CtrlK
BlogDocsLog inGet started
Tessl Logo

render-model-comparison-grid

Render a 'model comparison grid' video from a config — a fal-style "same prompt, N contenders" showcase — a dark real-DOM stage where per beat a monospace prompt fades in centered, docks to a small top strip, then a labeled 2-4 panel grid (static images OR muted video clips, mixable per cell) staggers in and holds for comparison, plus a minimal end card — frame-stepped via Playwright (video cells are frame-seeked deterministically) and encoded with FFmpeg. Deterministic assembly, FREE (cell media comes from create-image-fal / create-video-fal, music from create-music-elevenlabs), text stays pixel-crisp. Use for the model-comparison-grid format.

67

Quality

84%

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

78%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.

A lean, well-structured body for a simple single-purpose skill, with concrete commands, real bundle references, and explicit determinism constraints. The main gaps are the missing music-assembly step after master-silent.mp4 and the dense, semi-executable Run section.

Suggestions

Add the final assembly step: an ffmpeg command muxing the create-music-elevenlabs track onto master-silent.mp4, since the described output includes a music bed but the workflow stops at the silent master.

Reformat ## Run as a short numbered sequence with exact invocations (e.g. 'python scripts/build_composition.py ...') so the commands are copy-paste ready.

State what happens when the build validation fails (error message behavior and the fix loop: re-point cell paths / correct column count, then re-run).

DimensionReasoningScore

Conciseness

The body assumes competence (no explanations of what Playwright/FFmpeg are) and every paragraph carries non-derivable spec detail (beat timing, column rules, decode constraints). Not 5: the ## Run line crams the command, cost note, and a long parenthetical about the example config into one dense paragraph that could be tightened.

4 / 5

Actionability

Concrete commands are given: 'build_composition.py --config config.json --output hyperframe.html ; render_seekable_hyperframe.py hyperframe.html master-silent.mp4 <duration> --fps 30 --width 1280 --height 720', plus pointers to the shipped example config and schema. Not 5: the commands are not fully copy-paste ready (bare script names, no interpreter invocation, '<duration>' placeholder) and no worked config snippet is shown inline.

4 / 5

Workflow Clarity

A clear build -> render sequence exists and the build step validates inputs ('validates every cell path and the column count (2-4)'), with the renderer awaiting mediaReady()/renderAt(t). Not 5: there is no guidance for what happens when validation fails, and the pipeline ends at 'master-silent.mp4' — the music bed (a stated part of the output) has no assembly/mux step.

4 / 5

Progressive Disclosure

The body is under 50 lines, well-organized (overview, ## Run, ## Contract), and its references are real one-level-deep bundle files (scripts/build_composition.py, scripts/config.example.json, scripts/render_seekable_hyperframe.py — all present), with the config schema pushed to the top of build_composition.py. Per the simple-skill note, this earns full marks.

5 / 5

Total

17

/

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.

A very specific, distinctive description written in third person with explicit what/when structure. Its main weakness is the trigger layer: the 'Use for...' clause points only at the format's own name and natural synonyms users might actually say are missing.

Suggestions

Expand the trigger clause beyond the format name, e.g. 'Use when the user asks for a side-by-side AI model comparison video, a same-prompt model showcase, or the model-comparison-grid format.'

Add natural synonyms such as 'AI model comparison', 'side-by-side comparison video', or 'model showcase' to improve keyword coverage.

Trim choreography detail already in the body (e.g., the full beat timing) to reduce frontmatter token cost without losing triggers.

DimensionReasoningScore

Specificity

Quotes: 'Render a model comparison grid video from a config', 'a monospace prompt fades in centered, docks to a small top strip', 'a labeled 2-4 panel grid... staggers in and holds', 'frame-stepped via Playwright... and encoded with FFmpeg'. Multiple concrete actions with comprehensive coverage of the render pipeline, visual choreography, media types, and tooling. Not 4: coverage is comprehensive rather than having minor gaps.

5 / 5

Completeness

'What' is explicit ('Render a model comparison grid video from a config...') and 'when' is present ('Use for the model-comparison-grid format'). Not 5: the 'when' clause is circular — it restates the skill's own format name rather than giving concrete trigger phrases; not 3: the 'when' clause is explicitly present.

4 / 5

Trigger Term Quality

Quotes: 'model comparison grid', 'video', 'same prompt, N contenders', 'comparison'. Good natural keyword coverage, but common user phrasings like 'AI model comparison', 'side-by-side model showcase', or 'model showcase video' are absent. Not 5: a few natural terms/synonyms are missing; not 3: the core keywords are relevant and natural.

4 / 5

Distinctiveness Conflict Risk

A highly niche rendering capability ('model comparison grid' video, Playwright frame-stepping, 2-4 panel grid showcase) with distinct triggers and minimal overlap with other skills.

5 / 5

Total

18

/

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.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

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

Warning

Total

15

/

16

Passed

Repository
gooseworks-ai/goose-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.