Agent skill
angreal-tool-descriptions
This skill should be used when the user asks to "write a ToolDescription", "add AI guidance to task", "document task for AI", "set risk level", "write tool description prose", "guide AI agents", or needs guidance on angreal.ToolDescription, risk_level, writing effective descriptions for AI agent consumption, or making tasks AI-friendly.
Install this agent skill to your Project
npx add-skill https://github.com/angreal/angreal/tree/main/plugin/skills/angreal-tool-descriptions
SKILL.md
Angreal ToolDescriptions
Write effective ToolDescription prose to guide AI agents using your tasks.
Why ToolDescriptions Matter
When AI agents discover tasks via angreal tree --long, they see:
- Command name and arguments
- Your ToolDescription
The ToolDescription is the primary guidance for AI agents deciding whether and how to use your task. Think of it as a mini-prompt that teaches agents when and how to use your tool.
Basic Usage
import angreal
@angreal.command(
name="deploy",
about="Deploy to environment",
tool=angreal.ToolDescription(
"""
Deploy the application to a specified environment.
## When to use
- After successful build and tests pass
- When user explicitly requests deployment
## When NOT to use
- Directly from feature branches
- Without running tests first
## Examples
```
angreal deploy --env staging
angreal deploy --env production --version v1.2.3
```
""",
risk_level="destructive"
)
)
def deploy(env, version=None):
pass
ToolDescription Constructor
angreal.ToolDescription(
description, # Prose description (required)
risk_level="safe" # "safe", "read_only", or "destructive"
)
Risk Levels
| Level | Meaning | Use When |
|---|---|---|
safe |
No destructive effects | Default. Build, test, lint tasks |
read_only |
Only reads/reports | Status checks, info gathering |
destructive |
May modify or delete | Deploy, clean, database migrations |
Structuring Descriptions
Use consistent markdown sections:
tool=angreal.ToolDescription(
"""
One-line summary of what the tool does.
## When to use
- Scenario 1
- Scenario 2
## When NOT to use
- Anti-pattern 1
- Anti-pattern 2
## Examples
Concrete invocation examples with real arguments
## Preconditions
What must be true before running
## Output
What to expect from the tool
""",
risk_level="safe"
)
Writing Effective Descriptions
Be Specific About Context
Bad:
tool=angreal.ToolDescription("Runs tests")
Good:
tool=angreal.ToolDescription(
"""
Run the complete test suite including unit and integration tests.
## When to use
- Before committing changes
- After pulling changes to verify environment
- As part of CI/CD validation
## Output
Returns exit code 0 if all tests pass, non-zero otherwise.
"""
)
Include Concrete Examples
tool=angreal.ToolDescription(
"""
Build documentation from source.
## Examples
```
# Build to default output
angreal docs build
# Build with specific output path
angreal docs build --output ./site
# Build in watch mode
angreal docs build --watch
```
"""
)
Document Failure Modes
tool=angreal.ToolDescription(
"""
Install project dependencies.
## Common Failures
- **Network error**: Check internet connectivity
- **Permission denied**: May need sudo or virtual environment
- **Version conflict**: Check requirements.txt
## Recovery
If installation fails:
1. Clear cache: `angreal dev clean-cache`
2. Retry installation
"""
)
Describe Relationships
tool=angreal.ToolDescription(
"""
Run unit tests only (fast).
## Related Tasks
- `test.integration` - Integration tests (slower)
- `test.all` - Complete test suite
- `lint.check` - Check style (run before tests)
## Typical Workflow
1. `angreal lint check`
2. `angreal test unit` - Fast feedback
3. `angreal test all` - Full validation
"""
)
Examples by Task Type
Build Task
tool=angreal.ToolDescription(
"""
Build the project for release distribution.
## When to use
- Creating a release build
- Before running deployment tasks
## Preconditions
- Dependencies installed (`angreal dev check-deps`)
- Source compiles without errors
## Output
- Artifacts written to `dist/`
- Returns 0 on success
""",
risk_level="safe"
)
Database Migration
tool=angreal.ToolDescription(
"""
Apply pending database migrations.
## When to use
- After pulling changes with new migrations
- During deployment to update schema
## When NOT to use
- On production without backup
- Without reviewing migration contents
## Recovery
If migration fails:
1. Check migration logs
2. Run `angreal db rollback`
3. Fix and retry
""",
risk_level="destructive"
)
Status Check
tool=angreal.ToolDescription(
"""
Check project status and health.
## When to use
- Starting work to understand state
- Debugging to gather context
- Verifying environment setup
## Output
Reports on git branch, dependencies, build state, test summary.
""",
risk_level="read_only"
)
Best Practices
Do
- Write from the agent's perspective
- Include specific, actionable guidance
- Use markdown formatting for structure
- Document preconditions and postconditions
- Show example invocations with realistic arguments
- Explain error scenarios and recovery
Don't
- Write generic descriptions
- Assume the agent knows project context
- Leave out critical preconditions
- Skip risk_level for destructive operations
- Write walls of text without structure
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
angreal-arguments
This skill should be used when the user asks to "add arguments to a task", "use @angreal.argument", "add flags to command", "make argument required", "add optional parameter", "use python_type", "handle multiple values", or needs guidance on the @argument decorator, argument types, flags, default values, or CLI argument handling in angreal tasks.
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", or needs guidance on creating templates that others can consume via `angreal init`, template configuration, Tera syntax, or publishing templates.
angreal-patterns
This skill should be used when the user asks to "test angreal tasks", "mock angreal", "document tasks", "angreal best practices", "error handling in tasks", "subprocess patterns", "dry run mode", "verbose mode", or needs guidance on testing patterns, development workflows, documentation strategies, or common implementation patterns for angreal tasks.
angreal-integrations
This skill should be used when the user asks to "use Git in a task", "manage virtual environments", "use Docker Compose", "clone a repository", "create a venv", "run docker-compose", "use angreal.integrations", "render a template", "scaffold files", "generate files from template", "use render_template", "use render_directory", "use Flox", "flox environment", "cross-language environment", "flox services", "@flox_required", or needs guidance on the built-in Git, VirtualEnv, Docker, Flox, or Tera templating integrations available in angreal tasks.
angreal-init
This skill should be used when the user asks to "create an angreal project", "initialize angreal", "set up angreal", "add angreal to project", "start new angreal project", "create .angreal directory", or needs guidance on setting up angreal in a new or existing project, project templates, or initial task file structure.
angreal-authoring
This skill should be used when the user asks to "create an angreal task", "write a task file", "add a command to angreal", "make a new task", "organize tasks with groups", "use @angreal.command", "use command_group", or needs guidance on task file structure, the @command decorator, command groups, naming conventions, or task organization within an existing angreal project.
Didn't find tool you were looking for?