agentleFS
rm2thaddeusrm2thaddeus/Aitor_Skills/start-dev-graph/SKILL.md

start-dev-graph

Skill4 starsChanged 10 months agoMITView on GitHub

Start, stop, or check Dev Graph services on this machine. Use when the user asks to start Dev Graph, start backend only, start full stack, restart, stop, or check Docker, Neo4j, API, or UI status, or to provide a specific Dev Graph page URL.

The file

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 6 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈6

    Distinctive · estimate

    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
  1. Distinctive:

    Use this skill to run Dev Graph locally with the right subset of services.

    line 8
  2. Distinctive:

    If missing, stop and ask for the correct working directory.

    line 18
  3. Distinctive:

    stop: stop Docker services and list any remaining processes

    line 26
  4. Distinctive:

    Check Docker CLI and Docker Compose:

    line 29
  5. Distinctive:

    If Docker is installed but not running, say so and stop.

    line 32
  6. Distinctive:

    When launching uvicorn or npm, use new terminal windows so the main session stays responsive.

    line 44
  7. Very specific:

    Do not redirect uvicorn output to dev_graph_api.log in the repo root.

    line 63

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Start Dev Graph

Use this skill to run Dev Graph locally with the right subset of services.

Quickstart

  • Full stack: powershell -ExecutionPolicy Bypass -File skills\\start-dev-graph\\scripts\\start_dev_graph.ps1 -Mode full
  • Backend only: powershell -ExecutionPolicy Bypass -File skills\\start-dev-graph\\scripts\\start_dev_graph.ps1 -Mode backend

Workflow

  1. Confirm repo root
  • Require developer_graph/api.py and start_dev_graph.ps1.
  • If missing, stop and ask for the correct working directory.
  1. Decide the requested mode
  • full: Neo4j + API + UI
  • backend: Neo4j + API only
  • services: just Neo4j
  • frontend: only Dev Graph UI
  • status: report what is running
  • stop: stop Docker services and list any remaining processes
  1. Docker preflight
  • Check Docker CLI and Docker Compose:
    • docker version
    • docker compose version
  • If Docker is installed but not running, say so and stop.
  1. Start sequence
  • full: run .\start_dev_graph.ps1
  • backend:
    • docker compose up -d neo4j
    • uvicorn developer_graph.api:app --host 0.0.0.0 --port 8080 --reload
  • services:
    • docker compose up -d neo4j
  • frontend:
    • cd tools/dev-graph-ui then npm run dev

When launching uvicorn or npm, use new terminal windows so the main session stays responsive.

  1. Status checks
  1. Stop sequence
  • docker compose down
  • Remind the user to close any uvicorn or npm windows still running.

Notes

  • Docker Compose service name is neo4j in docker-compose.yml.
  • The Windows batch script uses neo4j_db; do not copy that name here.
  • Do not redirect uvicorn output to dev_graph_api.log in the repo root. The app writes the same file and will raise a permission error.
  • The UI may choose port 3001 if 3000 is already in use; the script expects 3001.

Script

  • Run: powershell -ExecutionPolicy Bypass -File skills\\start-dev-graph\\scripts\\start_dev_graph.ps1 -Mode full
  • Backend only: -Mode backend
  • Frontend + open page: -Mode frontend -Open -Page /dev-graph/structure
  • Note: -Open is required to open a browser; -Page alone will not open anything.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.