Verified project case study · Capability taxonomy
Cognitive Core Skills
A machine-readable taxonomy for reasoning, memory, planning, action, verification, learning, and governance capabilities.
Contribution
What ELI Labz contributed
ELI Labz owns and maintains the repository. Public history also attributes the large initial content commit to ai-in-pm, so this case study describes repository stewardship rather than sole authorship.
Context
The operating problem
Teams evaluating Intelligent Machine Systems need a shared language for capabilities and safeguards. This repository organizes those concepts into structured data, generated skill cards, schemas, rubrics, and tests.
Technical approach
How the system was shaped
- Represented the taxonomy in synchronized JSON and YAML with formal validation schemas.
- Generated individual markdown skill cards from the machine-readable source.
- Added rubric fixtures and Python tests to check taxonomy integrity and evaluation data.
- Established CI, contribution templates, release checks, and documentation paths for maintainable stewardship.
Demonstrated outcomes
What can be inspected
- The repository documents 159 generated skill cards across 13 domains in taxonomy version 1.0.0.
- Machine-readable artifacts, schemas, benchmark fixtures, and generated documentation are available together.
- The repository includes a repeatable local validation command and CI workflow.
Public sources
Claim boundaries
What this case study does not claim
- • Repository ownership and maintenance do not establish sole authorship of every taxonomy artifact.
- • Counts reflect the repository's documented version and may change as the taxonomy evolves.
Technology
Apply this engineering approach to your deployment.
Describe the workflow, constraints, and target outcome to generate an initial Forward Deployed Engineer engagement brief.
Scope an engagement