angreal-templates
This skill should be used when the user asks to "create an angreal template", "make a project template", "build a reusable template", "share a template", "write angreal.toml", "use Tera templating", "template variables", "conditional templates", "render a template in place", "use an official angreal template", "start a python/rust project with angreal", or needs guidance on creating templates that others can consume via `angreal init`, consuming the official angreal templates, in-place rendering, template configuration, Tera syntax, or publishing templates.
What this skill does
# Creating Angreal Templates
Create reusable project templates that others can consume via `angreal init <template>`.
## What Templates Are For
Templates let you create reusable project scaffolds. Users initialize new projects with:
```bash
angreal init https://github.com/user/my-template
angreal init /path/to/local/template
```
This is different from `angreal-init` (adding angreal to existing projects) - templates create entirely new projects from scratch.
## Official Templates
The angreal team maintains a set of ready-to-use templates in the
[github.com/angreal](https://github.com/angreal) organization. A **bare name**
passed to `angreal init` resolves to `https://github.com/angreal/<name>`, so
these can be used directly:
```bash
angreal init python # Python project template
angreal init rust # Rust project template
```
| Template | `angreal init` | What it scaffolds |
|----------|----------------|-------------------|
| `python` | `angreal init python` | Standard Python project |
| `python-gh` | `angreal init python-gh` | Python project wired for GitHub (Actions CI) |
| `python-gl` | `angreal init python-gl` | Python project wired for GitLab (GitLab CI) |
| `rust` | `angreal init rust` | Rust project: workspace layout, unified versioning, CI/CD, optional Tauri v2 desktop UI |
| `data-science` | `angreal init data-science` | Modern data-science project with epoch-based notebook organization and scientific computing patterns |
| `airflow` | `angreal init airflow` | Apache Airflow project scaffold |
| `airflow-provider` | `angreal init airflow-provider` | Apache Airflow provider package |
This list changes over time — browse [github.com/angreal](https://github.com/angreal)
for the current, authoritative catalog (any non-fork repo containing an
`angreal.toml` is a consumable template).
Resolution order for `angreal init <name>`:
1. A local path, if it exists
2. A cached template in `~/.angrealrc/`, if present
3. The GitHub repo `https://github.com/angreal/<name>`
## Rendering In Place
By default a template's single top-level templated directory (e.g.
`{{ project_name }}/`) becomes a **new** project root inside the current
directory. The `--in-place` / `-i` flag strips that top-level directory and
renders its contents **directly into the current working directory** — useful
for scaffolding into a folder you've already created (such as an existing git
repository or a directory of planning notes):
```bash
mkdir my-project && cd my-project
angreal init python --in-place # contents land in ./, no extra root dir
```
In-place rendering requires the template to have **exactly one** top-level
templated directory (it errors clearly on zero or multiple). Collisions with
existing files reuse `--force` semantics: the command aborts unless `--force`
is passed.
### `angreal init` flags
| Flag | Short | Effect |
|------|-------|--------|
| `--force` | `-f` | Render even if target paths/files already exist (overwrite) |
| `--defaults` | `-d` | Use default values from `angreal.toml` without prompting |
| `--in-place` | `-i` | Strip the template's top-level directory; render into the current directory |
| `--values <FILE>` | | Supply values from a file, bypassing interactive prompts |
## Template Structure
Every angreal template follows this structure:
```
my-template/
├── angreal.toml # Template configuration (required)
├── {{ project_name }}/ # Templated directories
│ ├── src/
│ └── tests/
├── README.md # Templated files
├── static_file.txt # Static files (copied as-is)
└── .angreal/ # Optional: post-init tasks
├── init.py # Post-initialization script
└── task_*.py # Template-specific tasks
```
## Template Configuration (angreal.toml)
The `angreal.toml` file defines template variables at the root level:
```toml
# Variables with defaults - users will be prompted for these
project_name = "my-project"
author_name = "Anonymous"
description = "A new project"
license = "MIT"
use_docker = false
python_version = "3.11"
# Optional: Custom prompts for better UX
[prompt]
project_name = "Enter your project name"
author_name = "Enter your name"
license = "Choose a license (MIT, Apache-2.0, GPL-3.0)"
# Optional: Validation rules
[validation]
project_name.not_empty = true
project_name.length_min = 3
license.allowed_values = ["MIT", "Apache-2.0", "GPL-3.0"]
```
### Variable Types
```toml
# String variables
project_name = "default-name"
author = "Your Name"
# Boolean variables
use_docker = false
include_tests = true
# Numeric variables
port = 8080
# List variables
dependencies = ["requests", "click", "pydantic"]
```
### Custom Prompts ([prompt] section)
Customize what users see when providing values:
```toml
[prompt]
project_name = "Enter your project name (lowercase, no spaces)"
author_email = "Your email address"
use_docker = "Include Docker support? (y/n)"
```
### Validation Rules ([validation] section)
Validate user input with these options:
```toml
[validation]
# Required field
project_name.not_empty = true
# String length
username.length_min = 3
username.length_max = 20
# Numeric range
port.type = "integer"
port.min = 1024
port.max = 65535
# Allowed values
license.allowed_values = ["MIT", "Apache-2.0", "GPL-3.0"]
# Regex pattern
email.regex_match = "^[a-zA-Z0-9._%+-]+@[a-zA-Z0-9.-]+\\.[a-zA-Z]{2,}$"
```
## Tera Templating Engine
Angreal uses [Tera](https://keats.github.io/tera/docs/) (similar to Jinja2) for templating.
### Variable Substitution
```markdown
# {{ project_name }}
{{ description }}
Created by {{ author_name }}
```
### Conditionals
```markdown
# {{ project_name }}
{% if use_docker %}
## Docker
Build and run with Docker:
```bash
docker build -t {{ project_name }} .
docker run {{ project_name }}
```
{% endif %}
{% if include_tests %}
## Testing
```bash
pytest tests/
```
{% endif %}
```
### Loops
```python
# requirements.txt
{% for dep in dependencies %}
{{ dep }}
{% endfor %}
```
### Filters
```markdown
# {{ project_name | title }}
Package: {{ project_name | lower | replace(from=" ", to="-") }}
Class: {{ project_name | title | replace(from=" ", to="") }}
```
Common filters:
- `upper` / `lower` - Change case
- `title` - Title case
- `replace(from="x", to="y")` - Replace text
- `trim` - Remove whitespace
## Templated Names
### Directory Names
```
my-template/
└── {{ project_name }}/
├── {{ project_name }}/
│ └── __init__.py
└── tests/
```
With `project_name = "my-app"` creates:
```
my-app/
├── my-app/
│ └── __init__.py
└── tests/
```
### File Names
```
{{ project_name }}.py
test_{{ project_name }}.py
```
## Escaping Template Syntax
Use `{% raw %}` to preserve template syntax in output files:
```
{% raw %}
{
"name": "{{ package_name }}",
"scripts": {
"test": "jest"
}
}
{% endraw %}
```
This outputs the literal `{{ package_name }}` without substitution. Use for:
- JSON files with curly braces
- Jinja/Tera templates you want to include in generated projects
- Documentation showing template examples
## Conditional File/Directory Creation
Control which files and directories are created based on template variables.
### Conditional File Content (Empty = No File)
Create files that are empty (and thus effectively skipped) when conditions aren't met:
```
{# Dockerfile - only has content if use_docker is true #}
{% if use_docker %}
FROM python:{{ python_version }}
WORKDIR /app
COPY . .
RUN pip install -e .
CMD ["python", "-m", "{{ project_name }}"]
{% endif %}
```
### Conditional Directories via Post-Init Script
Use `.angreal/init.py` to create or remove directories based on variables:
```python
# .angreal/init.py
import shutil
import os
import angreal
def init():
context = angreal.get_context()
project = context.get('project_name', 'project')
# Conditionally create directories
if context.get('include_docs', False):
os.makedirs(f"{projecRelated in Image & Video
watch
IncludedWatch a video (URL or local path). Downloads with yt-dlp, extracts auto-scaled frames with ffmpeg, pulls the transcript from captions (or Whisper API fallback), and hands the result to Claude so it can answer questions about what's in the video.
physical-ai-defect-image-generation
IncludedUse when the user wants to orchestrate defect image generation, run associated setup, or handle outputs on OSMO. The Day 0 path handles cold-start with USD-to-ROI, image-edit augmentation, and AnomalyGen to create initial PCBA datasets. The Day 1 path performs inference and labeling on real images. This skill helps with first-time asset setup, creation of finetuning checkpoints, and configuring deployment. Trigger keywords: defect image generation, dig workflow, dig pipeline, defect image detection workflow, aoi pipeline, aoi anomalygen, usd2roi anomalygen, day 0 pcba, day 1 pcba, day 1 real-photo alignment, day 1 manual roi, metal surface anomaly, glass defect, anomalygen finetune, setup_pcb, setup_metal, setup_glass, setup_pretrained, dig setup, dig datasets, dig pretrained checkpoint, dig image-edit endpoint.
accelint-react-best-practices
IncludedReact performance optimization and best practices. ALWAYS use this skill when working with any React code - writing components, hooks, JSX; refactoring; optimizing re-renders, memoization, state management; reviewing for performance; fixing hydration mismatches; debugging infinite re-renders, stale closures, input focus loss, animations restarting; preventing remounting; implementing transitions, lazy initialization, effect dependencies. Even simple React tasks benefit from these patterns. Covers React 19+ (useEffectEvent, Activity, ref props). Triggers - useEffect, useState, useMemo, useCallback, memo, inline components, nested components, components inside components, re-render, performance, hydration, SSR, Next.js, useDeferredValue, combined hooks.
elevenlabs-agents
IncludedBuild conversational AI voice agents with ElevenLabs Platform using React, JavaScript, React Native, or Swift SDKs. Configure agents, tools (client/server/MCP), RAG knowledge bases, multi-voice, and Scribe real-time STT. Use when: building voice chat interfaces, implementing AI phone agents with Twilio, configuring agent workflows or tools, adding RAG knowledge bases, testing with CLI "agents as code", or troubleshooting deprecated @11labs packages, Android audio cutoff, CSP violations, dynamic variables, or WebRTC config. Keywords: ElevenLabs Agents, ElevenLabs voice agents, AI voice agents, conversational AI, @elevenlabs/react, @elevenlabs/client, @elevenlabs/react-native, @elevenlabs/elevenlabs-js, @elevenlabs/agents-cli, elevenlabs SDK, voice AI, TTS, text-to-speech, ASR, speech recognition, turn-taking model, WebRTC voice, WebSocket voice, ElevenLabs conversation, agent system prompt, agent tools, agent knowledge base, RAG voice agents, multi-voice agents, pronunciation dictionary, voice speed control, elevenlabs scribe, @11labs deprecated, Android audio cutoff, CSP violation elevenlabs, dynamic variables elevenlabs, case-sensitive tool names, webhook authentication
humanizer
IncludedHumanize AI-generated text by detecting and removing patterns typical of LLM output. Rewrites text to sound natural, specific, and human. Uses 28 pattern detectors, 560+ AI vocabulary terms across 3 tiers, and statistical analysis (burstiness, type-token ratio, readability) for comprehensive detection. Use when asked to humanize text, de-AI writing, make content sound more natural/human, review writing for AI patterns, score text for AI detection, or improve AI-generated drafts. Covers content, language, style, communication, and filler categories.
generating-mermaid-diagrams
IncludedSalesforce architecture diagrams using Mermaid with ASCII fallback. Use this skill when generating text-based diagrams for Salesforce architecture, OAuth flows, ERDs, integration sequences, or Agentforce structure. TRIGGER when: user says "diagram", "visualize", "ERD", or asks for sequence diagrams, flowcharts, class diagrams, or architecture visualizations in Mermaid. DO NOT TRIGGER when: user wants PNG/SVG image output (use generating-visual-diagrams), or asks about non-Salesforce systems.