video-toolkit

Create professional videos autonomously using claude-code-video-toolkit — AI voiceovers, image generation, music, talking heads, and Remotion rendering.

Quality

75%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/video-toolkit/SKILL.md

Quality

Content

85%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 highly actionable with a well-sequenced, validated workflow and copy-paste-ready commands — its strongest dimensions. Its weakness is progressive disclosure: it is a monolithic file that would benefit from splitting setup, composition patterns, and cost reference material into separate, clearly signaled reference files.

Suggestions

Extract the Modal deploy/setup detail (Steps 2-4) into a references/SETUP.md and keep SKILL.md as a quick-start overview that links to it, reducing the monolithic bulk.

Move the Composition Patterns and Cost Estimates sections into references/ files (e.g. COMPOSITION.md, COSTS.md) linked from the main body with one-level-deep, clearly signaled references.

Factor out the repeated `cd ~/.openclaw/workspace/claude-code-video-toolkit` line into a single stated prerequisite to trim repeated tokens while preserving the path-safety warning.

Dimension	Reasoning	Score
Conciseness	Largely command-driven with minimal concept explanation and no padding of things Claude already knows. Minor trim opportunities exist: the `cd ~/.openclaw/workspace/...` line is repeated ~15 times and some flag commentary could be condensed. Not a 5 because of that repetition and a few verbose notes.	4 / 5
Actionability	Fully executable, copy-paste-ready commands with concrete flags, presets, speaker/tone lists, and a complete config example, covering the common cases thoroughly. Matches the anchor for fully executable, copy-paste-ready guidance.	5 / 5
Workflow Clarity	A clear 7-step sequence with explicit validation checkpoints (verify_setup.py at Steps 1 and 4, timing sync at Step 5, still-frame review at Step 6) plus an error-recovery feedback table. This batch/multi-asset workflow has the validation and feedback loops the rubric rewards.	5 / 5
Progressive Disclosure	No bundle files exist and the body makes no external references, so navigation is not the issue; the problem is a ~445-line monolithic file that inlines content (Modal deploy setup, composition patterns, cost estimates) that would be better split into separate referenced files. The under-50-lines exception does not apply, and well-organized headers alone do not move it above 3.	3 / 5
	Total	17 / 20 Passed

Description

66%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 clearly conveys what the skill does and names several concrete capabilities, giving it a distinct niche. Its main weakness is the absence of an explicit "Use when..." trigger clause, which caps completeness and limits when-to-use clarity.

Suggestions

Add an explicit "Use when..." clause naming natural triggers, e.g. "Use when creating explainer videos, product demos, or adding AI voiceovers, music, or talking-head narration."

Include common user-facing synonyms and file extensions (e.g. "explainer video", "product demo", ".mp4") to broaden trigger-term coverage.

Reframe the capability list as concrete actions (e.g. "Generate AI voiceovers, create images, compose music, animate talking heads, render with Remotion") rather than a single verb over nouns.

Dimension	Reasoning	Score
Specificity	Names the video domain plus several concrete capabilities ("AI voiceovers, image generation, music, talking heads, and Remotion rendering"), with only minor coverage gaps. Not a 5 because the capabilities are listed as nouns under a single verb rather than multiple distinct concrete actions.	4 / 5
Completeness	Has a clear "what" (create professional videos with the listed capabilities) but no "Use when..." clause or equivalent trigger guidance. Per the rubric guideline, a missing explicit trigger clause caps completeness at 3.	3 / 5
Trigger Term Quality	Includes natural terms users would say ("videos", "voiceovers", "image generation", "talking heads", "rendering") but misses common synonyms and file extensions like "explainer video" or ".mp4". Good coverage, a few natural terms missing.	4 / 5
Distinctiveness Conflict Risk	The named toolkit (claude-code-video-toolkit) and Remotion give it a clear, distinct niche with minimal conflict risk against unrelated skills. Not a 5 because it could still overlap marginally with general media-generation skills.	4 / 5
	Total	15 / 20 Passed

Validation

81%

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 — 13 / 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
referenced_paths_exist	Referenced path issues: 1 missing, 1 deeper-than-1-level	Warning

	Total	13 / 16 Passed

Repository: calesthio/OpenMontage
Path: .agents/skills/video-toolkit/SKILL.md
Commit: 1bab711

Reviewed: about 20 hours 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.