explain

Deep explanation of complex code, files, or concepts. Routes to expert agents, uses structural search, generates mermaid diagrams. Triggers on: explain, deep dive, how does X work, architecture, data flow.

2.14x

Quality

—

Does it follow best practices?

Impact

75%

2.14x

Average score across 3 eval scenarios

Securityby

Risky

Do not use without reviewing

Quality

Content

65%

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

Highly actionable with concrete commands and clear routing tables, but the body is long and teaches concepts Claude already knows, lacks validation checkpoints, and keeps everything inline rather than splitting reference material into separate files.

Suggestions

Move the full markdown output template and mermaid diagram syntax examples into a reference file (e.g. references/explanation-template.md), keeping only a brief pointer in SKILL.md.

Trim explanatory prose around concepts Claude already knows (mermaid syntax, what depth/focus modes mean) to improve token efficiency.

Add an explicit verification step (e.g. confirm the expert agent's output covers the requested depth/focus before presenting it) to give the workflow a clear checkpoint.

Dimension	Reasoning	Score
Conciseness	The body is mostly actionable, but the "Generate Explanation" section teaches mermaid flowchart/sequence/class syntax and a full output template — concepts Claude already knows — so it could be tightened rather than fully lean.	2 / 3
Actionability	Provides concrete, executable commands (ast-grep, rg, fd, tokei) with explicit fallbacks plus specific routing, depth, and focus tables — copy-paste ready guidance.	3 / 3
Workflow Clarity	The five steps are clearly sequenced with an architecture diagram, but there are no explicit validation or checkpoint steps, which the score-3 anchor requires even for a read-only workflow.	2 / 3
Progressive Disclosure	The skill is monolithic with no bundle files, and the full output template and mermaid examples are inline content that could be split into reference files; sections are well-organized but the body far exceeds 50 lines.	2 / 3
	Total	9 / 12 Passed

Description

92%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description with concrete capabilities, third-person voice, and an explicit trigger clause. Its only weakness is that some trigger terms ("explain", "architecture") are broad enough to risk overlap with sibling skills.

Suggestions

Tighten the broad trigger terms (e.g. "explain" / "architecture") with more distinctive phrasing like "explain how a specific file or function works" to reduce overlap with general analysis skills.

Consider naming a couple of expert agents in the description to sharpen the distinctiveness of the routing behavior.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ("Routes to expert agents, uses structural search, generates mermaid diagrams") rather than vague language, matching the score-3 anchor.	3 / 3
Completeness	Explicitly states what it does and includes an explicit "Triggers on:" clause answering when to use it, satisfying both halves required for a 3.	3 / 3
Trigger Term Quality	"Triggers on: explain, deep dive, how does X work, architecture, data flow" covers natural phrases a user would actually say, not just technical jargon.	3 / 3
Distinctiveness Conflict Risk	The niche (deep code explanation with expert-agent routing) is reasonably clear, but "explain" and "architecture" are broad terms that could overlap with other analysis skills, so it does not fully reach the unlikely-to-conflict bar of 3.	2 / 3
	Total	11 / 12 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: NeverSight/skills_feed
Commit: 26d37ce

Reviewed: 4 days 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.