setup-task
OfficialGenerate and validate causal task packages.
Education & Research#experimentation#counterfactuals#mechanistic interpretability#task setup#causal abstraction#token alignment
Authorgoodfire-ai
Version1.0.0
Installs0
System Documentation
What problem does it solve?
The setup-task Skill turns a task specification into a complete, convention-compliant causalab/tasks/<task_name>/ package so you can immediately run causal abstraction experiments instead of wiring files by hand.
Core Features & Use Cases
- Creates a full task package from an MD spec: Generates
config.py,templates.py, causal model code, counterfactual generators, token position logic, checker, metrics, and a summary notebook. - Guides spec ingestion and clarification: Supports existing specs (MD), or interactive/PDF-driven spec creation with approval checkpoints.
- Performs model validation wiring checks: Loads the specified model, validates end-to-end behavior, and verifies token alignment plus spacing-handling.
Quick Start
Run the skill by providing the path to your markdown task specification, for example: Invoke /setup-task path/to/task_spec.md and then confirm the extracted fields when prompted.
Dependency Matrix
Required Modules
None requiredComponents
Standard package💻 Claude Code Installation
Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.
Please help me install this Skill: Name: setup-task Download link: https://github.com/goodfire-ai/causalab/archive/main.zip#setup-task Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.