manim-explainer

Build reusable Manim explainers for technical concepts, graphs, system diagrams, and product walkthroughs, then hand off to the wider video stack if needed. Use when the user wants a clean animated explainer rather than a generic talking-head script.

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

85%

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

A well-structured, actionable skill body with executable commands, a real starter asset, and an explicit render-quality feedback loop. Its main weakness is mild redundancy (tools listed twice, trigger duplicated) and a little niche padding that could be trimmed for token efficiency.

Suggestions

Remove the duplicate fragment-assembly/siliconflow-tts entries — keep them only in 'Related Skills' and reference them once.

Trim or reword 'self-improvement lineage that informed the skill' to avoid self-referential fluff that does not aid execution.

De-duplicate the trigger guidance between 'When to Activate' and the frontmatter description to save tokens.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean and does not explain concepts Claude already knows, but it could be tightened: fragment-assembly and siliconflow-tts are listed in both 'Tool Requirements' and 'Related Skills', 'When to Activate' partially duplicates the description's trigger, and 'self-improvement lineage that informed the skill' reads as unnecessary self-referential padding. This fits the 'mostly efficient but could be tightened' anchor rather than the every-token-earns-its-place anchor 3.	2 / 3
Actionability	Provides copy-paste-ready, executable commands ('./skills/manim-explainer/scripts/render-manim.sh <scene_file>.py <ClassName> low ./output') with low/medium/high quality flags and a concrete smoke-test example against a real asset, matching the fully-executable anchor 3.	3 / 3
Workflow Clarity	The 7-step Workflow is sequenced and pairs with an explicit validation loop in Render Conventions ('start with a low-quality smoke test render' and 'only push to higher quality after composition and timing are stable'), giving the render-then-tighten checkpoint feedback the anchor 3 requires; the operation is not destructive/batch so the cap-at-2 note does not apply.	3 / 3
Progressive Disclosure	The body is a clear overview with well-signaled, one-level-deep references to real bundle files — [assets/network_graph_scene.py](assets/network_graph_scene.py) in a 'Reusable Starter' section and the scripts/render-manim.sh path in executable commands — both verified to exist, and content is appropriately split rather than monolithic.	3 / 3
	Total	11 / 12 Passed

Description

85%

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 specific, third-person description that clearly states both capability and an explicit use-when trigger, with a distinct niche. Trigger-term coverage is slightly narrow and could add common user phrasings like 'animation' or 'motion graphic'.

Suggestions

Broaden trigger terms to include natural user phrasings such as 'animation', 'motion graphics', or 'animated diagram' alongside 'animated explainer'.

Clarify the boundary with the 'wider video stack' skills so the description signals when NOT to activate this skill.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Build reusable Manim explainers for technical concepts, graphs, system diagrams, and product walkthroughs, then hand off to the wider video stack' — matching the score-3 anchor of several specific concrete actions, not just a single named domain.	3 / 3
Completeness	Explicitly answers both what ('Build reusable Manim explainers...') and when ('Use when the user wants a clean animated explainer rather than a generic talking-head script'), satisfying the anchor for clearly answering both with an explicit trigger.	3 / 3
Trigger Term Quality	The 'Use when the user wants a clean animated explainer rather than a generic talking-head script' clause gives some natural terms ('animated explainer', 'talking-head'), but coverage is narrow and omits common variations a user would actually say ('animation', 'motion graphic', 'diagram video'). It is above the jargon-only anchor 1 but below the broad-coverage anchor 3.	2 / 3
Distinctiveness Conflict Risk	The Manim-animated-explainer niche is distinct ('clean animated explainer rather than a generic talking-head script'), making it unlikely to trigger for unrelated skills; the 'hand off to the wider video stack' framing scopes rather than blurs its boundary.	3 / 3
	Total	11 / 12 Passed

Validation

87%

Warnings & errors only

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

Validation — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning

	Total	14 / 16 Passed

Repository: TeamWiseFlow/xiaobei
Path: crews/content-producer/skills/manim-explainer/SKILL.md
Commit: bcef823

Reviewed: 3 days ago

Table of Contents

Discovery Implementation Validation

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.