muapi-selfie-with-celebrities

Generate a realistic behind-the-scenes selfie of the user with a celebrity or main actor from a specific movie, followed by an option to generate a cinematic long-take video connecting multiple selfies.

Quality

61%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./library/visual/selfie-with-celebrities/SKILL.md

Quality

Content

65%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.

The skill body is well-structured and mostly executable, with concrete prompts and model IDs plus a sensible curl fallback. Its main weakness is workflow clarity: there are no validation/verification checkpoints after generation, capping that dimension at 3.

Suggestions

Add a verification checkpoint after Phase A and Phase B (e.g., confirm the generated image shows both the user and actor in 9:16 before offering the next step) to raise workflow_clarity above 3.

Provide the actual full `muapi image edit ...` and image-to-video CLI invocations (with flags) rather than describing the call as a plan step, to make actionability copy-paste ready.

Trim the bold restatement of the description directly under the H1 to save tokens without losing information.

Dimension	Reasoning	Score
Conciseness	The body is reasonably lean: a tight inputs table, two phased steps with concrete prompts, and a short notes section; only minor padding (the bold restatement of the description) could be trimmed.	4 / 5
Actionability	Provides concrete model IDs, exact prompt strings, reference-image wiring, and a curl fallback with polling, but the image-edit/video commands are described as plan steps rather than fully copy-paste muapi CLI invocations.	4 / 5
Workflow Clarity	Phases A and B are sequenced with clear gating ('Only when requested', 'If not provided, ask'), but there is no verification/feedback checkpoint after image or video generation to confirm output quality before proceeding.	3 / 5
Progressive Disclosure	Well-organized sections (Inputs, Steps, Trigger Keywords, Notes) with no nested references and everything inline at one level; it is a compact single-file skill that needs no bundle, so structure is good with only minor room to externalize the long prompt templates.	4 / 5
	Total	15 / 20 Passed

Description

57%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.

The description concretely states the two core capabilities but omits any explicit trigger/usage guidance, so it answers 'what' but not 'when'. It is distinct from generic media skills but would benefit from a 'Use when...' clause.

Suggestions

Add an explicit 'Use when...' clause naming natural user phrases such as 'selfie with celebrity', 'movie star selfie', or 'take a picture with an actor' to satisfy the 'when' half of completeness.

Surface the natural trigger keywords directly in the description (e.g., 'Use when the user asks for a selfie with a celebrity or actor from a movie') to lift trigger_term_quality.

Optionally list the optional video step more tersely so the core action reads first and the long-take video follow-on is clearly secondary.

Dimension	Reasoning	Score
Specificity	Names two concrete actions ('Generate a realistic behind-the-scenes selfie' and 'generate a cinematic long-take video connecting multiple selfies'), but stops at two rather than a comprehensive list of operations.	4 / 5
Completeness	It clearly states 'what' the skill does but lacks any explicit 'Use when...' / 'when should Claude use it' clause, which caps completeness at 3 per the judging guidelines.	3 / 5
Trigger Term Quality	The description contains no natural user-facing trigger phrases like 'selfie with celebrity' (those only appear in the body); it relies on technical framing rather than terms a user would naturally say.	3 / 5
Distinctiveness Conflict Risk	The niche (movie-set BTS selfie with a celebrity + connecting video) is fairly distinct with minimal overlap risk, though the generic 'selfie/video' framing leaves minor overlap with other media skills.	4 / 5
	Total	14 / 20 Passed

Validation

93%

Warnings & errors only

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

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: SamurAIGPT/Generative-Media-Skills
Path: library/visual/selfie-with-celebrities/SKILL.md
Commit: 3b62f78

Reviewed: 6 days ago

Table of Contents

Discovery Implementation Validation

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.