explain

Explains the intent behind source code by finding original session transcripts. Use explain with a function, file, or line of code to understand why it exists.

Quality

85%

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

Quality

Content

100%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.

An exemplary short, single-purpose skill body: concrete commands, explicit per-step validation with error-recovery messages, and tight organization with no padding. It fully meets the simple-skill exceptions for workflow clarity and progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The body is lean: it states what the skill works with, the required response header, and a 3-step process with no padding or explanation of concepts Claude already knows. Not a 4 because there is no over-explanation to trim; every token earns its place.	5 / 5
Actionability	Provides concrete, executable commands ('entire version', 'entire explain --no-pager --commit COMMIT_SHA') plus exact user-facing error strings for each failure mode. Not a 4 because the core commands are copy-paste ready and the common cases are covered; the git-blame delegation to a subagent is an architectural choice, not a gap.	5 / 5
Workflow Clarity	A clearly numbered 3-step sequence where each step has an explicit validation checkpoint and a 'stop and tell the user' feedback path on failure. Not a 4 because validation and error recovery are fully explicit at every step rather than implicit.	5 / 5
Progressive Disclosure	A simple, under-50-line skill with no need for external references, organized into clear sections (intro, Response Format, Process) — meeting the simple-skill exception for a top score. Not a 4 because nothing is misplaced and no nested references exist.	5 / 5
	Total	20 / 20 Passed

Description

70%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.

A clear, concise description that states both what the skill does and when to use it, with natural trigger phrasing. It is held back from the top band by limited action coverage and a 'when' clause framed as invocation arguments rather than concrete trigger scenarios.

Suggestions

Expand the action list beyond 'explains intent' and 'finds transcripts' (e.g., 'traces a function, file, or line back to the commit and session that created it') to lift specificity.

Reframe the 'when' as an explicit trigger clause, e.g. 'Use when the user asks why code exists, why a line was added, or what intent drove a file's creation'.

Add a synonym or two (e.g., 'why was this added', 'origin of this code') to broaden natural trigger coverage.

Dimension	Reasoning	Score
Specificity	Names the domain (source-code intent) and two concrete actions ('Explains the intent', 'finding original session transcripts'), but coverage is limited rather than comprehensive. Not a 4 because 'several specific actions' are not listed; not a 2 because the actions are concrete, not generic.	3 / 5
Completeness	Clearly states what it does ('Explains the intent behind source code by finding original session transcripts') and gives explicit trigger guidance ('Use explain with a function, file, or line of code to understand why it exists'). Not a 5 because the 'when' is framed as invocation args rather than concrete trigger scenarios; not a 3 because both what and when are present.	4 / 5
Trigger Term Quality	Includes natural phrases users would say — 'function, file, or line of code' and 'understand why it exists' — giving good keyword coverage. Not a 5 because it lacks synonyms and file-extension variants; not a 3 because the terms go beyond a single generic keyword.	4 / 5
Distinctiveness Conflict Risk	The 'finding original session transcripts' niche is largely distinct with clear triggers, with only minor overlap risk against general code-explanation skills. Not a 5 because 'explain'/'understand why code exists' could collide with broader explanation skills; not a 3 because the transcript-tracing angle is specific.	4 / 5
	Total	15 / 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: SnowingFox/ai-skills
Path: .agents/skills/explain/SKILL.md
Commit: d6882ad

Reviewed: ~15 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.