muapi-multi-angle-reshoot

Re-render a subject or scene from multiple dramatic camera angles, such as fish-eye, bird's-eye, low-angle, and macro, while maintaining consistent identity and detail.

Quality

70%

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/multi-angle-reshoot/SKILL.md

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.

The body is a well-structured, actionable recipe with concrete muapi commands, full prompts, and an explicit approval checkpoint before the batch generation phase. It is concise and self-contained, with only minor gaps in exact command syntax and per-step verification.

Suggestions

Show the full muapi invocation syntax (flags for prompt, model, reference, aspect ratio) for at least one generate and one edit call so the guidance is copy-paste ready.

Add a brief verification/retry note for the batch phase (e.g. what to do if an angle drifts from the reference) to push workflow clarity toward 5.

De-duplicate the repeated 'Maintain exact clothing, face, and setting consistency' clause by stating it once as a shared constraint for all Phase B prompts.

Dimension	Reasoning	Score
Conciseness	Lean, actionable body that assumes Claude's competence and avoids explaining known concepts, matching 'efficient; minor instances of over-explanation'; not 5 because the bold description restatement and repeated 'Maintain exact clothing...' clauses across prompts could be trimmed.	4 / 5
Actionability	Provides concrete CLI commands with model IDs, full copy-paste prompt text, aspect ratios, and a curl fallback, matching 'mostly executable guidance; minor gaps'; not 5 because the exact muapi flag/syntax form for each command is not shown.	4 / 5
Workflow Clarity	Clear two-phase sequence with an explicit approval checkpoint ('Present the base image to the user for approval') and a post-generation review step, matching 'clear sequence with most checkpoints'; not 5 because per-angle verification/error-recovery loops are not spelled out.	4 / 5
Progressive Disclosure	Self-contained with well-organized sections (Inputs, Steps, Trigger Keywords, Notes) and no nested references, matching 'good structure; most content appropriately placed'; not 5 because the body slightly exceeds the ~50-line simple-skill threshold that would let structure alone earn a 5.	4 / 5
	Total	16 / 20 Passed

Description

66%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 is specific and distinct, naming concrete angles and a clear capability, but it omits any explicit 'when to use' trigger guidance, which caps its completeness. It reads naturally in third person and uses genuine user-facing terms.

Suggestions

Add an explicit 'Use when...' clause naming the trigger scenarios (e.g. 'Use when the user wants multiple camera angles of the same subject, or asks for fish-eye, bird's-eye, low-angle, macro, or Dutch-angle reshoots') to lift completeness beyond 3.

Include a few more natural synonyms/variations (e.g. 'Dutch angle', 'worm's-eye view', 'change perspective') to round out trigger-term coverage toward 5.

Dimension	Reasoning	Score
Specificity	Lists several specific concrete actions/angles ("fish-eye, bird's-eye, low-angle, and macro") plus the consistency requirement, matching the 'several specific actions; minor gaps' anchor; not 5 because it is essentially one re-render action with angle examples rather than a comprehensive action list.	4 / 5
Completeness	Clearly states the 'what' (re-render from multiple angles with consistency) but lacks any 'Use when...' clause or equivalent explicit trigger guidance, which per the rubric caps completeness at 3; not 4 because the 'when' is absent rather than merely imprecise.	3 / 5
Trigger Term Quality	Includes natural terms users would actually say ("fish-eye", "bird's-eye", "low-angle", "macro", "camera angles"), matching the 'good keyword coverage; a few natural terms missing' anchor; not 5 because synonyms/file-style variants are not exhaustive.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (multi-angle reshoot) with distinct angle-based triggers and minimal conflict risk, matching the 'mostly distinct; minor overlap risk' anchor; not 5 because it shares surface area with general image-editing skills.	4 / 5
	Total	15 / 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/multi-angle-reshoot/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.