local-dev
- Repo stars 330
- License MIT
- Author updated Live
- Author repo claude-skill-registry
- Domain
- Data
- Compatible agents
-
- Claude Code
- Cursor
- Cline
- Codex
- Windsurf
- Gemini CLI
- +20
- Trust score
- 94 / 100 · audit passed
- Author / version / license
- @majiayu000 · MIT
- Token usage
- Lean
- Setup complexity
- Guided setup
- External API key
- Not required
- Operating systems
- macOS
- Runtime requirements
- No special requirements
- Permissions
-
- Read-only
- Shell exec
- Write / modify
- Network behavior
- Local-only
- Install commands
- 26 variants
Profile is derived at build time from SKILL.md and install vectors. Subject to drift from author intent.
Heads up: 未限定 allowed-tools，默认拥有全部工具权限。
---
name: local-dev
description: Start local development environment with backend and macOS app Start the backend server and macO…
category: data
runtime: no special runtime
---
# local-dev output preview
## PART A: Task fit
- Use case: Start local development environment with backend and macOS app Start the backend server and macOS app for local development. Run /local-dev to start both the backend and app, or: lsof -ti:8000 | xargs kill -9 2>/dev/null || true python3 -c "from dotenv import loaddotenv; loaddotenv(); import subprocess; subprocess.run(['python3', '-m', 'uvicorn', 'main:ap….
- Inputs: target material, constraints, expected output, and acceptance criteria.
- Evidence boundary: follow “Usage / Commands / Backend” and do not present inference as author intent.
## PART B: Execution result
- **01** The card summarizes the use case; runtime output centers on “Start local development environment with backend and macOS app Start the backend server and macOS app for local development. Run /local-dev to start both the backend and app, or: lsof -ti:8000 | xargs kill -9 2>/dev/null || true python3 -c "from dotenv import loaddotenv; loaddotenv(); import subprocess; subprocess.run(['python3', '-m', 'uvicorn', 'main:ap…”.
- **02** When the source has headings, the agent prioritizes “Usage / Commands / Backend” so the result follows the author’s structure.
- **03** Typical output includes task judgment, concrete steps, required commands or file edits, validation, and follow-up options.
- **04** Risk context follows the fingerprint: read files, run shell commands, write/modify files; mostly runs locally; usually needs no extra API key.
## Running Rules
- read files, run shell commands, write/modify files; mostly runs locally; usually needs no extra API key.
- Validate with a small sample before expanding scope.
- Return the result, validation criteria, and next iteration options.The source mentions slash commands such as `/local-dev`; use them first when your agent supports command triggers.
Name target files or source material, expected output, forbidden changes, and whether network or shell access is allowed. Permission fingerprint: read files, run shell commands, write/modify files.
Start with a small task and check whether the result follows “Usage / Commands / Backend”. Inspect diffs, logs, previews, or tests before expanding scope.
Confirm the final output includes a concrete result, evidence, and next action. If it stays generic, tighten inputs, boundaries, and acceptance criteria.
---
name: local-dev
description: Start local development environment with backend and macOS app Start the backend server and macO…
category: data
source: majiayu000/claude-skill-registry
---
# local-dev
## When to use
- Start local development environment with backend and macOS app Start the backend server and macOS app for local develo…
- Use it when the task has clear inputs, repeatable steps, and validation criteria.
## What to provide
- Target material, scope, expected result, and forbidden changes.
- Whether network, commands, file writes, or external services are allowed.
## Execution rules
- Organize steps around “Usage / Commands / Backend” and keep inference separate from source facts.
- read files, run shell commands, write/modify files; mostly runs locally; usually needs no extra API key.
- Validate with a small sample before expanding the task.
## Output requirements
- Return the deliverable, key evidence, validation method, and next action.
- Mark missing information as unknown; do not invent commands, platforms, or dependencies.The author source anchors workflow facts; repository files anchor sources and commands; Fluxly only adds fit, limitations, and quality judgment.
skill "local-dev" {
input -> user goal + target files + boundaries + acceptance criteria
context -> Usage / Commands / Backend
rules -> SKILL.md triggers / order / output contract
runtime -> no special runtime | read files, run shell commands, write/modify files | mostly runs locally
guardrails -> usually needs no extra API key + small-sample validation + diff/log review
output -> copyable result + checklist + next iteration
}Start Local Development Environment
Start the backend server and macOS app for local development.
Usage
Run /local-dev to start both the backend and app, or:
/local-dev backend- start backend only/local-dev app- build and run the macOS app (debug mode)/local-dev app --clean- clean build and run (forces Swift recompilation)/local-dev app --release- build and run in release mode
Commands
Backend
cd backend
lsof -ti:8000 | xargs kill -9 2>/dev/null || true
python3 -c "from dotenv import load_dotenv; load_dotenv(); import subprocess; subprocess.run(['python3', '-m', 'uvicorn', 'main:app', '--host', '0.0.0.0', '--port', '8000', '--reload'])"App
app/scripts/dev-macos.sh $EXTRA_ARGSWhere $EXTRA_ARGS can be:
--clean- force clean build (removes build cache, ensures Swift recompilation)--release- build in release mode instead of debug--no-run- build only, don't launch the app
Argument Handling
When $ARGUMENTS is "backend", only start the backend.
When $ARGUMENTS is "app", build and run the macOS app.
When $ARGUMENTS starts with "app ", pass remaining args to the script (e.g., "app --clean").
When $ARGUMENTS is empty or "all", start both backend and app.
Decide Fit First
Design Intent
How To Use It
Boundaries And Review