CtrlK
BlogDocsLog inGet started
Tessl Logo

manim-composer

Trigger when: (1) User wants to create an educational/explainer video, (2) User has a vague concept they want visualized, (3) User mentions "3b1b style" or "explain like 3Blue1Brown", (4) User wants to plan a Manim video or animation sequence, (5) User asks to "compose" or "plan" a math/science visualization. Transforms vague video ideas into detailed scene-by-scene plans (scenes.md). Conducts research, asks clarifying questions about audience/scope/focus, and outputs comprehensive scene specifications ready for implementation with ManimCE or ManimGL. Use this BEFORE writing any Manim code. This skill plans the video; use manimce-best-practices or manimgl-best-practices for implementation.

68

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

67%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 planning skill with a clear phased workflow, concrete clarifying questions, and a usable output template. Its main weaknesses are a generic principles section that pads the body and a broken templates reference paired with inlined template content.

Suggestions

Trim or move the '3b1b Style Principles' section into references/visual-techniques.md, keeping only the non-obvious guidance inline to reduce token padding.

Create the missing templates/scenes-template.md (or remove the broken reference) and reference it from the body instead of inlining the full template, so the overview stays lean.

Add an explicit checkpoint in Phase 2/3 such as 'Confirm audience, scope, and length with the user before generating the full scenes.md' to strengthen workflow validation.

DimensionReasoningScore

Conciseness

The workflow phases, clarifying questions, and output template are efficient and earn their tokens, but the '3b1b Style Principles' section ('Show, don't just tell', 'Pose questions', 'Acknowledge difficulty', 'Celebrate insight') restates generic pedagogy Claude already knows. It is not a 4 because that section is padding that could be trimmed, and not a 2 because the bulk of the body is genuinely useful rather than extensively padded.

3 / 5

Actionability

Provides concrete, actionable guidance: specific clarifying questions to ask, a copy-paste-ready scenes.md template structure, and named Manim output targets (ManimCE/ManimGL). It is not a 5 because there is no worked, filled-in example of a complete scenes.md (only a placeholder template), leaving a minor gap in coverage.

4 / 5

Workflow Clarity

Three numbered phases (Understand, Clarify, Create scenes.md) with substeps form a clear sequence, and Phase 2 includes a light feedback cue ('not all at once - adapt based on responses'). It is not a 5 because there is no explicit checkpoint confirming scope/audience with the user before generating the full plan, and not a 3 because the sequence is well-structured rather than loosely listed.

4 / 5

Progressive Disclosure

The body is an overview that signals one-level-deep references with descriptions (narrative-patterns.md, visual-techniques.md, scene-examples.md — all present). It is not a 5 because the referenced templates/scenes-template.md does not exist (no templates directory) while its content is duplicated inline, a minor organization gap.

4 / 5

Total

15

/

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.

A strong description that clearly states what the skill does, when to trigger it via concrete natural phrases, and how it differs from related implementation skills. It uses third-person voice for capabilities and reserves imperative 'Use this' for the trigger clause, matching the good-example pattern.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'Transforms vague video ideas into detailed scene-by-scene plans', 'Conducts research', 'asks clarifying questions about audience/scope/focus', 'outputs comprehensive scene specifications ready for implementation with ManimCE or ManimGL' — covering the workflow comprehensively. It is not a 4 because the actions span the full planning pipeline rather than having coverage gaps.

5 / 5

Completeness

Explicitly answers 'what' ('Transforms vague video ideas into detailed scene-by-scene plans... outputs comprehensive scene specifications') and 'when' with a numbered 'Trigger when: (1)...(5)' list plus 'Use this BEFORE writing any Manim code.' It is not a 4 because both what and when are concrete and explicit rather than weakly specified.

5 / 5

Trigger Term Quality

Includes natural user phrases and synonyms such as 'educational/explainer video', '3b1b style', 'explain like 3Blue1Brown', 'plan a Manim video or animation sequence', and 'compose or plan a math/science visualization'. It is not a 4 because both colloquial ('3b1b style') and descriptive variants are present with strong coverage.

5 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (Manim video planning) and explicitly distinguishes itself from implementation skills: 'This skill plans the video; use manimce-best-practices or manimgl-best-practices for implementation.' It is not a 4 because the boundary against sibling skills is stated, minimizing conflict risk.

5 / 5

Total

20

/

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.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 1 missing

Warning

Total

15

/

16

Passed

Repository
calesthio/OpenMontage
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.