CtrlK
BlogDocsLog inGet started
Tessl Logo

render-cinematic-music-video

Assemble a cinematic live-action-style music-video ad from a config — an original sung anthem carries the whole narrative while N 35mm-film-look i2v clips are each cut to their lyric window and hard-concatenated on the beat as a 3-act arc, the anthem muxed at loudnorm I=-14, cinematic lower-third serif captions built from the song's OWN word timings (never Whisper) with the hook line landing on the chorus drop, and closed on a brand end card composited from the real asset — never AI-rendered text. This is the FREE deterministic assembly stage (cut-to-window + hard concat + anthem mux + captions + end card); the anthem, keyframes, and clips come from create-music-elevenlabs / create-image-gpt-image-fal / create-video-fal. Use for the cinematic-music-video format.

62

Quality

78%

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 ./skills/ads/capabilities/render-cinematic-music-video/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

71%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 well-structured, information-dense overview with excellent progressive disclosure — all referenced bundle files exist, are one level deep, and are each introduced with their purpose. The main gaps are executability (no runnable entry point or code in the body, with the runner deliberately unbundled) and the total absence of validation/verification checkpoints in the assembly workflow.

Suggestions

Add an explicit invocation section with at least one concrete command or code block (e.g. the ffmpeg cut/concat/mux chain or a stitch script call), so the assembly is executable from SKILL.md rather than only described as a contract.

Insert validation checkpoints into the workflow — e.g. verify clip durations cover their lyric windows before concat, check words.json timestamps are monotonic before caption burn, and probe the final master's duration/streams before delivering.

De-duplicate the 'FREE / $0 deterministic' framing and the upstream-capability list, which each appear in both the intro and Run/Contract sections — stating it once in Run would save tokens without losing information.

DimensionReasoningScore

Conciseness

The body is dense and domain-specific with no explanation of concepts Claude already knows, but the 'FREE / $0 deterministic assembly' framing is repeated across the intro, Run, and Contract sections, and the upstream paid capabilities are listed twice. Not 5: these repetitions could be trimmed without losing information; not 3: the padding is minor.

4 / 5

Actionability

Concrete parameters appear throughout ('--placement low', 'afade' in/out + 'loudnorm I=-14', 'force_instrumental' false, 'words_timestamps' → words.json, 1080×1920 h264+aac), but the body contains no executable entry point — no script invocation, command, or code — and the bundle ships 'a config + this map, not a bundled runner', leaving the actual execution path unstated. Not 4: key execution details are missing, not just minor gaps.

3 / 5

Workflow Clarity

The assembly sequence is explicit and ordered ('cuts each clip to its lyric window, hard-concats on the beat, muxes the anthem, burns the… captions, and overlays the end card → the master') with clear input preconditions and dependency rationale. Not 5: there are no validation or verification checkpoints at all (no output check, no per-stage sanity step); not 3: the sequence and ordering rules are far more explicit than a bare step list.

4 / 5

Progressive Disclosure

The ~60-line body is a proper overview and every reference is real and one level deep, each signaled with its purpose: scripts/config.example.json ('the worked example — copy its structure, never its creative values'), scripts/PIPELINE.md ('maps every config block to its source step'), scripts/README.md ('documents the free assembly'). All three files exist in the bundle and stay at one level of nesting.

5 / 5

Total

16

/

20

Passed

Description

76%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 highly specific, well-disambiguated description that comprehensively enumerates the assembly actions and cleanly separates this free stage from the paid upstream capabilities. Its weaknesses are the jargon-heavy phrasing and a single narrow trigger clause that misses the natural terms a user would say when requesting a music-video ad.

Suggestions

Add natural trigger phrasings to the when-clause, e.g. 'Use when the user wants to assemble/render a cinematic music-video ad, cut clips to lyrics, or re-cut an existing one at no cost' rather than only naming the internal format.

Trim production jargon from the trigger-relevant surface (e.g. 'i2v clips', 'loudnorm I=-14') or pair each term with its natural synonym ('image-to-video clips', 'broadcast-level loudness') so users' phrasing can match.

Name the input artifacts users will reference (mp3, word timings, keyframes, clips, end-card asset) as keywords, since a user asking for this skill will typically mention those deliverables.

DimensionReasoningScore

Specificity

The description enumerates the full set of concrete assembly actions — clips 'cut to their lyric window and hard-concatenated on the beat', 'anthem muxed at loudnorm I=-14', 'lower-third serif captions built from the song's OWN word timings', 'brand end card composited from the real asset' — with comprehensive, jargon-precise coverage of the stage. Not 4: there are no coverage gaps in what the stage does.

5 / 5

Completeness

Both are answered: a clear, detailed 'what' (the full assembly pipeline) and an explicit 'when' ('Use for the cinematic-music-video format'). Not 5: the when-clause is a single format-name reference rather than concrete trigger phrases a user would actually say; not 3: both what and when are explicitly stated.

4 / 5

Trigger Term Quality

Some relevant natural terms are present ('music-video', 'anthem', 'captions', 'end card'), but the phrasing is dominated by technical jargon ('i2v clips', 'loudnorm I=-14', 'hard-concatenated') and the only trigger is the narrow 'Use for the cinematic-music-video format'. Not 4: common user phrasings like 'make/render a music video ad' or its synonyms are missing.

3 / 5

Distinctiveness Conflict Risk

It carves out a clear niche — the FREE deterministic assembly stage — and explicitly disambiguates from the named upstream paid skills ('create-music-elevenlabs / create-image-gpt-image-fal / create-video-fal'). Minimal conflict risk; matches anchor 5.

5 / 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.

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.