understand-domain
Extract business domain knowledge from a codebase and generate an interactive domain flow graph. Works standalone (lightweight scan) or derives from an existing /understand knowledge graph.
58
67%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./understand-anything-plugin/skills/understand-domain/SKILL.mdQuality
Discovery
57%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
The description communicates a clear and distinctive purpose—extracting domain knowledge and generating flow graphs—but falls short on completeness by lacking an explicit 'Use when...' clause. Trigger terms are somewhat specialized and could benefit from more natural user-facing language variations.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user wants to visualize business logic, understand domain flows, or map out how a codebase's business concepts relate to each other.'
Include more natural trigger terms users might say, such as 'business logic', 'domain model', 'code architecture', 'flow diagram', or 'visualize codebase structure'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain ('business domain knowledge', 'interactive domain flow graph') and mentions two modes ('standalone lightweight scan' or 'derives from existing /understand knowledge graph'), but doesn't list multiple concrete actions beyond 'extract' and 'generate'. | 2 / 3 |
Completeness | Clearly answers 'what' (extract domain knowledge and generate an interactive domain flow graph) but lacks an explicit 'Use when...' clause or equivalent trigger guidance, so the 'when' is only implied. | 2 / 3 |
Trigger Term Quality | Includes some relevant terms like 'domain', 'codebase', 'knowledge graph', 'domain flow graph', and '/understand', but misses common user-facing variations a user might naturally say (e.g., 'business logic', 'architecture diagram', 'code flow', 'domain model'). The term 'domain flow graph' is somewhat specialized. | 2 / 3 |
Distinctiveness Conflict Risk | The combination of 'business domain knowledge', 'domain flow graph', and the reference to '/understand knowledge graph' creates a clear niche that is unlikely to conflict with other skills. It's quite specific in its purpose. | 3 / 3 |
Total | 9 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured, actionable skill with clear multi-phase workflow and good branching logic. Its main weakness is verbosity — the plugin root resolution and worktree detection sections are very long inline bash blocks that inflate the token cost significantly. Some explanatory text (e.g., why preprocessing exists) could be trimmed since Claude doesn't need the rationale.
Suggestions
Extract the lengthy plugin root resolution and worktree detection bash blocks into a shared helper script, referencing it from SKILL.md to reduce inline verbosity.
Remove the explanatory paragraph in Phase 2 ('The preprocessing script does NOT produce a domain graph — it produces raw material...Think of it as a cheat sheet') — Claude doesn't need the rationale, just the instructions.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is moderately efficient but includes verbose sections, particularly the plugin root resolution block which is extremely long with many fallback paths and error messages. The worktree detection explanation is thorough but could be more concise. Some sections like Phase 2's explanation of why preprocessing exists ('Think of it as a cheat sheet...') are unnecessary for Claude. | 2 / 3 |
Actionability | The skill provides fully executable bash code for worktree detection and plugin root resolution, specific file paths for inputs/outputs, concrete commands like `python ./extract-domain-context.py "$PROJECT_ROOT"`, and clear references to external agent prompts and scripts. Each phase has specific, concrete actions. | 3 / 3 |
Workflow Clarity | The multi-step workflow is clearly sequenced across 7 phases (0-6) with explicit branching logic (Phase 1 decides between Path 1 and Path 2), validation in Phase 5 with error tolerance behavior specified, and cleanup steps. The conditional flow between phases is well-defined with clear decision points. | 3 / 3 |
Progressive Disclosure | The skill references external files (domain-analyzer agent prompt, extract-domain-context.py, /understand-dashboard) appropriately, but the main SKILL.md itself is quite long with the inline bash blocks for plugin resolution and worktree detection. The plugin root resolution code could potentially be extracted to a helper script. No bundle files were provided to verify referenced paths. | 2 / 3 |
Total | 10 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- Lum1104/Understand-Anything
- Commit
26edf61
- Reviewed
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.