CtrlK
BlogDocsLog inGet started
Tessl Logo

video-forge

视频制作全链路:素材入库 → 剧本冻结 → 全局配音 → 对齐 → 渲染 → 审查 → 交付。 Use when: 做视频、做 showcase、做教程视频、录屏剪辑、video review、节奏审查。 Not for: 纯代码开发(用 worktree/tdd)、纯文档写作(直接写)、PPT(用 ppt-forge)。 Output: schema 驱动的视频成片 + 多猫审查通过 + 可发布。

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.

A highly actionable, well-sequenced pipeline skill with concrete commands, validation gates, and feedback loops. Its one real gap is progressive disclosure: the repeatedly referenced refs/continuity.md is missing from the bundle.

Suggestions

Bundle refs/continuity.md — it is referenced three times (continuity check, seam-review degradation path, 15s failure cases) but no refs/ directory exists, so the links lead nowhere.

Consider moving the long rich-block JSON examples and/or the technical-stack table into a separate reference file so SKILL.md stays a lean overview.

Replace the bare F138 feature link (../../docs/features/F138-video-studio.md) with a short inline summary so the skill is self-contained when that doc is unavailable.

DimensionReasoningScore

Conciseness

The body is dense operational content — tables, named tools, and concrete thresholds (CRF 23, ≥0.7x, >200ms) — that assumes Claude's competence and avoids explaining generic concepts Claude already knows.

3 / 3

Actionability

Provides executable ffmpeg commands, copy-paste rich-block JSON with exact mimeType values, a retiming priority table with specific ranges, and named toolchains (CosyVoice, Qwen3-ForcedAligner, Remotion).

3 / 3

Workflow Clarity

A clearly sequenced A→G→R scene route with explicit review gates (F1/F2/F3), a 5-question Seam Review Gate that forces a degradation path on failure, and a Patch Loop feedback channel.

3 / 3

Progressive Disclosure

Sections are well organized and references to refs/continuity.md are clearly signaled one level deep, but that file is not bundled — the links resolve to nothing, breaking navigation.

2 / 3

Total

11

/

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.

A strong, third-person description that states concrete capabilities, gives natural trigger terms, and cleanly separates its scope from neighboring skills. It answers what, when, and not-for without padding.

DimensionReasoningScore

Specificity

Lists a concrete multi-step pipeline — "素材入库 → 剧本冻结 → 全局配音 → 对齐 → 渲染 → 审查 → 交付" — naming several specific actions rather than vague language.

3 / 3

Completeness

Explicitly answers both what (the full production pipeline) and when (an explicit "Use when" clause), and adds "Not for"/"Output" for extra clarity.

3 / 3

Trigger Term Quality

"Use when: 做视频、做 showcase、做教程视频、录屏剪辑、video review、节奏审查" covers natural phrasings a user would actually say, in both Chinese and English.

3 / 3

Distinctiveness Conflict Risk

A clear video-production niche with distinct triggers and an explicit "Not for" block redirecting code→worktree/tdd, docs→direct write, PPT→ppt-forge, minimizing conflict risk.

3 / 3

Total

12

/

12

Passed

Validation

87%

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

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

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

Warning

relative_links

Relative link issues: 3 missing, 1 suspicious

Warning

Total

14

/

16

Passed

Repository
zts212653/clowder-ai
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.