understand-explain

Use when you need a deep-dive explanation of a specific file, function, or module in the codebase

Quality

71%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

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

Quality

Content

81%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 an executable, well-sequenced workflow with notably strong graph-freshness validation and failure handling, and it largely respects token budget. The main gap is progressive disclosure: the inlined graph schema reference could be split out, and there are no external reference files to signal.

Dimension	Reasoning	Score
Conciseness	The body is largely lean and assumes Claude's knowledge of git and grep, though the inlined 'Graph Structure Reference' and 'How to Read Efficiently' sections add length that could be trimmed slightly.	4 / 5
Actionability	Provides concrete executable commands (UA_DIR resolution, git rev-parse/diff invocations) and specific JSON fields to grep, with only minor gaps where example grep invocations are not fully copy-paste ready.	4 / 5
Workflow Clarity	An explicit 8-step sequence with strong validation checkpoints in step 2 (graph-commit resolution, project-scoped diff inspection, staleness warning) and clear feedback ('Run /understand to refresh') plus graceful failure handling when git metadata is missing.	5 / 5
Progressive Disclosure	Well-organized into clear sections with no nested references, but it is a single self-contained file with an inlined graph schema reference that could arguably live in a separate file; no bundle files are present to navigate.	4 / 5
	Total	17 / 20 Passed

Description

62%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 cleanly states what the skill does and when to use it with a third-person trigger clause, but the 'when' is a single phrase and lacks synonym coverage and file-extension triggers. Specificity is moderate because the only action verb is the abstract 'explanation'.

Suggestions

Add concrete action verbs and synonyms, e.g. 'Provides an in-depth explanation, walkthrough, or breakdown of a specific file, function, or module'.

Broaden the 'Use when' clause with multiple natural triggers: 'Use when the user asks to understand, explain, or walk through a specific file, function, or module'.

Consider naming the artifact type (knowledge graph / codebase) to sharpen distinctiveness from generic explain skills.

Dimension	Reasoning	Score
Specificity	Names the domain ('deep-dive explanation') and three concrete targets ('file, function, or module') but the action itself is a single abstract verb rather than a list of several specific actions.	3 / 5
Completeness	Explicitly answers both what ('deep-dive explanation of a specific file, function, or module') and when ('Use when you need...'); the 'when' is a single clause and could be more specific with multiple trigger phrases.	4 / 5
Trigger Term Quality	Includes the natural phrase 'Use when you need a deep-dive explanation' but lacks common synonyms users say ('understand', 'walk me through', 'how does X work') and any file extensions.	3 / 5
Distinctiveness Conflict Risk	Targets a specific niche (graph-indexed component deep-dives) that is mostly distinct, with only minor overlap risk against a generic 'explain code' 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-explain/SKILL.md
Commit: ba450c4

Reviewed: ~14 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.