video-creation-collaborator

影品智创多智能体协同视频创作管理工具,提供11个智能体结构化分工、5阶段协同流程、质量管控标准与数据反馈机制,解决生图失真、视频合成瑕疵等问题,确保输出统一可控

Quality

50%

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 ./skills/video-creation-collaborator/video-creation-collaborator/SKILL.md

Quality

Content

41%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 skill lays out a clear, well-sequenced multi-agent pipeline with quality gates, but it is heavily verbose and its command examples do not match the actual bundled script interfaces (and reference several non-existent files), which materially hurts actionability and conciseness.

Suggestions

Reconcile every command with the real script CLI: image_generator.py uses --script/--output-dir/--resolution/--style (not --storyboard/--output); audio_generator.py takes only --narration/--output-dir/--voice-style (no --mode/--text/--voice/--output); remove --validate_only from the video_compositor example since that flag does not exist.

Delete or create the referenced-but-missing files (scripts/music_generator.py, scripts/audio_quality_checker.py, references/data-analysis.md) and the matching resource-index entries to avoid broken navigation.

Move the per-agent input/output/quality spec tables and the inline JSON heredocs into the existing references/ files (agent-prompts.md, asset-specifications.md), leaving SKILL.md as a lean overview — this would simultaneously improve conciseness and progressive_disclosure.

Dimension	Reasoning	Score
Conciseness	The 495-line body extensively restates agent responsibilities, inputs/outputs and quality standards already implied by the domain, repeats the quality-detection command blocks in two near-identical sections, and includes large inline JSON heredocs; it is noticeably verbose with several padded/over-explained sections rather than just minor trimmable bits.	2 / 5
Actionability	Commands look executable but several are factually wrong against the bundled scripts: image_generator.py takes --script (not --storyboard), audio_generator.py has no --mode/--text/--voice/--output flags, and referenced files music_generator.py, audio_quality_checker.py and references/data-analysis.md do not exist — so the copy-paste guidance is high-level/hint-level and missing the specific steps that actually run.	2 / 5
Workflow Clarity	The 5-phase / 11-agent pipeline is clearly sequenced with explicit trigger nodes and per-agent next-step handoffs, and validation checkpoints are present (image/video quality checks gate downstream steps, defects are rejected and redrawn); only minor gaps (no explicit re-validate-after-fix loop for the composition step) keep it from a 5.	4 / 5
Progressive Disclosure	Structure exists with a resource index pointing to references/ and assets/, but substantial detail that belongs in bundled files is inlined in SKILL.md (full agent I/O specs, repeated JSON configs), and the index lists three missing files (music_generator.py, audio_quality_checker.py, references/data-analysis.md) — references present but not cleanly signaled and content that should be separate is inline.	3 / 5
	Total	11 / 20 Passed

Description

58%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 conveys concrete capabilities and a distinctive niche clearly, but it lacks any explicit trigger/when-to-use guidance and underuses natural user-spoken phrasing, which cap completeness and trigger quality at the midpoint.

Suggestions

Add an explicit 'Use when ...' / '当用户需要...时调用' trigger clause naming natural user phrases like '短视频制作','AI视频生成','多智能体协同创作' to lift completeness and trigger_term_quality.

Include common synonyms/file cues (e.g. MP4, 分镜, 旁白配音, 字幕) so natural keyword coverage reaches comprehensive.

Consider a 5-level score for specificity by enumerating the concrete actions (生成图片/音频/字幕/视频, 质量检测, 数据迭代) instead of grouping them abstractly.

Dimension	Reasoning	Score
Specificity	Lists several concrete capabilities — '11个智能体结构化分工', '5阶段协同流程', '质量管控标准与数据反馈机制' — plus named problems ('生图失真','视频合成瑕疵'), which is several specific actions with only minor coverage gaps; not a fully exhaustive action list so not a 5.	4 / 5
Completeness	The 'what' is clearly stated (multi-agent collaborative video creation tool with structured division and quality control), but there is no explicit 'when to use' / 'Use when...' trigger clause at all, which the rubric caps at 3.	3 / 5
Trigger Term Quality	Contains relevant domain keywords ('视频创作','多智能体协同','生图失真','视频合成瑕疵') but omits the natural phrases a user would actually say (e.g. '短视频制作','AI视频生成') and has no file-extension or synonym coverage, so it sits at 'some relevant keywords, missing common variations'.	3 / 5
Distinctiveness Conflict Risk	The niche is fairly specific (multi-agent collaborative short-video creation with quality feedback loops) and unlikely to collide with unrelated skills; only minor overlap risk with generic video-generation skills keeps it from a 5.	4 / 5
	Total	14 / 20 Passed

Validation

75%

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 — 12 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (507 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 2 missing, 2 deeper-than-1-level	Warning
referenced_paths_exist	Referenced path issues: 6 missing, 4 deeper-than-1-level	Warning

	Total	12 / 16 Passed

Repository: anbeime/skill
Path: skills/video-creation-collaborator/video-creation-collaborator/SKILL.md
Commit: 7054767

Reviewed: 2 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.