CtrlK
BlogDocsLog inGet started
Tessl Logo

narrator-ai-cli

AI 电影/短剧解说视频自动生成(AI 解说大师 CLI Skill)。当用户需要创建电影解说视频、短剧解说、影视二创、AI 配音旁白视频、film commentary、video narration、drama dubbing、movie narration 时触发。内置电影素材库、BGM、多语种配音、解说模板。通过 narrator-ai-cli 命令行实现:搜片→选模板→选 BGM→选配音→生成文案→合成视频的全流程自动化。CLI client for Narrator AI video narration API.

72

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

85%

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

An excellent, highly actionable and well-sequenced workflow with strong progressive disclosure. The main weakness is repetition of the same safety caveats across multiple sections, which inflates token cost without adding clarity.

Suggestions

Consolidate the task_order_num-vs-task_id and 'confirm before acting' warnings into one authoritative section and cross-reference it once instead of restating them in Agent Rules, both path flows, and Important Notes.

Fix or remove the broken README.md link in Prerequisites, or fold the install/setup detail into an existing reference file.

Consider trimming the duplicated path-asymmetry explanation by keeping the canonical version in Important Notes #4 and linking to it from the Fast/Standard path sections.

DimensionReasoningScore

Conciseness

High-value domain knowledge but notably repetitive — the task_order_num-vs-task_id caution recurs in Agent Rules, both path sections, and Important Notes #4, and the 'confirm before acting' rule is restated several times. Mostly efficient but could be tightened.

2 / 3

Actionability

Copy-paste-ready CLI commands ('narrator-ai-cli material list --json --page 1 --size 100', 'task create voice-clone --json -d …'), concrete JSON field paths ('.files[0].file_id', '.results.tasks[0].video_url'), and explicit pricing — fully executable guidance.

3 / 3

Workflow Clarity

Both paths are sequenced Step 0→1→2→3→4 with explicit checkpoints (poll until top-level .status=2, task verify, task budget) and feedback loops (surface errors, ask retry/switch/abort; ask the user rather than fabricate) for cost-incurring irreversible operations.

3 / 3

Progressive Disclosure

A clean Reference Index table links to four real, well-organized one-level-deep files (resources/workflows/magic-video/operations), with the body as overview-plus-pointers. The one missing target is README.md referenced in Prerequisites, a minor broken pointer that does not undermine the disclosure structure.

3 / 3

Total

11

/

12

Passed

Description

100%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description: concrete capability list, bilingual natural triggers, explicit use-when guidance, and a distinct niche. Slight redundancy in the trailing English restatement but it does not weaken any dimension.

DimensionReasoningScore

Specificity

Lists multiple concrete actions across a full pipeline — '搜片→选模板→选 BGM→选配音→生成文案→合成视频' plus built-in material library, BGM, multilingual dubbing, and narration templates.

3 / 3

Completeness

Explicit 'when' clause ('当用户需要…时触发') plus a clear 'what' (end-to-end auto narration video generation), answering both what the skill does and when to invoke it.

3 / 3

Trigger Term Quality

Bilingual natural trigger coverage: '电影解说视频、短剧解说、影视二创、AI 配音旁白视频、film commentary、video narration、drama dubbing、movie narration' — terms a user would naturally say.

3 / 3

Distinctiveness Conflict Risk

A clear niche (AI movie/short-drama narration via a specific CLI) with distinctive triggers unlikely to collide with other skills.

3 / 3

Total

12

/

12

Passed

Validation

75%

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

Validation12 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

frontmatter_unknown_keys

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

Warning

relative_links

Relative link issues: 1 missing

Warning

Total

12

/

16

Passed

Repository
NarratorAI-Studio/narrator-ai-cli-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.