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.

Quality

61%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./understand-anything-plugin/skills/understand-domain/SKILL.md

Quality

Content

65%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is well-structured with concrete, executable guidance across six clear phases, but the batch workflow lacks a validation feedback loop and a referenced bundled script is absent from the bundle. These gaps hold workflow clarity and progressive disclosure at mid-level scores.

Suggestions

Add a fix-and-retry feedback loop in Phase 5 (e.g. on validation failure, re-run analysis or fix the offending entries before saving) so the batch operation can exceed workflow_clarity 3.

Provide the missing ./extract-domain-context.py script in a scripts/ bundle directory, or replace the reference with inline guidance, so the Phase 2 command is actually runnable.

Specify the 'standard graph validation pipeline' concretely (schema location, command, or script) rather than relying on an undefined external reference.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean and operational (concrete bash blocks, numbered phases) and assumes Claude's competence; a few justifying asides like the 'cheat sheet' analogy and the issue #133 note could be trimmed but earn their place.	4 / 5
Actionability	Provides concrete, executable bash for worktree detection, plugin-root resolution, and freshness checks, plus a real command ('python ./extract-domain-context.py "$PROJECT_ROOT"'); minor gaps remain in 'Dispatch a subagent' and the vague 'standard graph validation pipeline' reference.	4 / 5
Workflow Clarity	Six phases are clearly sequenced with a preflight freshness check and a validation step, but Phase 5 has no fix-and-retry feedback loop and on validation failure only 'saves what's valid'; for a batch codebase-scanning operation the missing feedback loop caps this at 3.	3 / 5
Progressive Disclosure	Sections are well organized into clear phases and references are one level deep, but the body instructs running a 'preprocessing script bundled with this skill' (./extract-domain-context.py) and reads $PLUGIN_ROOT/agents/domain-analyzer.md, while no scripts/ bundle directory exists, so a key referenced artifact is missing.	3 / 5
	Total	14 / 20 Passed

Description

58%Weight 40%Scale 1-5

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 clearly states what the skill does with concrete actions, but omits any 'when to use' trigger guidance, which limits completeness and natural trigger-term coverage. It is mostly distinct from sibling skills with only minor overlap risk.

Suggestions

Add an explicit 'Use when...' clause naming natural user triggers, e.g. 'Use when the user wants to visualize business domains or flows, or asks for a domain flow graph.'

Include common synonyms or file/artifact terms users might say (e.g. 'business flows', 'process steps', 'domain map') to improve trigger-term coverage.

Clarify the distinction from /understand up front so the two skills do not compete for the same trigger.

Dimension	Reasoning	Score
Specificity	Names the domain ('business domain knowledge from a codebase') and several concrete actions ('extract...', 'generate an interactive domain flow graph', 'lightweight scan', 'derives from an existing /understand knowledge graph'), but the two operational modes are not distinct capabilities, so coverage is good rather than comprehensive.	4 / 5
Completeness	The 'what' is clear (extract domain knowledge and generate a flow graph), but the 'when' is entirely missing with no 'Use when...' clause or equivalent trigger guidance, capping completeness at 3 per the rubric guideline.	3 / 5
Trigger Term Quality	Relevant keywords like 'business domain knowledge', 'codebase', 'domain flow graph', and 'knowledge graph' appear, but the terms lean technical and lack common synonyms or natural user phrasings; no 'Use when...' trigger phrase is given.	3 / 5
Distinctiveness Conflict Risk	The niche (business domain flow graph) is fairly distinct, but explicit references to the sibling '/understand knowledge graph' create minor overlap risk with that closely related skill.	4 / 5
	Total	14 / 20 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: Egonex-AI/Understand-Anything
Path: understand-anything-plugin/skills/understand-domain/SKILL.md
Commit: ba450c4

Reviewed: ~13 hours ago

Table of Contents

Discovery Implementation Validation

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.