cli-hub-matrix-video-creation

Capability-based multi-tool matrix for video production. Agents pick providers (CLI-Anything harnesses, public CLIs, Python libs, native binaries, cloud APIs) per capability rather than marching through fixed stages, including storyboard planning, story/audio direction, source triage, internet video/music search/download, capture/generation, analysis, sound design, high-end caption design, NLE/render doctor investigation, review, and packaging.

Quality

67%

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

Fix and improve this skill with Tessl

tessl review fix ./cli-hub-matrix/video-creation/SKILL.md

Quality

Content

71%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 a well-structured, actionable capability matrix with strong progressive disclosure and real validation/feedback loops, but its length and repeated cross-cutting rules leave some conciseness on the table.

Suggestions

Consolidate the repeated output-language rule and HyperFrames hard gate into a single authoritative statement and cross-reference it from sections instead of restating each time.

Move the long provider tables' less-common columns or per-provider operational notes into the relevant reference files to shrink the inline router.

Add a one-paragraph quickstart at the top showing the minimal end-to-end sequence (preflight → creative_direction.md → acquire → assemble → quality.review → package.encode) before the full capability catalog.

Dimension	Reasoning	Score
Conciseness	The body is dense and operational rather than padded with concepts Claude already knows, but it is very long (~530 lines) and repeats several rules across sections (the output-language rule, the HyperFrames hard gate, the source-audio/procedural-audio gates), which could be tightened.	3 / 5
Actionability	Provides many concrete, executable commands — the preflight bash block, yt-dlp/ffmpeg download and conversion commands, `cli-hub matrix install/info/preflight`, `scripts/video_doctor.py` subcommands, and `npx skills add` install strings — with only minor gaps where guidance stays at the level of discipline rules.	4 / 5
Workflow Clarity	Ordering is conveyed through hard gates and agent guidance ('run preflight once', 'start with creative_direction.md', 'video.search before video.download', 'transcribe after the final cut') plus an explicit quality.review investigation pass with validate/inspect feedback loops; validation is present so the destructive/batch cap does not apply, though the overall sequence is capability-based rather than a single fixed pipeline.	4 / 5
Progressive Disclosure	Detailed material is split into one-level-deep, well-signaled references that all exist as real files (references/story-structure-audio.md, captions.md, source-triage.md, nle-shotcut-kdenlive.md, sound-design.md, art-direction-review.md, render-doctor.md, scripts/video_doctor.py) and a dedicated 'Reference modules, external skills, and tool sources' table with Use-when and source columns.	5 / 5
	Total	16 / 20 Passed

Description

63%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 is specific and comprehensive about capabilities but leans heavily on internal jargon and omits an explicit 'Use when' trigger clause, leaving the 'when to use it' guidance only weakly implied.

Suggestions

Add an explicit 'Use when ...' sentence listing natural user triggers such as 'make a video', 'edit footage', 'add subtitles/captions', 'download B-roll or music', or 'render and review a final video'.

Replace internal jargon ('CLI-Anything harnesses', 'capability-based multi-tool matrix', 'marching through fixed stages') with user-facing phrasing so the description reads as something a user would actually say.

Include common synonyms and file extensions users mention (e.g., 'subtitles/SRT', 'B-roll', 'MP4', 'YouTube/Bilibili clips') to broaden natural trigger coverage.

Dimension	Reasoning	Score
Specificity	Lists many concrete actions across the domain — 'storyboard planning, story/audio direction, source triage, internet video/music search/download, capture/generation, analysis, sound design, high-end caption design, NLE/render doctor investigation, review, and packaging' — comprehensive coverage rather than vague language.	5 / 5
Completeness	Clearly states what the skill does (a capability-based provider matrix for video production) but has no 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at 3 per the rubric.	3 / 5
Trigger Term Quality	Contains some natural terms ('video production', 'video/music search/download', 'storyboard', 'caption') but is dominated by internal jargon ('CLI-Anything harnesses', 'capability-based multi-tool matrix', 'marching through fixed stages') and misses common user phrases like 'make a video', 'edit video', 'subtitles', or 'B-roll'.	3 / 5
Distinctiveness Conflict Risk	The capability-matrix/router framing and 'cli-hub-matrix-video-creation' niche are clearly distinct from generic editing skills, though there is minor overlap risk with the many sub-skills it routes to (storyboard-creation, advanced-video-downloader, etc.).	4 / 5
	Total	15 / 20 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
skill_md_line_count	SKILL.md is long (537 lines); consider splitting into references/ and linking	Warning
relative_links	Relative link issues: 1 suspicious	Warning

	Total	14 / 16 Passed

Repository: HKUDS/CLI-Anything
Path: cli-hub-matrix/video-creation/SKILL.md
Commit: 34f5195

Reviewed: 1 day 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.