muapi-workflow

Build, run, and visualize multi-step AI generation workflows. The AI architect translates natural language descriptions into connected node graphs — chain image generation, video creation, enhancement, and editing into automated pipelines.

Quality

66%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

Fix and improve this skill with Tessl

tessl review fix ./library/workflow/SKILL.md

Quality

Content

61%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 highly actionable with concrete muapi commands and clear script references, but it is held back by redundant CLI-reference content and a build workflow that lacks validation checkpoints for batch generation operations. Tightening redundancy and adding a verify-before-run step would raise the weakest dimensions.

Suggestions

Add an explicit validation checkpoint in the build protocol (e.g. inspect the node graph with 'muapi workflow get' and confirm required API inputs before executing) to satisfy the batch-operation feedback-loop requirement.

Remove or consolidate the 'CLI Reference' section so commands are not duplicated across 'Core Operations' and the reference block.

Trim the 'Example Agent Reasoning' illustration; the numbered Discover/Match/Analyze/Choose steps already convey the procedure.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient command blocks, but the 'Example Agent Reasoning' block and the 'CLI Reference' section restate commands already shown elsewhere; not a 4 because these padded/redundant sections could be trimmed, not a 2 because the bulk is lean executable guidance.	3 / 5
Actionability	Concrete copy-paste commands like 'muapi workflow create "..."' and 'muapi workflow execute <workflow_id> --input "node1.prompt=..."' cover common image and video pipeline cases; not a 5 because placeholders and a few undemonstrated subcommands (templates, rename, delete) leave minor gaps.	4 / 5
Workflow Clarity	The 'Protocol: Building a Workflow' lists sequenced Steps 1–5, but validation checkpoints and error-recovery loops are absent for a batch generation operation, so per the rubric cap workflow clarity cannot exceed 3.	3 / 5
Progressive Disclosure	Core Operations clearly signals the real bundle scripts (generate-workflow.sh, discover-workflow.sh, interactive-run.sh, run-workflow.sh) one level deep with good section structure; not a 5 because the inline CLI Reference duplicates content that overlaps the script references.	4 / 5
	Total	14 / 20 Passed

Description

71%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 actionable with good natural trigger terms and a clear niche, but it lacks any explicit 'Use when' trigger guidance, which caps completeness at 3. Adding a concrete trigger clause would lift the weakest dimension.

Suggestions

Append an explicit 'Use when...' clause, e.g. 'Use when building or running multi-step AI media generation pipelines (image, video, enhance, edit) on muapi.ai.'

Include the platform name 'muapi.ai' in the description to improve distinctiveness and reduce overlap with generic workflow skills.

Add a couple of natural synonyms users might say ('AI pipelines', 'generation chains', 'automation recipe') to round out trigger term coverage.

Dimension	Reasoning	Score
Specificity	Quotes 'Build, run, and visualize multi-step AI generation workflows' and 'chain image generation, video creation, enhancement, and editing into automated pipelines' list multiple concrete actions with comprehensive coverage of the domain; not a 4 because coverage is broad rather than having minor gaps.	5 / 5
Completeness	A clear 'what' is present ('Build, run, and visualize... chain image generation, video creation...') but there is no 'Use when...' clause or explicit trigger guidance, so per the judging guideline completeness is capped at 3.	3 / 5
Trigger Term Quality	Natural terms like 'image generation', 'video creation', 'workflows', and 'pipelines' appear, but 'node graphs' and 'AI architect' are more technical and common synonyms/variations a user might say are missing; not a 5 due to incomplete synonym coverage, not a 3 because several natural keywords are present.	4 / 5
Distinctiveness Conflict Risk	The niche of chaining AI media-generation steps into node-graph pipelines is mostly distinct with minor overlap risk against generic automation/pipeline skills; not a 5 because the description omits the platform name that would fully isolate it.	4 / 5
	Total	16 / 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/workflow/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.