CtrlK
BlogDocsLog inGet started
Tessl Logo

chengfeng-finish-talking-head

把口播基础素材制作成完整成片:生成并审核分镜、动画和总时间线,随后导出与验收 final.mp4。用户说口播成片、口播分镜、口播动画、导出口播视频、继续口播成片,或确认卡回传 action=continue_finish_storyboard / continue_finish_animation / continue_finish_timeline / return_finish_storyboard / return_finish_animation / return_finish_timeline 时使用。不要用于原始删词、单独安装、单独打开工作台或普通 HyperFrames 视频。

76

Quality

96%

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

SKILL.md
Quality
Evals
Security

Quality

Content

92%Weight 40%Scale 1-3

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 tightly structured, highly executable orchestration workflow with concrete commands, explicit validation checkpoints, and well-organized one-level references. Its only minor weakness is a few dense prose passages that could be trimmed for token efficiency.

DimensionReasoningScore

Conciseness

Mostly lean and free of concept padding, but a few prose passages (e.g. repeated ensure-running rationale and multi-clause stop rules) could be tightened; it earns slightly below 3 rather than 2 because it does not explain concepts Claude already knows.

2.5 / 3

Actionability

Provides fully executable bash with concrete env-var setup, flag-specific CLI calls (e.g. 'render run --expected-revision ... --confirmed --json'), and copy-paste-ready config JSON, matching the level-3 anchor.

3 / 3

Workflow Clarity

Uses a fixed stage sequence (preflight -> readback -> proposal -> CAS -> review binding -> confirm -> execute -> verify) with explicit validation checkpoints (artifact state checks, revision binding, verification.json passed=true, evidence-tier reporting) and feedback loops (revision_conflict -> re-read; fail-closed stops).

3 / 3

Progressive Disclosure

Body is an overview that delegates detail to one-level-deep, clearly signaled references (storyboard-rules.md, animation-rules.md, animation-module-contract.md, timeline-and-export.md), all verified to exist as real files in ./references/, with well-organized sections and easy navigation.

3 / 3

Total

11.5

/

12

Passed

Description

100%Weight 40%Scale 1-3

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 concise yet specific: it names concrete actions, lists natural trigger terms plus card-action signals, and explicitly bounds when to (and not to) use the skill. It cleanly distinguishes itself from sibling skills via clear exclusions.

DimensionReasoningScore

Specificity

Lists multiple concrete actions ('生成并审核分镜、动画和总时间线,随后导出与验收 final.mp4'), matching the level-3 anchor that names several specific operations rather than vague language.

3 / 3

Completeness

Explicitly answers both what (produce finished cut) and when ('用户说...时使用') with concrete trigger guidance, satisfying the level-3 anchor rather than capping at 2.

3 / 3

Trigger Term Quality

Provides natural user-facing terms ('口播成片、口播分镜、口播动画、导出口播视频、继续口播成片') plus card-action triggers, giving broad coverage of phrases users would actually say.

3 / 3

Distinctiveness Conflict Risk

Has a clear niche with explicit exclusions ('不要用于原始删词、单独安装、单独打开工作台或普通 HyperFrames 视频') and distinct triggers, making wrong-skill activation unlikely.

3 / 3

Total

12

/

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

relative_links

Relative link issues: 1 missing, 2 suspicious

Warning

Total

15

/

16

Passed

Repository
Agentchengfeng/chengfeng-videocut-skills
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.