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

76%

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

85%

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

The content is highly actionable and workflow-rich, with executable commands, explicit validation feedback loops, and well-structured one-level-deep references to real bundle files. The main weakness is conciseness, as the document is long and repeats agent/quality detail that could live in references.

Suggestions

Move the per-agent responsibility/input/output/quality-standard blocks (steps 1-11) into references/agent-prompts.md and keep only the stage overview and trigger handoffs inline to reduce repetition.

Consolidate the duplicated quality-detection sections ('质量检测工具使用' and '质量检测流程') into a single section pointing to references/quality-standards.md.

Trim the verbose 使用示例 walkthroughs to one concise end-to-end example, leaving detailed scenarios to the references.

Dimension	Reasoning	Score
Conciseness	The body is highly detailed and mostly free of explanatory fluff about concepts Claude already knows, but at ~440 lines it is lengthy and repeats the 5-stage agent descriptions, quality dimensions, and detection steps across multiple sections, which could be tightened or offloaded to references.	2 / 3
Actionability	Provides fully executable bash/python commands with concrete flags, file paths, and JSON config examples (e.g., video_compositor.py --config ... --validate_only, image_quality_checker.py --check_limb_anomaly) that are copy-paste ready and backed by real scripts in ./scripts/.	3 / 3
Workflow Clarity	The 5-stage, 11-agent process is explicitly sequenced with trigger nodes, '下一级触发' handoffs, and explicit validation checkpoints (前置质检/强制质检,不合格驳回) plus a validate->fix->retry loop for batch and destructive image/video operations.	3 / 3
Progressive Disclosure	SKILL.md is an overview that signals one-level-deep references to real files (references/agent-prompts.md, quality-standards.md, asset-specifications.md, assets/templates/) and a resource index, with content appropriately split; all referenced paths exist in the bundle.	3 / 3
	Total	11 / 12 Passed

Description

67%

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 distinct, naming concrete capabilities and a clear niche. It falls short on completeness and trigger term quality because it omits an explicit 'Use when...' clause and leans on domain jargon rather than natural user phrasing.

Suggestions

Add an explicit 'Use when...' clause in third person (e.g., 'Use when orchestrating multi-agent short-video production or when the user needs standardized collaborative video workflows').

Include more natural, user-facing trigger terms alongside the technical ones (e.g., '短视频制作', '多智能体协作', '视频生成') so users' everyday phrasing matches.

Ensure the description stays in third person and keeps the 'when' guidance explicit rather than implied through problem framing.

Dimension	Reasoning	Score
Specificity	Lists multiple 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', and specific problems solved ('生图失真', '视频合成瑕疵').	3 / 3
Completeness	Clearly states what the tool does, but the 'when' trigger is only implied via the problem framing ('解决...问题,确保输出统一可控'); there is no explicit 'Use when...' clause, which caps completeness at 2.	2 / 3
Trigger Term Quality	Contains relevant terms ('视频创作', '多智能体协同', '生图失真') but is domain-jargon-heavy and lacks the common natural variations a user might say; no 'Use when...' phrasing with everyday keywords.	2 / 3
Distinctiveness Conflict Risk	Targets a clear niche (multi-agent collaborative short-video creation with quality control) with distinct triggers unlikely to overlap with generic document or code skills.	3 / 3
	Total	10 / 12 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: f595e96

Reviewed: about 12 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.