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.

70

Quality

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Quality

Content

72%

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 executable FFmpeg, Remotion, and Python examples organized into a clear six-layer pipeline, and its structure and references are well-organized. It loses points on conciseness due to editorial commentary and is capped on workflow clarity because batch and destructive operations lack validation checkpoints.

Suggestions

Add validation/verification checkpoints to batch and destructive steps: e.g., check the segment files exist and are non-empty after the cuts.txt loop, and verify concat succeeded before downstream use.

Trim the editorial commentary (e.g., 'This is where taste lives', 'This layer is about structure, not final creative taste') to tighten conciseness while keeping the actionable content.

Confirm the `ffmpeg ... -c copy` cut commands note that stream-copy cuts may be imprecise on non-keyframe boundaries, since that affects batch output correctness.

DimensionReasoningScore

Conciseness

Code and commands are lean and skip explaining what FFmpeg/Remotion is, but editorial commentary like 'AI video editing is useful when you stop asking it to create the whole video', 'This layer is about structure, not final creative taste', and 'This is where taste lives' adds tokens that could be trimmed. Not a 3 because of this padded framing; not a 1 because it does not explain concepts Claude already knows.

2 / 3

Actionability

Provides fully executable FFmpeg commands, a complete copy-paste Remotion TSX composition, and runnable Python for ElevenLabs and VideoDB calls. Matches the 'fully executable code/commands, copy-paste ready' anchor. Not a 2 because there is no pseudocode or missing key details.

3 / 3

Workflow Clarity

The six layers are clearly sequenced (Capture → Organization → Cuts → Composition → Generated Assets → Final Polish), but batch/destructive operations like the cuts.txt loop and concat/reframe commands have no validation or verification checkpoints. Per the rubric, missing validation in destructive/batch workflows caps this at 2. Not a 3 because checkpoints are absent; not a 1 because the sequence is explicit.

2 / 3

Progressive Disclosure

A single-file skill with well-organized sections and one-level-deep references to related skills (fal-ai-media, videodb, content-engine), all clearly signaled. Navigation is easy and references are not nested. Not a 2 because the structure is clear and the cross-references are shallow.

3 / 3

Total

10

/

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 across all four dimensions: it specifies concrete actions and tools, includes natural trigger terms, answers both what and when with an explicit 'Use when' clause, and occupies a distinct real-footage-editing niche. It uses third-person voice throughout with no over-claims.

DimensionReasoningScore

Specificity

Names multiple concrete actions ('cutting, structuring, and augmenting real footage') and a specific toolchain (FFmpeg, Remotion, ElevenLabs, fal.ai, Descript, CapCut), matching the 'lists multiple specific concrete actions' anchor. Not a 2 because it goes well beyond naming a domain and partial actions.

3 / 3

Completeness

Explicitly answers both what ('cutting, structuring, and augmenting real footage' through the named pipeline) and when ('Use when the user wants to edit video, cut footage, create vlogs, or build video content'). The explicit 'Use when...' clause with concrete triggers matches the top anchor; not capped at 2 because the when is explicit.

3 / 3

Trigger Term Quality

Includes natural phrases a user would say ('edit video', 'cut footage', 'create vlogs', 'build video content'), giving good coverage of likely trigger language. Not a 2 because the triggers are genuine user phrasing rather than only generic terms, though a few variations ('trim', 'shorts') are absent.

3 / 3

Distinctiveness Conflict Risk

The 'real footage' editing niche plus a named, ordered toolchain distinguishes it from pure-generation skills (it explicitly cross-references fal-ai-media), giving a clear niche unlikely to trigger the wrong skill. Not a 2 because the scope is sharply bounded rather than broadly overlapping.

3 / 3

Total

12

/

12

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

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.