explain

Explains features, terms, and concepts from a codebase. Use whenever the user asks to explain, describe, or understand something ("explain X", "what is X", "how does X work"). Also use when starting an implementation, refactor, or test task — invoke as `depth:pamphlet <concept>` before writing code, `depth:novella <concept>` before designing an approach, or `depth:novel <concept>` before a deep refactor. Agent-triggered mode (depth: prefix) skips the interview and returns a structured WHAT/WHERE/HOW/CONNECTS TO block instead of a narrative.

Quality

78%

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 ./skills/explain/SKILL.md

Quality

Content

71%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 highly actionable and well-sequenced with concrete templates and clear branching between user- and agent-triggered modes. Its weaknesses are redundancy between the top-level STOP block and the later Agent-Triggered Mode section, and five playbook references that point to files absent from the bundle.

Suggestions

Provide the missing playbook files (default.md, architecture.md, pattern.md, technology.md, design.md) in a references/ directory so the routing targets actually exist.

De-duplicate the depth-routing and structured-block field definitions that appear in both the 'STOP — Read This First' section and the 'Agent-Triggered Mode' section — define them once and cross-reference.

Trim or collapse the 'Example Interaction Shapes' list, which repeats routing cases already implied by the Phase 2 routing rules.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and instructional rather than padded with concepts Claude already knows, but the depth-routing and structured-block field definitions are duplicated between the 'STOP — Read This First' section and the 'Agent-Triggered Mode' section, and the long 'Example Interaction Shapes' list could be trimmed — fitting anchor 3.	3 / 5
Actionability	It provides copy-paste-ready templates (the WHAT/WHERE/HOW/CONNECTS TO block, the follow-up footer, the AskUserQuestion options with exact headers and labels) plus concrete output constraints (e.g. '2–5 sentences as a single plain paragraph', the [file:line](path#Lline) link format), matching anchor 5's fully executable guidance.	5 / 5
Workflow Clarity	The workflow has a clear sequence with explicit branching — the STOP prefix-check gate, one-at-a-time interview pacing, then playbook routing — but there are no validation/error-recovery feedback loops, which is acceptable for a non-destructive explanation skill and places it at anchor 4 rather than 5.	4 / 5
Progressive Disclosure	The body is well-sectioned and clearly signals one-level-deep references ('follow architecture.md', 'follow default.md'), but the referenced playbook files (default.md, architecture.md, pattern.md, technology.md, design.md) do not exist anywhere in the bundle, so the disclosure structure is incomplete and not actually navigable — fitting anchor 3.	3 / 5
	Total	15 / 20 Passed

Description

86%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 is strong: it pairs a clear statement of what the skill does with concrete, natural trigger phrases and covers both user- and agent-triggered modes. Its main weakness is mild genericness in the 'what is X' trigger that could overlap with non-codebase explanation requests.

Dimension	Reasoning	Score
Specificity	The description names the domain ('Explains features, terms, and concepts from a codebase') and one-to-two concrete action categories (explain/describe/understand, plus returning a structured WHAT/WHERE/HOW/CONNECTS TO block in agent mode), but is not comprehensive in its action list — it fits anchor 3 rather than anchor 4's 'several specific actions'.	3 / 5
Completeness	It explicitly answers both what ('Explains features, terms, and concepts from a codebase') and when ('Use whenever the user asks to explain, describe, or understand something...') with concrete trigger phrases, matching the anchor 5 example pattern.	5 / 5
Trigger Term Quality	It includes comprehensive natural trigger phrases users would actually say — 'explain X', 'what is X', 'how does X work' — alongside synonyms describe/understand, matching the anchor 5 'comprehensive coverage of natural terms including synonyms'.	5 / 5
Distinctiveness Conflict Risk	The codebase-explanation niche is mostly distinct with clear triggers, but generic phrasing like 'what is X' carries minor overlap risk with general-knowledge or other explain skills, so it sits at anchor 4 rather than 5.	4 / 5
	Total	17 / 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
relative_links	Relative link issues: 2 missing, 2 deeper-than-1-level	Warning

	Total	15 / 16 Passed

Repository: RoleModel/rolemodel-skills
Path: skills/explain/SKILL.md
Commit: 6695348

Reviewed: 3 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.