D2: Mindset & Procedures (15 points)

Purpose: Provide philosophical framing and step-by-step workflows.

Scoring:

Points Signal
13–15 Clear mindset + detailed procedures + when/when-not guidance
10–12 Has most elements, minor gaps
7–9 Missing a key element
0–6 Generic or absent

Components

  1. Clear Mindset/Philosophy (5 points)
  • Core principle or philosophy
  • Why this approach over alternatives
  • Example: “Trust but verify” (proof-of-work), “Composition over inheritance” (structural-design)
  1. Step-by-Step Procedures (5 points)
  • Numbered workflow
  • Clear entry/exit points
  • Validation steps
  • Example: TDD cycle (Red → Green → Refactor)
  1. When/When-Not Guidance (5 points)
  • Clear activation criteria
  • Explicit non-applicable scenarios
  • Example: “Use for backend APIs, NOT for UI styling”

Example

Strong Mindset + Procedures (15/15):

# Test-Driven Development

## Mindset
Write tests BEFORE implementation. The test defines the contract; implementation fulfils it.

## Workflow
1. Red: Write failing test (verify it fails)
2. Green: Minimum code to pass
3. Refactor: Improve without breaking tests

## When to Apply
✅ New functions, features, bug fixes (reproduce first)
❌ UI styling, configuration, documentation

## When NOT to Apply
- Throwaway prototypes
- Generated code
- Trivial getters/setters

Sub-scorer Breakdown

The D2 scorer runs three sub-scorers independently:

  • Preconditions — “Before you start” or “Requirements” sections that set up entry criteria
  • Postconditions — “After completion” or “Definition of Done” sections that define success
  • Decision points — conditional guidance (“if X then Y, otherwise Z”) embedded in the workflow

All three should be present for a full score.

Academic References

@article{bakal2026knowledge,
  title         = {Knowledge Activation: AI Skills as the Institutional Knowledge Primitive for Agentic Software Development},
  author        = {Bakal},
  year          = {2026},
  journal       = {arXiv preprint arXiv:2603.14805},
  eprint        = {2603.14805},
  archivePrefix = {arXiv},
  url           = {<https://arxiv.org/abs/2603.14805}>
}

@inproceedings{carriero2025pko,
  title         = {Procedural Knowledge Ontology (PKO)},
  author        = {V. A. Carriero and M. Scrocca and I. Baroni and A. Azzini and I. Celino},
  year          = {2025},
  booktitle     = {Proceedings of the European Semantic Web Conference (ESWC 2025)},
  publisher     = {Springer},
  url           = {<https://doi.org/10.1007/978-3-031-94578-6_19>}
}

@article{bi2025realtime,
  title         = {Real-Time Procedural Learning From Experience for AI Agents},
  author        = {Bi and Hu and Nasir},
  year          = {2025},
  journal       = {arXiv preprint arXiv:2511.22074},
  eprint        = {2511.22074},
  archivePrefix = {arXiv},
  url           = {<https://arxiv.org/abs/2511.22074}>
}

@article{bi2026automating,
  title         = {Automating Skill Acquisition through Large-Scale Mining of Agentic Repositories},
  author        = {Bi and Wu and Hao and others},
  year          = {2026},
  journal       = {arXiv preprint arXiv:2603.11808},
  eprint        = {2603.11808},
  archivePrefix = {arXiv},
  url           = {<https://arxiv.org/abs/2603.11808}>
}