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.

76

Quality

94%

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-structured instruction-only skill: the workflow is clearly sequenced with feedback loops and a quality checklist, guidance is concrete throughout, and detail is appropriately offloaded to two well-signaled, one-level-deep reference files. The only improvement area is trimming the handful of rules that are stated multiple times across sections.

Suggestions

Consolidate the solution-hiding rule into one authoritative statement (core behavior) and have the learning contract, course completion, and quality checklist reference it rather than restate it.

The incremental 'one chapter at a time' rule appears in core behavior, the learning contract, and the course map section — state it once and trim the restatements.

DimensionReasoningScore

Conciseness

The body is dense with operational rules and avoids teaching concepts Claude already knows, but a few rules repeat across sections: solution-hiding appears in core behavior, the learning contract, course completion, and the quality checklist, and the incremental-teaching rule is restated several times. It is efficient with minor trimmable repetition — the score-5 anchor's 'every token earns its place' is not quite met.

4 / 5

Actionability

Fully concrete guidance despite being instruction-only: specific counts (3–12 chapters, 2–4 warm-up questions, 3–5 exercises), an 8-step lesson loop, a 5-step grading sequence with named verdict categories, an enumerated bilingual command list, and defined state fields. The guidance is copy-paste ready in the instructional sense the scoring notes describe.

5 / 5

Workflow Clarity

The multi-step process is clearly sequenced (input mode → course start → course map → lesson loop → grading → mastery tracking → completion) with explicit feedback loops: the hint ladder, remediate/advance decisions on both wrong and correct answers, and a pre-response quality checklist that functions as a validation checkpoint.

5 / 5

Progressive Disclosure

SKILL.md is a genuine overview and both references are real files, clearly signaled, and one level deep: 'See references/session-formats.md for both formats' and 'Consult references/practice-and-mastery.md for exercise-writing rules, difficulty bands, adaptation, and grading rubrics'. The body also explains the division of labor (cognitive levels vs difficulty bands), and neither reference file nests further references.

5 / 5

Total

19

/

20

Passed

Description

96%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 description that explicitly answers both what the skill does and when to use it, with an unusually rich set of natural trigger phrases including non-English variants and resume-mode triggers. The only weakness is that a few of its broad verbs ('review', 'study', 'understand') could collide with general explanation or summarization skills.

DimensionReasoningScore

Specificity

The description lists multiple concrete actions with comprehensive coverage: turning a PDF, paper, book chapter, document, URL, or topic into a structured interactive course, plus answer grading, hints, spaced review, final assessment, level adaptation, and preservation of page or section references. It goes beyond the score-4 anchor's 'minor gaps in coverage' — the action set covers the full course lifecycle.

5 / 5

Completeness

Both questions are explicitly answered: the 'what' is 'Turn an uploaded PDF, paper, book chapter, document, URL, or user-provided topic into a structured, interactive learning course', and the 'when' is a full 'Use when...' clause with concrete trigger phrases for new courses, explicit requests, and resumption from saved state.

5 / 5

Trigger Term Quality

Comprehensive natural terms including synonyms: 'learn, study, understand, master, review, or practice a subject chapter by chapter', 'tutorial', 'curriculum', 'exercises, quizzes', 'teach me this', 'learn this PDF', plus Chinese equivalents ('分章节教学', '带我学', '接着上次学') and resume triggers ('continue my course'). These are phrases a user would naturally say.

5 / 5

Distinctiveness Conflict Risk

Distinct niche triggers like 'teach me this' and 'learn this PDF' clearly separate this from summarization or explanation skills. However, broad verbs such as 'review', 'study', and 'understand' carry some overlap risk with general explain/summarize requests, so it is 'mostly distinct with minor overlap' rather than minimal conflict risk.

4 / 5

Total

19

/

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.

Validation — 16 / 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.