CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

manimgl-best-practices

Trigger when: (1) User mentions "manimgl" or "ManimGL" or "3b1b manim", (2) Code contains `from manimlib import *`, (3) User runs `manimgl` CLI commands, (4) Working with InteractiveScene, self.frame, self.embed(), ShowCreation(), or ManimGL-specific patterns. Best practices for ManimGL (Grant Sanderson's 3Blue1Brown version) - OpenGL-based animation engine with interactive development. Covers InteractiveScene, Tex with t2c, camera frame control, interactive mode (-se flag), 3D rendering, and checkpoint_paste() workflow. NOT for Manim Community Edition (which uses `manim` imports and `manim` CLI).

Quality

81%

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

The canonical home for this skill is manimgl-best-practices in calesthio/OpenMontage

SKILL.md
Quality
Evals
Security

Quality

Content

61%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's inline content is high quality — lean, executable ManimGL code with a genuinely useful ManimGL-vs-ManimCE differences table and pitfalls list. However, its progressive disclosure is broken in practice: the entire link index points to files absent from the bundle while the actual references/ files are orphaned, leaving an agent unable to navigate to the detailed material the skill promises.

Suggestions

Fix the bundle mismatch: either add the referenced rules/, examples/, templates/, and LICENSE.txt files, or repoint SKILL.md's link index at the 8 existing references/*.md files (e.g. three_d_surfaces.md, equation_transforms.md) so the actual bundle is discoverable.

Deduplicate 'Common Pitfalls' against the 'Key Differences from ManimCE' table — both cover ShowCreation vs Create, self.frame vs self.camera.frame, and fix_in_frame(); keep one.

Remove the Installation section (`pip install manimgl`, `manimgl --version`) — it explains steps Claude already knows and adds tokens without new information.

DimensionReasoningScore

Conciseness

The body is mostly lean, executable code with terse comments and no padding essays about what Manim is — matching 'efficient; minor instances of over-explanation that could be trimmed'. It is not a 5 because the 'Common Pitfalls' section repeats content already in the 'Key Differences from ManimCE' table (ShowCreation vs Create, self.frame, fix_in_frame), and the Installation section (`pip install manimgl`, `manimgl --version`) explains something Claude already knows.

4 / 5

Actionability

The Quick Reference provides copy-paste-ready, executable code covering the common cases (scene structure, render commands, camera control, Tex/t2c, embed, checkpoint_paste), which meets the 5 anchor's inline standard. It drops to 4 because the top-level instruction 'Read individual rule files for detailed explanations' and every example/template link points to files that do not exist in the bundle, so that concrete guidance cannot be executed.

4 / 5

Workflow Clarity

The body is a pattern catalog rather than a sequenced workflow: the Interactive Development Workflow section sketches a mini-sequence (-se then checkpoint_paste) but there is no explicit path through the material, and the primary 'How to use' instruction is unusable because the referenced rule files are missing. This sits at 'sequence present but implicit' rather than 4's 'clear sequence with most checkpoints present'; no validation cap applies since no destructive or batch operations are involved.

3 / 5

Progressive Disclosure

Scored against the actual bundle: every referenced path in the body (17 rules/*.md, 5 examples/*.py, 4 templates/*.py, LICENSE.txt) is a dead link to nonexistent files, while the 8 real bundle files under references/ (equation_transforms.md, three_d_surfaces.md, etc.) are never mentioned in SKILL.md at all — and each of those in turn points to missing examples/*.py files. The links are clearly signaled and one level deep (keeping this above a 1), but navigation is fundamentally broken, matching 'references are buried' at the 2 anchor.

2 / 5

Total

13

/

20

Passed

Description

95%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: it explicitly answers both what the skill covers and when to trigger it, with concrete API-level trigger terms and an explicit exclusion clause that cleanly disambiguates it from Manim Community Edition. The only weakness is that capabilities are phrased as topic coverage ('Covers...') rather than concrete actions.

DimensionReasoningScore

Specificity

The description lists six concrete named capabilities ("Covers InteractiveScene, Tex with t2c, camera frame control, interactive mode (-se flag), 3D rendering, and checkpoint_paste() workflow"), which matches the 'several specific actions; minor gaps' anchor. It falls short of a 5 because capabilities are framed as topic coverage ('Covers X, Y, Z') rather than the concrete action verbs of the top anchor ("Extract text... fill forms... merge documents").

4 / 5

Completeness

Both halves are explicit: 'when' via "Trigger when: (1) User mentions... (2) Code contains... (3) User runs... (4) Working with..." and 'what' via the concrete capability list (InteractiveScene, Tex with t2c, camera frame control, -se flag, 3D rendering, checkpoint_paste()). This directly matches the anchor 'Clearly and explicitly answers both what AND when with concrete trigger phrases'.

5 / 5

Trigger Term Quality

Trigger terms are comprehensive and natural: "manimgl", "ManimGL", "3b1b manim", the import statement `from manimlib import *`, "manimgl CLI commands", and API names like "InteractiveScene, self.frame, self.embed(), ShowCreation()". This covers synonyms, the import pattern, and the CLI exactly as a user working with ManimGL would say them, matching the top anchor.

5 / 5

Distinctiveness Conflict Risk

The niche is clear (3b1b/ManimGL specifically) and the single largest conflict risk — Manim Community Edition — is explicitly excluded: "NOT for Manim Community Edition (which uses `manim` imports and `manim` CLI)". Triggers are distinct to this library, matching the 'clear niche with distinct triggers; minimal conflict risk' anchor.

5 / 5

Total

19

/

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

relative_links

Relative link issues: 28 missing

Warning

Total

15

/

16

Passed

Repository

calesthio/OpenMontage

Path

.claude/skills/manimgl-best-practices/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.