CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

live-tutorial

Create an annotated MP4 tutorial from a workflow demonstrated in the owner's actual application. Use when asked for a tutorial video, not merely to watch an action live.

Quality

90%

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

100%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.

The body is a dense, production-quality instruction set: a numbered workflow with explicit validation and error handling, exact tool names, a copy-paste renderer invocation with manifest schema, and precise annotation rules. Nothing is padded and the single bundle dependency is properly externalized.

DimensionReasoningScore

Conciseness

About 46 lean lines covering a complex multi-step workflow with zero concept explanations and no padding; every prohibition encodes a concrete failure mode ("do not search it for frames", "never shell automation", "do not reconstruct them"). Matches anchor 5 (every token earns its place); the occasional repeated constraint is deliberate reinforcement rather than over-explanation.

5 / 5

Actionability

Fully executable guidance: exact tool calls ("computer_use.cua.start_recording" with "record_video: false"), copy-paste renderer commands for both bash and PowerShell, a complete JSON manifest schema with exact field names, and precise point-annotation copy rules ({x, y, coordinateWidth, coordinateHeight}). Matches anchor 5 (copy-paste ready, covers the common cases).

5 / 5

Workflow Clarity

A clearly sequenced 6-step process with explicit validation ("Check the renderer's resolvedTargets against the intended controls... Correct any mismatch before returning fileMarker verbatim"), verification of intermediate states in steps 3-4, and retry guidance ("Keep valid captures across retries rather than re-recording"). Destructive actions are explicitly gated, so the destructive/batch cap does not apply. Matches anchor 5.

5 / 5

Progressive Disclosure

The body is under 50 lines with well-organized sections; renderer implementation is correctly externalized to the bundled script scripts/render-tutorial.mjs, which exists and is invoked by exact path; no nested or buried references. Per the rubric's simple-skill guidance this matches anchor 5.

5 / 5

Total

20

/

20

Passed

Description

75%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.

The description cleanly answers both what the skill does and when to use it, with an explicit trigger phrase and a negative clause that sharply reduces conflict risk. Its weaknesses are limited keyword breadth (no "how-to", "walkthrough", or "screen recording" synonyms) and a single composite action rather than a list of specific capabilities.

Suggestions

Broaden trigger coverage with natural synonyms users would say, e.g. "Use when asked for a tutorial, how-to, or demo video of an app workflow".

Mention one or two more concrete capabilities (e.g. capturing annotated step screenshots and rendering captions) so the 'what' reads as a list of specific actions rather than a single composite one.

DimensionReasoningScore

Specificity

Names the domain and one concrete composite action ("Create an annotated MP4 tutorial from a workflow demonstrated in the owner's actual application") but lists only that single action rather than several, leaving coverage of demonstrating, captioning, and rendering implicit. Matches anchor 3 (1-2 concrete actions, not comprehensive); not anchor 4 since it does not list several specific actions.

3 / 5

Completeness

Explicitly answers both: what ("Create an annotated MP4 tutorial from a workflow demonstrated in the owner's actual application") and when with a concrete trigger phrase ("Use when asked for a tutorial video") plus a negative disambiguator ("not merely to watch an action live"). Matches anchor 5 clearly.

5 / 5

Trigger Term Quality

Includes the primary natural phrase "asked for a tutorial video" plus "MP4" and the distinguishing "watch an action live", but misses common variations users would say such as "how-to video", "walkthrough", "demo video", or "screen recording". Anchor 3 fits (relevant keywords missing common synonyms); anchor 4 would require only a few missing terms.

3 / 5

Distinctiveness Conflict Risk

Clear niche (annotated tutorial videos produced from live demonstration) with distinct triggers; the negative clause actively prevents mis-triggering against a live-viewing skill. Matches anchor 5 (clear niche, minimal conflict risk).

5 / 5

Total

16

/

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

leon-ai/leon

Path

skills/agent/live-tutorial/SKILL.md

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.