ce-explain

Create a durable, visual teaching artifact — plus an optional check-in (predict-then-reveal for diffs, corrected exercises) that makes it stick — for something worth learning: a concept, a diff, an idea, or a window of your own recent work. Use when the user wants to be taught, wants a deep explainer, wants to understand a substantial change, or wants a work recap built for retention. Not for ordinary Q&A, brief 'why?' follow-ups, operational diagnosis, status updates, or a concise trade-off answer that belongs inline in chat. For learning, not repo docs or verdicts.

Quality

92%

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

Quality

Content

85%Weight 40%Scale 1-3

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

A well-structured, actionable instruction skill with a clear six-phase workflow, explicit validation feedback loops, and clean one-level-deep progressive disclosure. Its only weakness is mild verbosity in harness-conditional fallback prose that could be tightened or offloaded.

Suggestions

Tighten the Interaction Method and Destination ask paragraphs: move per-harness tool names and option-cap edge cases into references/destinations.md, keeping the body to the rule and the one-line fallback.

The Model Tiers and Artifact Root sections mix durable rules with config-resolution detail; consider pulling the ce-docs-root resolution block into a reference so the body states only where and when to resolve it.

Dimension	Reasoning	Score
Conciseness	The body is dense and largely earns its tokens, but several passages over-specify harness-conditional fallbacks (the long Interaction Method paragraph and the Destination ask's per-platform option caps) that could be tightened or moved to a reference; it sits between the lean score-3 and the slightly padded score-2 anchor.	2 / 3
Actionability	Provides concrete executable bash for scratch-root creation with explicit symlink/ownership guards, names exact reference files for each phase, and gives per-option destination routing with real commands — matching the copy-paste-ready score-3 anchor for an instruction skill.	3 / 3
Workflow Clarity	The six-phase sequence is explicit with validation checkpoints throughout: scratch-root safety checks, empty-range/empty-window handling that asks before substituting, the hard ordering rule for quiz reveals, and 'settle rendering then run consent gate' feedback loops — matching the score-3 anchor.	3 / 3
Progressive Disclosure	SKILL.md is an overview that points one level deep to six real, well-signaled reference files (intake, check-in, explainer-html/markdown, destinations, agents/work-recap-scout), each referenced at the exact phase that needs it, matching the clear-overview-with-one-level-deep-references score-3 anchor.	3 / 3
	Total	11 / 12 Passed

Description

100%Weight 40%Scale 1-3

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 precise, third-person description that states concrete actions, natural trigger phrasing, an explicit 'Use when' clause, and an exclusion list that sharply bounds scope. It satisfies all four anchors at the top of the scale without verbosity.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Create a durable, visual teaching artifact', 'plus an optional check-in (predict-then-reveal for diffs, corrected exercises)', and four distinct input types — closely matching the score-3 anchor listing several specific concrete actions.	3 / 3
Completeness	Explicitly answers both 'what' (create a visual teaching artifact plus optional check-in) and 'when' via an explicit 'Use when...' clause, and additionally delimits scope with a 'Not for...' exclusion list, satisfying the score-3 anchor for both what AND when.	3 / 3
Trigger Term Quality	Covers natural phrasings a user would actually say — 'wants to be taught', 'wants a deep explainer', 'wants to understand a substantial change', 'wants a work recap built for retention' — with good coverage of common variations rather than technical jargon.	3 / 3
Distinctiveness Conflict Risk	The 'Not for...' clause (ordinary Q&A, operational diagnosis, status updates, trade-off answers, repo docs, verdicts) carves a clear niche from sibling skills and lists distinct triggers, making conflict with other skills unlikely per the score-3 anchor.	3 / 3
	Total	12 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
referenced_paths_exist	Referenced path issues: 1 deeper-than-1-level	Warning

	Total	14 / 16 Passed

Repository: EveryInc/compound-engineering-plugin
Path: skills/ce-explain/SKILL.md
Commit: a9f6d53

Reviewed: 7 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.