CtrlK
BlogDocsLog inGet started
Tessl Logo

video-studio

Use when the user asks to create or edit videos end-to-end (script→video, auto-cut/jumpcut, captions/subtitles, polishing for Shorts/Reels/TikTok). Current implemented backend: local FFmpeg (probe/render/jumpcut/burn-subtitles/polish). Planned/optional backends: Remotion (motion graphics templates), VectCutAPI (CapCut/剪映 timeline editing), and video-audio-mcp (MCP tool wrapper) when available. Produces a finished video artifact (MP4 by default) from assets + copy + a design/storyboard plan.

59

Quality

68%

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 ./bundled/skills/video-studio/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

53%Weight 40%Scale 1-5

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 well-organized overview that correctly delegates bulk implementation to bundled files and provides concrete subcommand examples, but it is held back by a hardcoded machine-specific script path, repeated path padding, and the absence of explicit validation checkpoints in a batch/destructive video pipeline.

Suggestions

Replace the hardcoded 'C:\Users\羽裳\.codex\skills\video-studio\scripts\video_studio.py' path with a relative/parameterized form (e.g. a SCRIPT variable or 'python scripts/video_studio.py') so commands are copy-paste executable on any machine.

Add an explicit validation checkpoint between render and polish (e.g. probe/ffprobe the intermediate MP4 and verify it plays before polishing), with a fix→retry loop on failure, to satisfy the batch-operation feedback-loop requirement.

Trim the optional-backend prose in '背后能力(融合方案)' to a one-line note per backend and remove the repeated absolute-path padding to improve token efficiency.

DimensionReasoningScore

Conciseness

The body is mostly action-oriented and avoids explaining basic concepts, but it repeats a machine-specific absolute path verbatim five times and spends prose explaining optional backends Claude already understands, so it could be tightened.

3 / 5

Actionability

Commands include real subcommands and parameterized flags with example values, but the hardcoded user path (C:\Users\羽裳\...) and a placeholder spec path break copy-paste executability on any other machine, a meaningful gap beyond minor.

3 / 5

Workflow Clarity

The render→polish sequence and a pre-delivery quality-gate checklist are present, but there is no explicit inter-step validation checkpoint or validate→fix→retry feedback loop; per the rubric, batch/destructive workflows without validation are capped at 3.

3 / 5

Progressive Disclosure

Implementation bulk lives in scripts/video_studio.py and the spec example in references/sample_spec.json (both real and referenced in the body), giving a good one-level-deep split, though references are signaled via backtick paths rather than markdown links and no pointer to the script's full help is given.

4 / 5

Total

13

/

20

Passed

Description

83%Weight 40%Scale 1-5

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 strong: it explicitly covers both what the skill produces and when to use it, with concrete trigger phrases and platform synonyms. Specificity and distinctiveness are solid but not maximal due to a few high-level terms and minor overlap risk with general media skills.

DimensionReasoningScore

Specificity

Lists several concrete actions (probe/render/jumpcut/burn-subtitles/polish, auto-cut, captions/subtitles, polishing), though 'create or edit videos end-to-end' and 'script→video' remain somewhat high-level, leaving minor gaps versus a fully comprehensive action list.

4 / 5

Completeness

Opens with an explicit 'Use when the user asks to create or edit videos end-to-end (...)' trigger clause and states what it produces ('a finished video artifact (MP4 by default) from assets + copy + a design/storyboard plan'), clearly answering both what and when with concrete triggers.

5 / 5

Trigger Term Quality

Good natural-term coverage including platform synonyms ('Shorts/Reels/TikTok'), 'captions/subtitles', and 'auto-cut/jumpcut', but a few common phrasings (e.g. 'make a video', '剪辑') and extension-style terms (.mp4) are missing.

4 / 5

Distinctiveness Conflict Risk

The end-to-end video-pipeline niche with FFmpeg backend and Shorts/Reels/TikTok framing is mostly distinct, with only minor overlap risk against generic media skills.

4 / 5

Total

17

/

20

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

referenced_paths_exist

Referenced path issues: 4 missing

Warning

Total

15

/

16

Passed

Repository
foryourhealth111-pixel/Vibe-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.