valantic-brand
valantic-cec-deutschland-gmbh/claude-code-marketplace · skills.sh
Open source Repository Open in the app JSON README (API)
About
Skill publicada por valantic-cec-deutschland-gmbh/claude-code-marketplace no skills.sh. Instale com: npx skills add valantic-cec-deutschland-gmbh/claude-code-marketplace@valantic-brand
Details
- Kind
- Agent skills
- Publisher
- valantic-cec-deutschland-gmbh
- Origin
- skillssh
- Category
- ferramentas
- Last push
- 2026-06-10T19:02:42Z
- Repository state
- ativo
- Language
- Python
- License
- NOASSERTION
- Added
- 2026-10-07 05:28:07
- Updated
- 2026-10-07 05:28:07
- Origin id
valantic-cec-deutschland-gmbh/claude-code-marketplace/valantic-brand
README
# Valantic Claude Code Marketplace
Company-internal Claude Code marketplace providing branded tools, workflows, and coding standards for Valantic developers.
## Installation
```bash
# Add the Valantic marketplace
/plugin marketplace add valantic-CEC-Deutschland-GmbH/claude-code-marketplace
# Browse available plugins
/plugins
# Install individual plugins
/plugin install valantic-brand-guidelines@valantic-claude-code-marketplace
/plugin install valantic-documents@valantic-claude-code-marketplace
/plugin install valantic-dev-workflow@valantic-claude-code-marketplace
/plugin install valantic-coding-standards@valantic-claude-code-marketplace
/plugin install valantic-project-setup@valantic-claude-code-marketplace
/plugin install valantic-ai-permission-evaluator@valantic-claude-code-marketplace
/plugin install valantic-fast-tools@valantic-claude-code-marketplace
```
## Available Plugins
| Plugin | Type | Description |
|--------|------|-------------|
| `valantic-brand-guidelines` | Skill | Liquid Brand Design system (Routes A/B/C, colors, typography) |
| `valantic-documents` | Skill | Branded PPTX/PDF/DOCX generation with Valantic templates |
| `valantic-dev-workflow` | Commands + Hooks | Deployment, review, onboarding commands + permission hooks |
| `valantic-coding-standards` | Skill + Hooks | Enforce company coding conventions automatically |
| `valantic-project-setup` | Skill + Commands | Bootstrap new projects with Valantic templates (PHP, React, Spring) |
| `valantic-ai-permission-evaluator` | Hooks | LLM-powered tool safety evaluation using GPT-4.1-nano |
| `valantic-fast-tools` | Hooks + Agents | Force all agents to use fast CLI tools (rg, fd, bat) for faster context building |
## Plugin Details
### valantic-brand-guidelines
Applies Valantic's official **Liquid Brand Design** system. Includes:
- Visual Routes A (Restrained), B (Standard), C (Dynamic)
- Official color palette (Coral `#FF5757`, Purple Heart `#4C26B7`, Peach `#FFCCAA`)
- Typography system (Calibre/Segoe UI)
- CSS variables and design tokens
### valantic-documents
Generate branded documents:
- **PPTX**: Presentations with Valantic slide layouts and styling
- **PDF**: Reports and whitepapers with brand colors and typography
- **DOCX**: Business documents with proper formatting
### valantic-dev-workflow
Development workflow commands:
- `/deploy` — Guided deployment with environment checks and rollback support
- `/review` — Structured code review against Valantic standards
- `/onboard` — New developer onboarding checklist
Includes a permission evaluator hook that enforces safe tool usage policies.
### valantic-coding-standards
Automatic enforcement of Valantic coding conventions:
- PHP: PSR-12, strict types, Spryker/Symfony patterns
- TypeScript/React: functional components, strict mode, naming conventions
- Java/Spring: standard patterns, proper annotations
- General: error handling, logging, security practices
Pre-tool-use hook checks edits against standards.
### valantic-project-setup
Bootstrap new projects:
- `/new-project` — Interactive project scaffolding
- PHP (Spryker/Symfony) template
- React (Next.js/Vite) template
- Spring Boot (Kotlin/Java) template
### valantic-ai-permission-evaluator
LLM-powered pre-tool-use hook that evaluates **every** Claude Code tool call for safety using OpenAI's GPT-4.1-nano model. Unlike the regex-based evaluator in `valantic-dev-workflow`, this uses an LLM to contextually assess whether a tool operation is safe.
**Prerequisites:**
- Node.js and npm installed
- An OpenAI API key set as `OPENAI_API_KEY` environment variable
**Setup:** Dependencies are installed automatically on first session start via a `SessionStart` hook. No manual `npm install` required.
**How it works:**
- Internal tools (TaskUpdate, TaskCreate, etc.) are auto-approved as always safe
- All other tool calls are sent to GPT-4.1-nano for real-time safety evaluation
- Safe operations are auto-approved; flagged operations prompt the user for confirmation
- On evaluation failure, falls back to asking the user (never silently allows)
**Comparison with regex-based evaluator:**
| | Regex (`valantic-dev-workflow`) | AI (`valantic-ai-permission-evaluator`) |
|---|---|---|
| Scope | Bash commands only | All tool calls |
| Approach | Pattern matching | LLM contextual evaluation |
| Dependencies | Python stdlib only | Node.js + `openai` npm package |
| External API | None | OpenAI API (`OPENAI_API_KEY` required) |
| Latency | ~instant | ~200-500ms per evaluation |
### valantic-fast-tools
Forces every Claude Code agent (including the built-in exploration agents) to use modern, fast CLI tools instead of `grep`/`find`/`cat` - searches that build agent context run 5-50x faster with ripgrep alone. A `PreToolUse` hook blocks slow commands with a corrective message so the agent retries with the fast tool, and three CLAUDE.md-aware exploration agents (`code-explorer`, `code-architect`, `code-reviewer`) are registered automatically.
**System dependencies (install these or the hook stays passive):**
```bash
# Arch
sudo pacman -S ripgrep fd bat tree jq
# Debian / Ubuntu (symlink fdfind to fd)
sudo apt install ripgrep fd-find bat tree jq
# macOS
brew install ripgrep fd bat tree jq
```
The hook is binary-aware: each rule only activates when the fast alternative is actually installed, and `jq` is required for the hook itself. Two optional one-line settings (`USE_BUILTIN_RIPGREP=0`, deny built-in `Explore`/`Plan` agents) unlock the full effect - see the [plugin README](https://github.com/valantic-cec-deutschland-gmbh/claude-code-marketplace/blob/HEAD/plugins/valantic-fast-tools/README.md) for what is automated vs. manual.
## GitHub Agents
Reusable GitHub Actions workflows powered by Claude Code CLI that run autonomously in CI. This collection is centralized here so every consuming repository only needs a thin caller workflow.
See **[github-agents.md](https://github.com/valantic-cec-deutschland-gmbh/claude-code-marketplace/blob/HEAD/github-agents.md)** for the full catalog, setup instructions, and design rationale.
## TweakCC UI Configuration
This repository includes a [`.tweakcc/config.json`](https://github.com/valantic-cec-deutschland-gmbh/claude-code-marketplace/blob/HEAD/.tweakcc/config.json) that customizes the Claude Code terminal UI. It is managed by [TweakCC](https://github.com/Piebald-AI/tweakcc), a tool for theming and personalizing the Claude Code CLI experience.
**What's configured:**
- **8 color themes** — Dark, Light, ANSI-only, Colorblind-friendly, Monochrome, and Sweet
- **Custom thinking verbs** — Replaces the default spinner text with personality (hmm, oof, yeet, segfault, ...)
- **Braille spinner animation** — Progressive dot-fill pattern with reverse mirror
- **Styled user messages** — Custom borders, colors, and formatting
- **Misc tweaks** — Expanded thinking blocks, conversation titles, swarm mode, session memory, and more
**Install TweakCC:**
```bash
npm install -g tweakcc
```
After installation, TweakCC picks up the `.tweakcc/config.json` from the repo root and applies the configured themes and settings to your Claude Code session. See the [TweakCC documentation](https://github.com/Piebald-AI/tweakcc) for all available configuration options.
## Security
- **No secrets**: API keys, tokens, and passwords must stay in local environment variables
- **Private repo**: Developers need GitHub access via SSH or HTTPS
- **Hook scripts**: Use Python standard library only (no pip dependencies)
- **MCP configs**: Use `${ENV_VAR}` patterns for credentials
## Contributing
See [CONTRIBUTING.md](https://github.com/valantic-cec-deutschland-gmbh/claude-code-marketplace/blob/HEAD/CONTRIBUTING.md) for guidelines on adding or updating plugins.