ce-explain

Create a durable visual teaching artifact for something worth learning. 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, operational diagnosis, or a concise trade-off that belongs in chat. For learning, not repo docs or verdicts.

Quality

87%

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

92%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.

A dense, well-engineered process skill: executable grounding code, six explicitly sequenced phases with validation gates and feedback loops, and clean one-level-deep references to real bundle files. The only minor weakness is a few paragraphs that repeat degradation rationale and could be trimmed for token efficiency.

Suggestions

Consolidate the two no-subagent/no-blocking-tool degradation explanations (Phase 2 recap mode and Phase 6 non-interactive) into a single shared rule referenced once, to reduce repeated prose.

Tighten the Phase 3 diff-mode hard-ordering paragraph by splitting the rule from its rationale so the imperative reads faster.

Dimension	Reasoning	Score
Conciseness	The body is lean, assumes Claude's competence, and runs an executable bash block rather than narrating concepts, but a few passages (the repeated no-subagent degradation explanations and the lengthy diff-mode ordering paragraph) could be tightened, keeping it just below the every-token-earns-its-place anchor.	4 / 5
Actionability	It provides a copy-paste-ready bash block with explicit security checks plus concrete per-phase mechanics (exact phase-choice recording, hard ordering rule, named reference files per phase), covering the common cases such as empty ranges, empty windows, and no-subagent degradation.	5 / 5
Workflow Clarity	Six phases are sequenced with explicit validation checkpoints (run-dir ownership/symlink checks, operational-question gate, warrant test, prediction-before-reveal ordering) and feedback loops (prediction lands -> reveal names gaps; correct exercises and name the gap), matching the explicit-validation-and-feedback-loops anchor.	5 / 5
Progressive Disclosure	SKILL.md is a clear overview with well-signaled, one-level-deep references to real files (intake.md, orchestration.md, check-in.md, explainer-html.md, explainer-markdown.md, destinations.md, agents/work-recap-scout.md), each owning a delimited concern, with content appropriately split and easy to navigate.	5 / 5
	Total	19 / 20 Passed

Description

82%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 strong, third-person description with an explicit Use-when trigger set and clear negative boundaries that distinguish it from sibling skills. The only gap is specificity: it names one core capability rather than enumerating several concrete actions.

Suggestions

List two or three concrete actions the skill performs (e.g. "compose an HTML explainer, run a prediction check-in, publish to a chosen destination") to lift specificity toward the several-actions anchor.

Add a couple of natural trigger synonyms users say in chat (e.g. "walk me through", "catch me up on") to round out trigger-term coverage.

Dimension	Reasoning	Score
Specificity	"Create a durable visual teaching artifact" names the core action and its variants (deep explainer, work recap), but it is a single capability rather than a list of several concrete actions, fitting the 1-2-actions anchor rather than the several-actions anchor.	3 / 5
Completeness	It explicitly answers both what ("durable visual teaching artifact for something worth learning") and when (a "Use when..." clause with multiple concrete triggers), plus a "Not for..." negative boundary, matching the explicit-what-and-when-with-concrete-triggers anchor.	5 / 5
Trigger Term Quality	"wants to be taught, wants a deep explainer, wants to understand a substantial change, or wants a work recap" gives good natural-phrase coverage users would actually say, with a few common variants missing, matching the good-coverage anchor rather than comprehensive coverage.	4 / 5
Distinctiveness Conflict Risk	The explicit "Not for ordinary Q&A, operational diagnosis, or a concise trade-off... not repo docs or verdicts" carve-outs give it a clear niche with distinct triggers and minimal conflict risk with adjacent skills.	5 / 5
	Total	17 / 20 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: 26bf5b1

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.