CtrlK
BlogDocsLog inGet started
Tessl Logo

historical-science-video-prod

自动化生成历史科学类3分钟科普短视频的全流程素材包,包含口播文案、分镜脚本、Veo2提示词、人物形象规范等,适配即梦平台视频生成。

62

Quality

73%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/historical-science-video-prod/historical-science-video-prod/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

65%

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

The body is actionable with an executable command and a reasonable step sequence, plus well-signaled references for scripts and references. It loses points for mild redundancy, a missing output-validation checkpoint, and orphaned asset templates not linked from the overview.

Suggestions

Add a verification step after generation (e.g. check the four expected output files exist and the storyboard meets the 3-minute / 4–6s-per-shot constraint) before declaring success.

Link the assets/output-templates/ templates in the 资源索引 with '何时读取' triggers so all bundle files are navigable from SKILL.md.

De-duplicate the 使用示例 command against 操作步骤, or collapse 任务目标 since it restates the description.

DimensionReasoningScore

Conciseness

The body is largely lean and free of basic-concept padding, but the 任务目标 section restates the description and 使用示例 repeats the same command already given in 操作步骤, so it could be tightened rather than earning the fully-lean level 3.

2 / 3

Actionability

It provides a complete, copy-paste-ready command — 'python scripts/generate_video_materials.py --theme … --era … --core_conclusion … --output_dir …' — with concrete parameters and named output files, matching the 'fully executable, copy-paste ready' anchor.

3 / 3

Workflow Clarity

Steps are sequenced (准备输入信息 → 执行生成脚本 → 查看输出素材) with optional branches, but there is no validation/verification checkpoint confirming the generated outputs are correct and complete, so it sits at the 'sequence present but checkpoints missing' level 2 rather than 3.

2 / 3

Progressive Disclosure

The body gives a clear overview and well-signaled one-level references with explicit '何时读取' triggers for scripts/ and references/, but the three template files under assets/output-templates/ are never referenced from the body, leaving a navigation gap that keeps it below the 'easy navigation' level 3.

2 / 3

Total

9

/

12

Passed

Description

82%

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, third-person, and well-differentiated, naming concrete deliverables and natural trigger terms. Its main weakness is the absence of an explicit 'Use when…' clause, which caps completeness at 2.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user wants to create historical or popular-science short videos, mentions Veo2 or the 即梦 platform, or asks for a narration/storyboard/Veo2-prompt material package.'

Reduce jargon framing like '全流程素材包' in favor of the concrete outputs a user would request by name.

DimensionReasoningScore

Specificity

The description enumerates multiple concrete deliverables — '口播文案、分镜脚本、Veo2提示词、人物形象规范' — plus the auto-generate action ('自动化生成...全流程素材包'), matching the 'lists multiple specific concrete actions' anchor rather than the domain-only level 2.

3 / 3

Completeness

It clearly answers 'what' (auto-generate a full material package with the listed outputs) but offers no 'Use when…' or equivalent explicit trigger guidance, so per the rubric guideline completeness is capped at 2 rather than reaching the explicit-when level 3.

2 / 3

Trigger Term Quality

It contains natural terms a user would actually say for this need — '历史科学类科普短视频', '3分钟', 'Veo2', '即梦平台' — giving good coverage of common phrasings rather than only jargon or a single generic term.

3 / 3

Distinctiveness Conflict Risk

The niche is sharply defined — history-science popular-science shorts for the 即梦 platform via Veo2 — making it unlikely to trigger for unrelated skills, which fits the 'clear niche with distinct triggers' anchor rather than the overlapping level 2.

3 / 3

Total

11

/

12

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
anbeime/skill
Reviewed

Table of Contents

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.