CtrlK
BlogDocsLog inGet started
Tessl Logo

video-editing

AI-assisted video editing workflows for cutting, structuring, and augmenting real footage. Covers the full pipeline from raw capture through FFmpeg, Remotion, ElevenLabs, fal.ai, and final polish in Descript or CapCut. Use when the user wants to edit video, cut footage, create vlogs, or build video content.

68

Quality

82%

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

65%

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

The body is highly actionable with complete code across every pipeline layer and a clear layered sequence, but it is held back by opinion padding, missing validation checkpoints on batch operations, and an all-inline structure that would benefit from splitting into reference files.

Suggestions

Add validation/verification steps after batch operations (e.g., probe segment duration with ffprobe, verify concat count matches cuts.txt, fail fast on missing files) to lift workflow clarity.

Move the full Remotion composition, ElevenLabs/fal.ai generation scripts, and social-reframing/scene-detection recipes into separate reference files linked from a concise overview to improve progressive disclosure.

Trim thesis prose ("Core Thesis", "The value is compression", "This is where taste lives") and tool-commentary to keep only guidance that Claude could not infer.

DimensionReasoningScore

Conciseness

Mostly efficient with executable code throughout, but padded with thesis prose ("The value is not generation. The value is compression.", "This is where taste lives.", "FFmpeg handles the boring but critical work") that explains stance rather than instructs, fitting the mostly-efficient-but-could-be-tightened anchor.

2 / 3

Actionability

Provides copy-paste-ready, executable FFmpeg commands, a complete Remotion TSX composition, and working ElevenLabs/fal.ai code snippets rather than pseudocode, matching the fully-executable anchor.

3 / 3

Workflow Clarity

The six-layer pipeline is clearly sequenced, but batch and destructive operations (batch cut from EDL, concatenation) lack any validation or verification checkpoints, capping clarity at 2 per the batch-operations rule.

2 / 3

Progressive Disclosure

The single ~310-line file is well-sectioned but monolithic; detailed material that could live in separate references (full Remotion composition, ElevenLabs script, reframing/scene-detection recipes) is inline, matching the some-structure-but-could-be-split anchor.

2 / 3

Total

9

/

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.

The description is strong: it states concrete actions, names the toolchain, and provides explicit natural-language triggers covering both what and when. It uses third person and avoids fluff.

DimensionReasoningScore

Specificity

Lists multiple concrete actions ("cutting, structuring, and augmenting real footage") and names the specific tools in the pipeline (FFmpeg, Remotion, ElevenLabs, fal.ai, Descript, CapCut), matching the score-3 anchor for multiple specific concrete actions.

3 / 3

Completeness

Clearly answers what it does ("AI-assisted video editing workflows for cutting, structuring, and augmenting real footage") and when to use it with an explicit "Use when the user wants to..." clause, satisfying both halves.

3 / 3

Trigger Term Quality

Explicit trigger phrases users would naturally say ("edit video", "cut footage", "create vlogs", "build video content") give good coverage of natural terms rather than jargon.

3 / 3

Distinctiveness Conflict Risk

The "real footage" framing and editing-oriented triggers (cut, structure, vlog) carve a clear niche distinct from generation skills, making conflict with fal-ai-media or videodb unlikely on the stated triggers.

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

metadata_version

'metadata.version' is missing

Warning

Total

15

/

16

Passed

Repository
affaan-m/ECC
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.