CtrlK
BlogDocsLog inGet started
Tessl Logo

render-ig-live-gallery

Render an 'Instagram-Live social-proof gallery' video from a config — ~5 real brand product stills each framed as an Instagram-LIVE card (IG gradient-ring avatar, username, verified check, red LIVE badge, viewer count, close X, a short claim-free live-comment feed, an empty 'Add a comment…' bar, and reaction hearts floating up the right edge), with a brand-approved benefit sentence building one phrase per slide and a clean logo endcard, rendered deterministically with PIL frames plus FFmpeg — FREE (the music bed comes from create-music-elevenlabs), products and wordmark stay crisp. Use for the ig-live-gallery format.

65

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

75%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 compact, well-structured instruction body with concrete run commands, a complete config schema, and unusually specific craft rules that encode real rendering gotchas. The main gaps are the missing config.example.json it advertises and the lack of a concrete mux/QC command plus an explicit error-recovery loop in the output pipeline.

Suggestions

Ship the referenced config.example.json (the Glossier worked example) or fix the path so the body's promise of a full worked config resolves to a real file.

Replace 'Generate + mux the create-music-elevenlabs bed with a short fade in/out + loudnorm' with the actual copy-paste ffmpeg command(s) including the -map 0:v:0 -map 1:a:0 and fade arguments.

Add an explicit feedback loop after the stills quick-check, e.g. 'if a product is off-center or the ring clips, adjust slides[].image or phrase length and re-render stills before building the full master'.

DimensionReasoningScore

Conciseness

The body is lean and assumes competence: the Run section is two commands, the config shape is a compact field list, and craft rules state non-obvious constraints ('an L<246 threshold') without padding. Minor trimming is possible — the card-chrome inventory repeats the description nearly verbatim and 'Deterministic and FREE' restates frontmatter claims.

4 / 5

Actionability

The Run commands are copy-paste ready ('python3 scripts/build.py --config config.json --assets <stills-dir> --out master-silent.mp4') and the config shape documents every field, and craft rules give executable constants (L<246, top 50%). Not a 5 because the body points to 'config.example.json' as a full worked config but that file is absent from the bundle, and the music-mux step is delegated without a concrete ffmpeg/loudnorm command.

4 / 5

Workflow Clarity

A clear sequence exists: render stills ('quick check — one frame per slide'), build the silent master, generate + mux the music bed with 'fade in/out + loudnorm', then 'QC with watch'. The stills check is an explicit validation checkpoint before the expensive steps; it falls short of a 5 only because there is no explicit fix-and-retry guidance if the stills QC or loudnorm step fails.

4 / 5

Progressive Disclosure

Well-organized sections (Run, Choices, Craft rules, Output) with implementation correctly pushed to scripts/build.py (310 lines) and only an overview kept inline, one level deep. Not a 5 because the worked-example reference 'config.example.json is a full worked config (Glossier)' is dangling — the file does not exist in the bundle — leaving the reader without the promised navigable detail.

4 / 5

Total

16

/

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 dense, highly specific third-person description that comprehensively states what the skill produces and how (PIL + FFmpeg, deterministic, free) and draws clear boundaries against generative tools. The main weakness is the trigger clause: 'Use for the ig-live-gallery format' relies on an internal format name rather than natural user phrasing.

Suggestions

Replace or supplement 'Use for the ig-live-gallery format' with natural user phrasing, e.g. 'Use when the user asks for an Instagram-Live-style product gallery video, social-proof promo, or ig-live-gallery format'.

Add common synonyms of the trigger terms (IG Live, live-style promo, vertical product video) so the description matches how users actually ask.

Trim the long parenthetical chrome inventory (~50 words of UI detail) — the body already specifies the card elements — to reduce description token cost without losing distinctiveness.

DimensionReasoningScore

Specificity

Multiple concrete actions are enumerated: 'Render an Instagram-Live social-proof gallery video from a config', framing '~5 real brand product stills' as IG-Live cards with a specific chrome list, 'a brand-approved benefit sentence building one phrase per slide', 'a clean logo endcard', 'rendered deterministically with PIL frames plus FFmpeg'. Coverage of what the skill does is comprehensive and nothing is vague.

5 / 5

Completeness

The 'what' is fully explicit (render IG-Live-style gallery videos from a config with PIL + FFmpeg), and a 'when' clause exists ('Use for the ig-live-gallery format'). It is not a 5 because the 'when' is a thin internal format reference rather than concrete user-need trigger phrases; not a 3 because 'when' guidance is present, not missing.

4 / 5

Trigger Term Quality

Good natural terms users would plausibly say: 'Instagram-Live', 'social-proof gallery', 'video', 'brand product stills', 'logo endcard'. However the explicit trigger is the internal format name 'Use for the ig-live-gallery format', which is jargon a user would not naturally say; common variants like 'IG Live', 'reel', or 'story' phrasing are missing.

4 / 5

Distinctiveness Conflict Risk

A clear niche (Instagram-Live-styled social-proof gallery video rendering) with a distinctive feature set and explicit boundaries ('no generative image/video, no AI-rendered text', 'the music bed comes from create-music-elevenlabs'), so risk of firing for the wrong skill is minimal.

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.