teach

Constraint-driven teaching at three depths: a 5-Minute Gist (the whole picture in one read), an Expert Briefing (dense one-sitting mental model), or a Full Curriculum (interactive, section-by-section). Use whenever the user wants to learn or understand anything: "teach me X", "explain X", "give me the gist of X", "what's the deal with X", "crash course on X", "briefing on X", "how does X actually work", "help me understand X", "5 min version of X", or when they're prepping for a meeting or conversation on an unfamiliar topic. Even casual asks like "make X make sense", "what's a linter?", or "why is X the way it is" should trigger this. First establish which depth fits, then teach in that mode.

1.90x

Quality

89%

Does it follow best practices?

Impact

99%

1.90x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Quality

Content

78%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 well-structured, actionable skill body: it cleanly separates a shared engine from three mode-specific reference files, gives concrete style and self-audit directives, and uses progressive disclosure effectively. The main lever is tightening the shared-engine prose to assume a bit more of Claude's competence.

Suggestions

Trim the 'Explain through necessity' and style-rules sections to denser bullets; several paragraphs restate principles Claude can infer, which would lift conciseness without losing guidance.

Add one short before/after mini-example illustrating 'say the thing then explain it' inline so the actionability of the style rules is self-evident rather than abstract.

Make the escalation-ladder step an explicit checkpoint in the workflow sequence (not just a closing offer) so the multi-mode flow has a clearer feedback/continuation loop.

Dimension	Reasoning	Score
Conciseness	Mostly lean and directive with punchy style rules, but the shared-engine section is lengthy and re-states framing Claude could infer, leaving a few instances of over-explanation that could be trimmed.	4 / 5
Actionability	Concrete, executable guidance throughout (signpost patterns, the say-the-thing-then-explain rule, real-number examples, a mandatory jargon scan) with only minor gaps; it is instruction-only but the directives are specific.	4 / 5
Workflow Clarity	Clear two-step sequence (Pick the Mode -> Read the Mode's Reference, Then Teach) with a self-audit checklist acting as a validation checkpoint before sending; minor gaps in explicit feedback loops but no destructive/batch operations so the cap does not apply.	4 / 5
Progressive Disclosure	Clear overview pointing to one-level-deep, well-signaled references (gist.md, briefing.md, curriculum.md) that are verified present, with content appropriately split between the engine overview and per-mode detail files.	5 / 5
	Total	17 / 20 Passed

Description

100%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.

An exceptionally strong description: it states concrete capabilities, gives a rich set of natural trigger phrases, answers both 'what' and 'when' explicitly, and carves out a clear, low-conflict niche. No vague fluff or over-claims.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions across three named depths (5-Minute Gist, Expert Briefing, Full Curriculum) and an explicit process ('First establish which depth fits, then teach in that mode'), giving comprehensive coverage.	5 / 5
Completeness	Explicitly answers both what (a three-depth teaching engine) and when (concrete trigger phrases plus an explicit fallback: 'Even casual asks ... should trigger this').	5 / 5
Trigger Term Quality	Comprehensive natural phrases users actually say ('teach me X', 'explain X', 'give me the gist of X', 'crash course on X', 'make X make sense', 'what's the deal with X') including synonyms and casual variants.	5 / 5
Distinctiveness Conflict Risk	Clear niche (constraint-driven teaching/explanation) with distinct, recognizable triggers and minimal overlap risk with other skills.	5 / 5
	Total	20 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: EveryInc/teach-skill
Path: SKILL.md
Commit: 02ec4c8

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.