port-model

Port or add a model to SD.Next using a phased integration flow: select the least-new-code path that follows SD.Next conventions, then implement loader and routing updates, then validate.

Quality

66%

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 ./.github/skills/port-model/SKILL.md

Quality

Content

65%

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 thorough, well-sequenced porting playbook with strong workflow clarity and concrete SD.Next touchpoints. Its weaknesses are mild redundancy inflating length, structural-only actionability, and total absence of progressive-disclosure file structure.

Suggestions

Split the long reference-catalog and CHANGELOG detail into a separate reference file (e.g. references/reference-catalog.md) and link to it from SKILL.md to introduce progressive disclosure.

Add at least one concrete minimal code skeleton (e.g. a stub `pipelines/model_<name>.py` loader function) so the actionability matches the structural guidance.

Deduplicate the loader/routing file lists that appear in both the integration-path sections and 'Required SD.Next Touchpoints' to tighten conciseness.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and assumes Claude's competence (no basic concept explanations), but the body runs ~290 lines with some redundancy — e.g., integration paths and 'Required SD.Next Touchpoints' both enumerate the same loader/routing files — that could be tightened.	2 / 3
Actionability	Concrete file paths and function names (e.g. 'pipelines/model_<name>.py', 'sd_models.path_to_repo(checkpoint_info)', 'generic.load_transformer(...)') give executable direction, but most guidance is structural lists and conventions rather than complete, copy-paste-ready code.	2 / 3
Workflow Clarity	The phased flow is explicit (collect inputs, mandatory questions, decision tree with three numbered paths, validation checklist) and includes an ordered validation sequence with the directive to 'Always report what was validated and what was not', plus the gated-model abort checkpoint as an error-recovery loop.	3 / 3
Progressive Disclosure	There are no bundle files in references/scripts/assets, and the single reference to '.github/instructions/core.instructions.md' is an external repo path rather than a skill-internal reference, so the body is effectively a monolithic single-file skill with no progressive disclosure structure.	1 / 3
	Total	8 / 12 Passed

Description

67%

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 distinctive, clearly scoping the work to SD.Next/Diffusers model porting. Its main weakness is the absence of an explicit 'Use when...' trigger clause and limited natural-language trigger terms.

Suggestions

Add an explicit 'Use when...' clause (e.g. 'Use when adding a new model family to SD.Next or wiring an upstream Diffusers pipeline into SD.Next').

Include natural trigger phrasings users would actually say, such as 'add support for a model', 'wire this model into SD.Next', or 'port a checkpoint'.

Drop or compress the implementation-method detail ('select the least-new-code path... then implement... then validate') to keep the description a capability/trigger statement rather than a process summary.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions ('select the least-new-code path', 'implement loader and routing updates', then 'validate') along with concrete SD.Next artifacts (loader, routing), giving a comprehensive action set.	3 / 3
Completeness	It clearly states what the skill does (phased integration flow), but provides no explicit 'Use when...' trigger clause, so the 'when' side is only implied by the topic, capping completeness at 2.	2 / 3
Trigger Term Quality	Contains relevant domain terms ('port', 'model', 'SD.Next', 'Diffusers', 'loader'), but lacks the natural phrasings a user would actually say ('add support for', 'wire in', 'add this model') and has no shorthand like 'model port'.	2 / 3
Distinctiveness Conflict Risk	The narrow pairing of 'SD.Next' + 'Diffusers' + 'loader and routing' is a clear niche unlikely to trigger for unrelated skills.	3 / 3
	Total	10 / 12 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-model/SKILL.md
Commit: 058a7f0

Reviewed: about 23 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.