CtrlK
BlogDocsLog inGet started
Tessl Logo

lecture-style

Masterclass lecturing — one continuous explanation carried by slides, with dense pages, long narration that builds an argument across several real cases, and checkpoints that are rare and deliberate. Use when the ask is a lecture, a masterclass, a systematic walkthrough of a subject, 「大师课」「系统讲解」「讲透」, or any topic whose payoff is understanding rather than practice; also use when the user names this style. Not for hands-on training (that is `workshop-style`) and not for a course whose point is manipulating a mechanism (that is `deep-interactive`).

67

Quality

84%

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

75%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 tightly written, opinionated design skill that assumes Claude's competence and translates abstract style goals into concrete, quantified rules anchored on real runtime APIs. The main opportunities are showing one complete generate_scene call and tightening the occasional rhetorical framing.

DimensionReasoningScore

Conciseness

Dense and opinionated with no padding of concepts Claude already knows; quantified rules and good/bad narration examples earn their place. A few rhetorical framing lines ("Density is a feature here: a lecture page that says one thing is a wasted page") could be trimmed, so it is efficient rather than maximally lean.

4 / 5

Actionability

Gives concrete API calls (generate_scene, set_roster, create_stage), named fields (brief, materialFacts, voiceDesign.delivery), and quantified thresholds (4–6 keyPoints, 3–5 pages per arc, ≤1 interactive page, one quiz per 4–5 pages) plus copy-ready example briefs. It is instruction-only so there is no executable code, and a complete worked generate_scene call is not shown, keeping it at 4 rather than 5.

4 / 5

Workflow Clarity

A clear generation sequence is present — plan in conversation, then create_stage, then one generate_scene per page with an explicit brief, with page content and narration written by separate calls. Validation checkpoints are implicit, but this is a design skill rather than a destructive/batch operation, so the missing-feedback-loop cap does not apply.

4 / 5

Progressive Disclosure

No bundle files exist; the single SKILL.md is well-organized with clear section headers (The shape, Page density, Narration, The roster, Carrying the style into the generators, Scene naming) and no inlined content that belongs in a separate file. Because it exceeds 50 lines, the simple-skill 5-exception does not strictly apply, so it sits at 4.

4 / 5

Total

16

/

20

Passed

Description

87%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, well-scoped description: it states what the skill produces, gives concrete multilingual trigger phrases, and draws explicit boundaries against adjacent styles. The only soft spot is that the "what" reads as output characteristics rather than a crisp action list, keeping specificity at 4.

DimensionReasoningScore

Specificity

Lists several concrete output characteristics — "one continuous explanation carried by slides", "dense pages", "long narration that builds an argument across several real cases", "checkpoints that are rare and deliberate" — but these are descriptive qualities of the deliverable rather than a comprehensive action-verb list, so it sits at 4 rather than 5.

4 / 5

Completeness

Explicitly answers both what ("Masterclass lecturing — one continuous explanation carried by slides…") and when ("Use when the ask is a lecture, a masterclass… or any topic whose payoff is understanding rather than practice") with concrete trigger phrases and negative boundary guidance.

5 / 5

Trigger Term Quality

Good natural-term coverage with English synonyms ("lecture", "masterclass", "systematic walkthrough") and Chinese variants (「大师课」「系统讲解」「讲透」) plus a "names this style" catch-all; a few natural phrasings could still be missing, so not a 5.

4 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (masterclass lecture design) and explicitly disambiguates from sibling skills — "Not for hands-on training (that is `workshop-style`) and not for a course whose point is manipulating a mechanism (that is `deep-interactive`)", minimizing conflict risk.

5 / 5

Total

18

/

20

Passed

Validation

93%

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

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
THU-MAIC/OpenMAIC
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.