frontend-visualqa 0.1.0__tar.gz

frontend_visualqa-0.1.0/.agents/skills/README.md

@@ -0,0 +1,11 @@
+# Agent skills (Codex / OpenAI compatible clients)
+
+The canonical skill lives at `skills/frontend-visualqa/`.
+
+`.agents/skills/frontend-visualqa/` is only a compatibility wrapper:
+
+- `SKILL.md` is a symlink to the canonical skill body
+- `references/` is a symlink to the canonical support files
+- `agents/` is a symlink to the canonical agent metadata
+
+Edit the canonical files under `skills/frontend-visualqa/` so the content does not drift across install paths.

frontend_visualqa-0.1.0/.agents/skills/frontend-visualqa/SKILL.md

@@ -0,0 +1 @@
+../../../skills/frontend-visualqa/SKILL.md

frontend_visualqa-0.1.0/.agents/skills/frontend-visualqa/agents/openai.yaml

@@ -0,0 +1,13 @@
+appearance:
+  name: "Frontend Visual QA"
+  description: "Claim-based visual QA for local frontends"
+
+interface:
+  display_name: "Frontend Visual QA"
+  description: "Verify local frontend changes with screenshot-backed visual claims"
+  brand_color: "#0F766E"
+  default_prompt: "Verify a local frontend change with frontend-visualqa"
+
+dependencies:
+  mcp_servers:
+    - frontend-visualqa

frontend_visualqa-0.1.0/.agents/skills/frontend-visualqa/references/claim-writing.md

@@ -0,0 +1,55 @@
+# Claim Writing
+
+Claims should describe one visible fact each.
+
+Good claims:
+
+- `The modal title reads "Invite teammate"`
+- `The Save button is visible without scrolling`
+- `The selected tab has a blue underline`
+- `At 375px width, the sidebar is replaced by a menu button`
+- `After form submit, a success toast appears in the top right corner`
+
+Weak claims:
+
+- `The modal works`
+- `The page looks good`
+- `The layout is cleaner now`
+- `The interaction feels smooth`
+
+## Rules
+
+1. Write claims that can be proven from the final screenshot.
+2. Keep each claim to a single user-visible fact.
+3. Split compound assertions into separate claims.
+4. Use exact visible copy for headings, labels, and button text when text matters.
+5. Always set an explicit viewport when responsive behavior matters.
+
+## Navigation Hints
+
+If the page needs interaction before the claim can be judged, keep the claim short and put the setup steps in `navigation_hint`.
+
+Good:
+
+- Claim: `The delete confirmation dialog is visible`
+- Navigation hint: `Open the first row action menu and click Delete before judging the claim.`
+
+Bad:
+
+- Claim: `Open the first row action menu, click Delete, and confirm the delete dialog is visible`
+
+## Claim Batching
+
+Prefer 1-5 related claims per run.
+
+Good batch:
+
+- `The modal title reads "Edit Task"`
+- `The Save button is visible without scrolling`
+- `The Cancel button is left of Save`
+
+Bad batch:
+
+- 20 unrelated claims across multiple pages and viewports
+
+Small batches make failures easier to diagnose and keep the agent from conflating unrelated states.

frontend_visualqa-0.1.0/.agents/skills/frontend-visualqa/references/install.md

@@ -0,0 +1,62 @@
+# Install And Setup
+
+## Requirements
+
+- A running local frontend
+- Yutori API key — run `uvx yutori auth login` or set `YUTORI_API_KEY`
+- Playwright Chromium installed once
+
+## Quick Install
+
+Authenticate with Yutori:
+
+```bash
+uvx yutori auth login
+```
+
+MCP server (works with all clients):
+
+```bash
+npx add-mcp -n frontend-visualqa "uvx frontend-visualqa serve"
+```
+
+Skill (cross-agent):
+
+```bash
+npx skills add yutori-ai/frontend-visualqa -g
+```
+
+Restart the agent client after setup.
+
+## CLI Fallback
+
+If the MCP server is not installed, the same runner can be used directly:
+
+```bash
+frontend-visualqa screenshot http://localhost:3000
+frontend-visualqa verify http://localhost:3000 --claims "The heading reads Dashboard"
+```
+
+## Persistent Login
+
+For auth-gated apps, populate the persistent browser profile once:
+
+```bash
+frontend-visualqa login http://localhost:3000/login
+```
+
+Subsequent runs can use persistent mode:
+
+```bash
+frontend-visualqa verify http://localhost:3000/dashboard \
+  --browser-mode persistent \
+  --claims "The user avatar is visible in the header"
+```
+
+## If Tools Are Missing
+
+If the skill is installed but the `frontend-visualqa` tools are unavailable in the current client:
+
+1. Install or register the MCP server.
+2. Restart the client so it rescans skills and MCP servers.
+3. Retry with `take_screenshot` before writing claims.

frontend_visualqa-0.1.0/.agents/skills/frontend-visualqa/references/protocol.md

@@ -0,0 +1,47 @@
+# QA Protocol
+
+## Preflight
+
+Before running claim verification, confirm:
+
+- the local URL is reachable
+- the viewport matches the scenario you care about
+- the page does not require an unavailable login
+- the claims are concrete and short
+
+If any of that is unclear, call `take_screenshot` first.
+
+## Recommended Loop
+
+1. Use the app's normal tooling, the browser's current session, or a `navigation_hint` to reach the relevant state.
+2. Capture a screenshot baseline if route or state is uncertain.
+3. Run `verify_visual_claims` on a small batch of related claims.
+4. Read the structured result for each claim.
+5. Inspect the saved screenshots when a claim fails or is inconclusive.
+6. Fix the frontend and rerun the same claims.
+
+## Status Meanings
+
+- `passed`: visual evidence matched the claim
+- `failed`: the page rendered something different from the claim
+- `inconclusive`: the runner explored but could not determine the claim confidently
+- `not_testable`: the environment blocked verification, usually because the page was unreachable, crashed, or required unavailable auth
+
+## When To Reset Browser State
+
+Use `manage_browser` if:
+
+- the runner is clearly on the wrong page
+- stale cookies or local storage are affecting the result
+- a previous run left the browser in an unexpected state
+- the viewport needs to be changed without restarting the whole client session
+
+For auth-gated flows, prefer persistent mode over repeating manual login on every run.
+
+## Scope Boundaries
+
+This skill is for targeted, claim-based visual QA during development. It is not meant to replace:
+
+- end-to-end functional coverage
+- CI-wide regression suites
+- open-ended design critique without explicit claims

frontend_visualqa-0.1.0/.claude-plugin/marketplace.json

@@ -0,0 +1,18 @@
+{
+  "name": "frontend-visualqa-plugins",
+  "owner": {
+    "name": "Yutori",
+    "email": "support@yutori.com"
+  },
+  "metadata": {
+    "description": "Official frontend-visualqa plugin marketplace for Claude Code",
+    "version": "1.0.0"
+  },
+  "plugins": [
+    {
+      "name": "frontend-visualqa",
+      "source": "./",
+      "description": "Local visual QA for frontends with Yutori n1 and Playwright"
+    }
+  ]
+}

frontend_visualqa-0.1.0/.claude-plugin/plugin.json

@@ -0,0 +1,16 @@
+{
+  "name": "frontend-visualqa",
+  "version": "1.0.0",
+  "description": "Local visual QA for frontends with Yutori n1 and Playwright",
+  "author": {
+    "name": "Yutori",
+    "email": "support@yutori.com",
+    "url": "https://yutori.com"
+  },
+  "homepage": "https://github.com/yutori-ai/frontend-visualqa",
+  "repository": "https://github.com/yutori-ai/frontend-visualqa",
+  "license": "Apache-2.0",
+  "keywords": ["frontend", "visual-qa", "browser", "playwright", "mcp"],
+  "skills": "skills",
+  "mcpServers": ".mcp.json"
+}

frontend_visualqa-0.1.0/.codex/config.toml

@@ -0,0 +1,3 @@
+[mcp_servers.frontend-visualqa]
+command = "uvx"
+args = [ "frontend-visualqa", "serve" ]

frontend_visualqa-0.1.0/.cursor-plugin/marketplace.json

@@ -0,0 +1,18 @@
+{
+  "name": "frontend-visualqa-plugins",
+  "owner": {
+    "name": "Yutori",
+    "email": "support@yutori.com"
+  },
+  "metadata": {
+    "description": "Official frontend-visualqa plugin marketplace for Cursor",
+    "version": "1.0.0"
+  },
+  "plugins": [
+    {
+      "name": "frontend-visualqa",
+      "source": "./",
+      "description": "Local visual QA for frontends with Yutori n1 and Playwright"
+    }
+  ]
+}

frontend_visualqa-0.1.0/.cursor-plugin/plugin.json

@@ -0,0 +1,16 @@
+{
+  "name": "frontend-visualqa",
+  "version": "1.0.0",
+  "description": "Local visual QA for frontends with Yutori n1 and Playwright",
+  "author": {
+    "name": "Yutori",
+    "email": "support@yutori.com",
+    "url": "https://yutori.com"
+  },
+  "homepage": "https://github.com/yutori-ai/frontend-visualqa",
+  "repository": "https://github.com/yutori-ai/frontend-visualqa",
+  "license": "Apache-2.0",
+  "keywords": ["frontend", "visual-qa", "browser", "playwright", "mcp"],
+  "skills": "skills",
+  "mcpServers": ".mcp.json"
+}

frontend_visualqa-0.1.0/.github/workflows/publish_to_pypi.yml

@@ -0,0 +1,28 @@
+name: Publish frontend-visualqa to PyPI
+
+on:
+  release:
+    types: [published]
+  workflow_dispatch:
+
+jobs:
+  publish:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+
+      - uses: actions/setup-python@v5
+        with:
+          python-version: "3.12"
+
+      - name: Install build tools
+        run: pip install build twine
+
+      - name: Build package
+        run: python -m build
+
+      - name: Publish to PyPI
+        run: twine upload dist/*
+        env:
+          TWINE_USERNAME: __token__
+          TWINE_PASSWORD: ${{ secrets.PYPI_API_TOKEN }}

frontend_visualqa-0.1.0/.gitignore

@@ -0,0 +1,227 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[codz]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+.DS_Store
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py.cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# UV
+#   Similar to Pipfile.lock, it is generally recommended to include uv.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#uv.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+#poetry.toml
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#   pdm recommends including project-wide configuration in pdm.toml, but excluding .pdm-python.
+#   https://pdm-project.org/en/latest/usage/project/#working-with-version-control
+#pdm.lock
+#pdm.toml
+.pdm-python
+.pdm-build/
+
+# pixi
+#   Similar to Pipfile.lock, it is generally recommended to include pixi.lock in version control.
+#pixi.lock
+#   Pixi creates a virtual environment in the .pixi directory, just like venv module creates one
+#   in the .venv directory. It is recommended not to include this directory in version control.
+.pixi
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.envrc
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/
+
+# Abstra
+# Abstra is an AI-powered process automation framework.
+# Ignore directories containing user credentials, local state, and settings.
+# Learn more at https://abstra.io/docs
+.abstra/
+
+# Visual Studio Code
+#  Visual Studio Code specific template is maintained in a separate VisualStudioCode.gitignore 
+#  that can be found at https://github.com/github/gitignore/blob/main/Global/VisualStudioCode.gitignore
+#  and can be added to the global gitignore or merged into this file. However, if you prefer, 
+#  you could uncomment the following to ignore the entire vscode folder
+# .vscode/
+
+# Ruff stuff:
+.ruff_cache/
+
+# frontend-visualqa runtime artifacts
+artifacts/
+
+# Agent / planning artifacts (internal docs, not shipped)
+agent_artifacts/
+
+# Node
+node_modules/
+package-lock.json
+
+# Playwright
+/test-results/
+/playwright-report/
+/blob-report/
+/playwright/.cache/
+
+# PyPI configuration file
+.pypirc
+
+# Cursor
+#  Cursor is an AI-powered code editor. `.cursorignore` specifies files/directories to
+#  exclude from AI features like autocomplete and code analysis. Recommended for sensitive data
+#  refer to https://docs.cursor.com/context/ignore-files
+.cursorignore
+.cursorindexingignore
+
+# Marimo
+marimo/_static/
+marimo/_lsp/
+__marimo__/
+
+# Claude Code
+.claude/

frontend_visualqa-0.1.0/.mcp.json

@@ -0,0 +1,8 @@
+{
+  "mcpServers": {
+    "frontend-visualqa": {
+      "command": "uvx",
+      "args": ["frontend-visualqa", "serve"]
+    }
+  }
+}