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。

79

Quality

100%

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

100%

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

A tightly written orchestration skill: lean, executable, with an explicitly sequenced multi-stage workflow, fail-closed validation gates, and well-signaled one-level-deep references that match the bundle. It assumes Claude's competence and adds only domain-specific protocol.

DimensionReasoningScore

Conciseness

The body is information-dense and operational throughout — numbered stages, bash commands, validation gates, and fail-closed rules — with no teaching of concepts Claude already knows; every line earns its place despite the ~190-line length.

3 / 3

Actionability

Provides fully executable bash commands with concrete script paths, flags, and --json outputs (e.g. 'node "$VC" artifact put "$jobDir" --type visual-plan ... --json'), plus specific completion criteria that are copy-paste ready given the workflow variables.

3 / 3

Workflow Clarity

A clearly sequenced 0→6 pipeline (preflight → readback → proposal → CAS → review binding → confirmation → execution → verification) with explicit validation checkpoints and feedback loops (revision mismatch stops and reconciles; return_finish_* re-enters review without advancing state).

3 / 3

Progressive Disclosure

SKILL.md is an overview that defers detail to well-signaled one-level-deep references — storyboard-rules.md, animation-rules.md, animation-module-contract.md, timeline-and-export.md (all present in ./references/) — keeping the main body focused on orchestration.

3 / 3

Total

12

/

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 dense, third-person description that states concrete capabilities, provides explicit user-spoken and card-action triggers, and carves out a clear niche with exclusions. It fully answers both 'what' and 'when' with minimal padding.

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' — naming the specific deliverables and stages rather than vague language.

3 / 3

Completeness

Explicitly answers both what (produce final.mp4 via storyboard/animation/timeline) and when ('用户说...时使用' and card action triggers), with an explicit '不要用于...' exclusion clause.

3 / 3

Trigger Term Quality

Covers natural Chinese trigger phrases users would say ('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 explicit card-return action codes, giving broad natural coverage.

3 / 3

Distinctiveness Conflict Risk

Clear niche (口播成片 continuation on existing projectId) with distinct triggers and an exclusion list ('不要用于原始删词、单独安装...普通 HyperFrames 视频'), making wrong-skill triggering 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.