it in the reply, and align env vars if the project requires it (VITE_API_URL, …
- Very specific: line 39
Use the project's identity check: GET /health, /api/health, page <title>, or equivalent from AGENTS.md.
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Finish with dev server
When a task changed runnable code (UI, API, config), before closing:
1. Find documented ports
Read project docs first — prefer ports already written somewhere:
AGENTS.md,README.md,docs/stack.md.env.example,vite.config.*,package.jsonscripts- Fallback order in project rules (e.g. backend 3000 → 3001)
Do not invent a port if the repo documents one.
2. Check if servers are up
Inspect terminals and listen on the documented port(s). Start missing processes without asking permission using the project's documented commands.
3. Port already in use
When the preferred port is taken:
- Identify the owning process (PID, command line, working directory).
- Same project (cwd under this repo, or known dev script for this app) → stop that process, restart on the documented port.
- Another project or unknown → do not kill; use the next fallback port documented in this repo (e.g. 3000 → 3001 → 3002). Update nothing in the other project.
- If no fallback is documented, pick the next free port, note it in the reply, and align env vars if the project requires it (
VITE_API_URL,CORS_ORIGIN, etc.).
4. Validate
Use the project's identity check: GET /health, /api/health, page <title>, or equivalent from AGENTS.md.
5. Report
Give the user effective URLs (scheme + host + port + path). Never end a coding task without test URLs when a local app exists.
Skip
Libraries, templates with no dev server, or tasks that only changed docs/skills with no runnable app.
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.

