CtrlK
BlogDocsLog inGet started
Tessl Logo

learn-everything

Turn an uploaded PDF, paper, book chapter, document, URL, or user-provided topic into a structured, interactive learning course. Use when the user wants to learn, study, understand, master, review, or practice a subject chapter by chapter; asks for a tutorial or curriculum from source material; wants exercises, quizzes, answer grading, hints, spaced review, or a final assessment; or says "teach me this", "learn this PDF", "分章节教学", "带我学", or similar; or returns to continue a previous course ("continue my course", "接着上次学") or supplies a saved course-state file or state block. Adapt explanations and practice to the learner's level, preserve page or section references for documents, and teach incrementally rather than dumping all content at once.

77

Quality

96%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

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 well-architected instruction-only skill: actionable numbered procedures, explicit feedback loops and a pre-response quality checklist, and clean two-file progressive disclosure. The only meaningful improvement is tightening minor redundancy across sections to earn full conciseness marks.

Suggestions

Consolidate the solution-hiding rule into one canonical statement instead of restating it in Core behavior, the Practice section, and Quality checks.

A few sizing/structuring rules in 'Build the course map' overlap with 'Determine the input mode'; merge the duplicate guidance to shorten the body.

Consider moving the full learner-commands table or the cognitive-levels list into a reference file to further slim the core SKILL.md, since both are lookup-style detail.

DimensionReasoningScore

Conciseness

Mostly efficient and assumes Claude's competence (no basic-concept padding, e.g. it never explains what a PDF or a quiz is), but at ~200 lines a few sections repeat guidance already implied elsewhere (e.g. solution-hiding restated in Core behavior, Quality checks, and Practice) and could be trimmed, fitting the 4 anchor rather than the every-token-earns-its-place 5 anchor.

4 / 5

Actionability

Provides concrete, copy-paste-ready procedures despite being instruction-only: an 8-step lesson loop, a 5-step grading sequence, four named difficulty bands, six cognitive levels, and an explicit learner-commands table — the scoring notes exempt instruction-only skills from needing code when guidance is this actionable, matching the 5 anchor.

5 / 5

Workflow Clarity

Multi-step processes are explicitly sequenced with validation checkpoints and feedback loops: the lesson loop grades then decides advance/remediate/increase, the resume mode runs warm-up retrieval before new content, and a "Quality checks" checklist runs before each response, matching the 5 anchor (clear sequence, explicit validation, feedback loops, checklist).

5 / 5

Progressive Disclosure

SKILL.md is a clear overview with two well-signaled one-level-deep references ("See `references/session-formats.md`", "Consult `references/practice-and-mastery.md`"); both files exist, are flat with no nested see-also chains, and hold detail (formats, exercise rubrics) appropriately split out of the main body, matching the 5 anchor.

5 / 5

Total

19

/

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: dense rather than padded, third-person/imperative voice, comprehensive input and trigger coverage, and explicit what-and-when guidance. Its only soft spot is length, but every clause carries distinct trigger or capability information.

DimensionReasoningScore

Specificity

Lists multiple concrete actions ("Turn ... into a structured, interactive learning course", "Adapt explanations and practice", "preserve page or section references", "teach incrementally") with comprehensive coverage of input types and behaviors, matching the comprehensive-coverage anchor rather than the minor-gaps anchor at 4.

5 / 5

Completeness

Explicitly answers both what ("Turn an uploaded PDF ... into a structured, interactive learning course") and when via a concrete "Use when ..." clause with multiple trigger phrases, exactly matching the 5 anchor; it is well above the 4 anchor whose 'when' is only adequate.

5 / 5

Trigger Term Quality

Comprehensive natural trigger terms including synonyms ("learn, study, understand, master, review, or practice", "tutorial or curriculum", "exercises, quizzes, answer grading, hints, spaced review") plus multilingual variants ("分章节教学", "带我学", "接着上次学") and resume triggers ("continue my course"), exceeding the 4 anchor which expects only a few missing terms.

5 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (building adaptive chapter-by-chapter learning courses from sources or topics) with distinctive multilingual triggers and resume-state signals, giving minimal conflict risk with other skills; the 4 anchor's minor-overlap caveat does not apply.

5 / 5

Total

20

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
XiaomiMiMo/MiMo-Code
Reviewed

Table of Contents

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.