digitalmodel-code-explorer
Fast orientation guide for the digitalmodel codebase, with module lookup, source-to-test mapping, and targeted inspection patterns to avoid repeated bulk-reading of digitalmodel/src and tests.
Best use case
digitalmodel-code-explorer is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Fast orientation guide for the digitalmodel codebase, with module lookup, source-to-test mapping, and targeted inspection patterns to avoid repeated bulk-reading of digitalmodel/src and tests.
Teams using digitalmodel-code-explorer should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/code-explorer/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How digitalmodel-code-explorer Compares
| Feature / Agent | digitalmodel-code-explorer | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Fast orientation guide for the digitalmodel codebase, with module lookup, source-to-test mapping, and targeted inspection patterns to avoid repeated bulk-reading of digitalmodel/src and tests.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# Digitalmodel Code Explorer ## Purpose Use this skill to navigate `digitalmodel/src/digitalmodel/` and its tests without bulk-reading large numbers of files. It is intended to reduce repeated manual source exploration by giving a fast module map and lookup workflow. ## Core Areas in digitalmodel/src/digitalmodel/ Examples of major areas present on this machine include: - `fatigue/` - `cathodic_protection/` - `structural/` - `subsea/` - `reservoir/` - `signal_processing/` - `well/` - `workflows/` - top-level helpers like `engine.py`, `units.py`, `__main__.py` ## Recommended Exploration Pattern ### 1. Find the relevant package first ```bash find digitalmodel/src/digitalmodel -maxdepth 2 -type f | head -50 ``` ### 2. Narrow by topic before reading files Examples: ```bash rg -n "rainflow|sn curve|fatigue" digitalmodel/src/digitalmodel/fatigue rg -n "orcawave|diffraction|rao" digitalmodel/src/digitalmodel rg -n "cathodic|anode|iccp" digitalmodel/src/digitalmodel/cathodic_protection ``` ### 3. Read only the most relevant files Prefer: - package `__init__.py` - API-facing modules - the exact function/class implementation you matched - the corresponding tests ## Source -> Test Mapping Pattern Before editing a source file, look for mirrored or neighboring tests. Examples: ```bash find digitalmodel/tests -type f | rg "fatigue|cathodic|orcawave|orcaflex" ``` Heuristic mapping: - `digitalmodel/src/digitalmodel/fatigue/<module>.py` -> search under `digitalmodel/tests/` for `<module>` or the package name - package-level behavior -> check `digitalmodel/tests/<package>/` and `digitalmodel/tests/unit/` ## Useful Fast Questions This Skill Helps Answer - Which package owns a domain concept? - Where is the public API versus a helper implementation? - What tests exist for a module before changing it? - Which neighboring files should be compared for similar patterns? ## Practical Workflow 1. identify the domain/package 2. grep for the concrete symbol or topic 3. read the smallest relevant set of files 4. map to tests before implementation 5. only then expand outward if architecture context is still missing ## Common Pitfalls - reading an entire package tree before asking a narrower question - editing a module without finding its tests first - assuming domain ownership without checking sibling packages - mixing package discovery and implementation in the same pass ## Good Companion Commands ```bash find digitalmodel/src/digitalmodel -maxdepth 2 -type f | sort find digitalmodel/tests -type f | sort | head -100 rg -n "class |def " digitalmodel/src/digitalmodel/<package> ``` ## Notes This is an orientation skill, not a replacement for reading source. Its goal is to reduce repeated bulk-read behavior by making the first pass targeted and test-aware.
Related Skills
digitalmodel-worktree-test-execution-with-shared-venv
Run digitalmodel tests from isolated worktrees without uv editable-dependency failures by using the main repo's existing virtualenv and PYTHONPATH.
digitalmodel-orcawave-orcaflex-proof-workflows
Class-level digitalmodel OrcaWave/OrcaFlex readiness, semantic-proof, fixture-proof, and closeout workflows.
digitalmodel-orcawave-orcaflex-workflow
Current-state workflow for navigating and extending digitalmodel OrcaWave/OrcaFlex capabilities across code, tests, issues, queue tooling, and licensed-machine boundaries.
test-oversized-skill
A test fixture skill that exceeds 200 lines with multiple H2/H3 sections for split testing.
interactive-report-generator
Generate interactive HTML reports with Plotly visualizations from data analysis results. Supports dashboards, charts, and professional styling.
data-validation-reporter
Generate interactive validation reports with quality scoring, missing data analysis, and type checking. Combines Pandas validation, Plotly visualization, and YAML configuration for comprehensive data quality reporting.
agent-os-framework
Generate standardized .agent-os directory structure with product documentation, mission, tech-stack, roadmap, and decision records. Enables AI-native workflows.
OrcaFlex Specialist Skill
```yaml
repo-ecosystem-hygiene
Interpret the daily read-only repo ecosystem hygiene audit and route remediation through approved workflows.
domain-knowledge-sweep
Systematic multi-source research of an engineering domain. Spawns parent issue → 6 research subissues (Standards, Academic, Industry, LinkedIn-marketing, Code-audit, Synthesis) → gap implementation subissues. Replaces LinkedIn-only extraction with defensible comprehensive sourcing.
subagent-write-verification
Independently verify subagent-claimed file writes with filesystem and git checks before treating the artifact as real, before committing it, and before referencing the path in downstream prompts.
git-operation-serialization-preflight
Before any commit, stash, merge, reset, rebase, or checkout in a multi-agent or shared-checkout environment, run a bounded preflight to detect active git writers and stale index/config locks, then serialize the mutating step under a single-writer guarantee.