port-pipeline

Port custom model pipeline implementations to Diffusers using phased priorities: preserve behavior first, avoid new dependencies second, and keep device/attention handling configurable throughout. Use when migrating custom or non-Diffusers pipeline code into SD.Next repo-local pipeline files such as pipelines/model_<name>.py or pipelines/<model>/pipeline.py.

Quality

84%

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

Quality

Content

81%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 content is a well-structured, actionable instruction skill with a strong validated workflow and clear external reference signaling. Its main weakness is that the core porting steps are descriptive rather than concrete, and the intro/When-To-Use sections slightly restate the description.

Suggestions

Tighten the opening summary and 'When To Use' section to avoid restating the frontmatter description verbatim.

Add a small concrete code skeleton or signature example for the pipeline class (e.g., a minimal __call__ signature aligned with Diffusers patterns) to lift actionability from descriptive to executable.

Consider moving the detailed Review Checklist or Output Expectations into a short reference file if the skill grows, to keep SKILL.md as a lean overview.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean and assumes Claude's knowledge of Diffusers concepts, but the opening summary and 'When To Use' section partially restate the frontmatter description, offering minor trimming opportunities rather than padding.	4 / 5
Actionability	Concrete executable guidance is present (specific file placement like 'pipelines/<model>/transformer.py', lint commands 'source venv/bin/activate', 'pnpm ruff', 'pylint <file>'), but the core porting implementation steps remain descriptive rather than copy-paste ready, leaving minor gaps.	4 / 5
Workflow Clarity	An eight-step workflow is clearly sequenced with explicit validation checkpoints (lint re-run loop in step 6, behavior parity validation in step 7), a mandatory clarification gate, and a review checklist with error-recovery feedback.	5 / 5
Progressive Disclosure	The skill is well-organized into clear sections and points to one external reference ('.github/instructions/core.instructions.md') that is one level deep and clearly signaled, but the body is a single ~110-line file with no progressive split, which is appropriate yet not maximally decomposed.	4 / 5
	Total	17 / 20 Passed

Description

87%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 strong: it states concrete actions, gives an explicit 'Use when' trigger tied to specific file paths, and occupies a distinct niche. Minor room for more exhaustive action/synonym coverage keeps specificity and trigger_term_quality at 4.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ('Port custom model pipeline implementations to Diffusers', 'preserve behavior first', 'avoid new dependencies second', 'keep device/attention handling configurable'), but coverage is more about approach priorities than an exhaustive action list, so it sits below the comprehensive 5.	4 / 5
Completeness	Explicitly answers both what ('Port custom model pipeline implementations to Diffusers ...') and when ('Use when migrating custom or non-Diffusers pipeline code into SD.Next repo-local pipeline files ...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Natural domain terms users would say are present ('port ... to Diffusers', 'migrating custom or non-Diffusers pipeline code', 'SD.Next repo-local pipeline files', concrete path patterns), with good but not exhaustive synonym coverage.	4 / 5
Distinctiveness Conflict Risk	A clearly defined niche (porting custom pipelines to Diffusers for SD.Next repo-local files) with specific path-based triggers and minimal overlap risk with unrelated skills.	5 / 5
	Total	18 / 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: vladmandic/sdnext
Path: .github/skills/port-pipeline/SKILL.md
Commit: c40fc01

Reviewed: ~17 hours 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.