# Backend Workflow

> A Claude skill from Mallikarjun-Roddannavar/playwright-agentic-automation.

- **Type:** Skill
- **Install:** `agentstack add skill-mallikarjun-roddannavar-playwright-agentic-automation-backend-workflow`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [Mallikarjun-Roddannavar](https://agentstack.voostack.com/s/mallikarjun-roddannavar)
- **Installs:** 0
- **Category:** [AI & ML](https://agentstack.voostack.com/c/ai-and-ml)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [Mallikarjun-Roddannavar](https://github.com/Mallikarjun-Roddannavar)
- **Source:** https://github.com/Mallikarjun-Roddannavar/playwright-agentic-automation/tree/main/.agents/skills/backend-workflow

## Install

```sh
agentstack add skill-mallikarjun-roddannavar-playwright-agentic-automation-backend-workflow
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# Backend Workflow Skill

## Purpose
Use this skill when working on FastAPI backend changes in this repository.

## Applies to
- `backend/main.py`
- `backend/auth.py`
- `backend/models.py`
- `backend/requirements.txt`
- `backend/database.json`

## Core rules
- Preserve JWT + RBAC behavior:
  - `admin` full access
  - `editor` create/edit/upload only
  - `viewer` read-only
- Keep `/token` password flow working.
- Keep optional OAuth endpoints functional when env vars are set.
- Do not break `/docs`.
- Keep `detail` messages predictable for frontend toasts/tests.

## Standard workflow
1. Read current endpoint + dependency usage in `main.py`.
2. Apply minimal changes.
3. If auth logic changes, keep it centralized in `auth.py`.
4. Run backend validation commands.
5. Update README when setup/env/api contract changes.

## Validation commands
Run from `backend/`:

```bash
python -m py_compile main.py auth.py models.py
uvicorn main:app --reload --port 8000
```

Optional API sanity checks:
- `GET /health`
- `POST /token`
- one protected folder/file endpoint with Bearer token

## Guardrails
- Keep JSON storage simple and BOM-safe.
- Keep uploaded file cleanup behavior on folder/file delete.
- Avoid introducing external DB/infra unless explicitly requested.

## Verification Marker (Temporary)
- If this skill is applied in a run, include this exact phrase once in a progress update:
  - `backend-workflow skill applied`

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [Mallikarjun-Roddannavar](https://github.com/Mallikarjun-Roddannavar)
- **Source:** [Mallikarjun-Roddannavar/playwright-agentic-automation](https://github.com/Mallikarjun-Roddannavar/playwright-agentic-automation)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-mallikarjun-roddannavar-playwright-agentic-automation-backend-workflow
- Seller: https://agentstack.voostack.com/s/mallikarjun-roddannavar
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.