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.

63

Quality

75%

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

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/manim-composer/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

50%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is well-organized into a clear workflow with genuine supporting reference files, but it lands at mid-level across all dimensions: an inlined template and generic principles dilute conciseness, guidance relies on placeholders, the workflow lacks validation checkpoints, and one referenced template file is missing.

Suggestions

Move the inlined scenes.md scaffold into the referenced templates/scenes-template.md (and create that file), keeping only a brief pointer plus field descriptions inline to improve conciseness and progressive disclosure.

Trim the '3b1b Style Principles' to the non-obvious specifics Claude wouldn't already infer, removing truisms like 'Show, don't just tell' and 'Pause for insight'.

Add explicit validation checkpoints to the workflow, e.g., confirm audience/scope answers with the user before drafting scenes.md, and verify the draft covers the identified 'aha moment' and misconceptions before finalizing.

DimensionReasoningScore

Conciseness

Mostly lean and well-structured, but it inlines a ~55-line scenes.md template that should live in the referenced template file, and the '3b1b Style Principles' restate generic pedagogical truisms ('Show, don't just tell', 'Pause for insight') Claude already knows. This is 'mostly efficient but could be tightened' (score 2), not the verbose concept-explaining score-1 nor the lean score-3.

2 / 3

Actionability

Provides a concrete output scaffold and specific clarifying question sets, but much of the guidance relies on placeholders ('[Video Title]', '[X minutes]') and abstract directives ('Find the aha moment'). This matches the score-2 'some concrete guidance but incomplete' anchor rather than fully copy-paste-ready score-3 or vaguely-abstract score-1.

2 / 3

Workflow Clarity

The three phases (Understand → Clarify → Create) are clearly sequenced, but there are no explicit validation checkpoints or feedback loops (e.g., confirm scope with the user before drafting, verify the plan covers all key insights). This matches the score-2 'sequence present but checkpoints missing or implicit' anchor, not the score-3 explicit-validation level.

2 / 3

Progressive Disclosure

References (narrative-patterns.md, visual-techniques.md, scene-examples.md) are present, real, and one level deep, but the body inlines the full scenes.md template that should be a separate file, and the referenced templates/scenes-template.md does not exist. This matches the score-2 'content that should be separate is inline' / organization-could-improve anchor, not the clean score-3.

2 / 3

Total

8

/

12

Passed

Description

100%

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 is specific, complete, and distinctive: it lists concrete actions, provides explicit natural-language triggers, answers both what and when, and disambiguates from sibling implementation skills. It is one of the strongest reference-quality examples.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'Transforms vague video ideas into detailed scene-by-scene plans', 'Conducts research, asks clarifying questions', and 'outputs comprehensive scene specifications ready for implementation with ManimCE or ManimGL'. This matches the score-3 anchor of multiple specific concrete actions, not the score-2 'some actions' level.

3 / 3

Completeness

Explicitly answers what (research, clarify, plan, output specs) and when via a numbered 'Trigger when:' list plus 'Use this BEFORE writing any Manim code'. The 'when' is fully explicit, so it clears the score-3 bar rather than the score-2 'when missing or implied' level.

3 / 3

Trigger Term Quality

Captures natural phrasings users actually say — 'create an educational/explainer video', '3b1b style', 'explain like 3Blue1Brown', 'compose' or 'plan' a visualization. This is good coverage of natural terms, not the score-2 'some keywords but missing common variations' level.

3 / 3

Distinctiveness Conflict Risk

Clear Manim-planning niche with distinctive triggers, and it explicitly hands implementation off to 'manimce-best-practices or manimgl-best-practices', resolving sibling-skill overlap. This matches the score-3 'clear niche, unlikely to conflict' anchor.

3 / 3

Total

12

/

12

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.