CtrlK
BlogDocsLog inGet started
Tessl Logo

check-models

Audit SD.Next model integrations end-to-end: loaders, detect/routing, reference catalogs, and pipeline API contracts.

68

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

100%

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 tight, well-sequenced audit checklist with concrete named APIs, explicit validation steps, and clean organization; it assumes Claude's competence throughout and avoids padding.

DimensionReasoningScore

Conciseness

The body is lean and sectioned (Audits A-D, Runtime Validation, Reporting Format, Pass Criteria) without explaining concepts Claude already knows, so every section earns its place and verbosity is avoided.

3 / 3

Actionability

Although it contains no runnable code, it is an instruction-only audit skill whose guidance is concrete and specific (named functions like sd_models.path_to_repo, model_quant.get_dit_args, diffusers.DiffusionPipeline and exact reference file paths), so per the scoring notes absence of code is not penalized when guidance is actionable.

3 / 3

Workflow Clarity

Audits A-D are explicitly ordered, the Runtime Validation section provides validation checkpoints with a fallback ('If runtime checks are not feasible, report limitations clearly'), and the Pass Criteria plus severity-ordered Reporting Format give clear feedback loops, matching the 'clear sequence with explicit validation steps' anchor.

3 / 3

Progressive Disclosure

The skill is a single well-organized file with no bundle files present and only a clearly signaled one-level pointer to .github/instructions/core.instructions.md, so per the scoring notes a well-organized skill with no need for external references scores 3.

3 / 3

Total

12

/

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 clearly occupies a distinct niche, but it omits any explicit 'when to use' trigger guidance and leans on internal jargon rather than natural user-facing keywords, capping trigger quality and completeness at 2.

Suggestions

Add a 'Use when...' clause naming natural trigger phrases (e.g., 'Use when auditing SD.Next model integrations, checking loader/detect/reference consistency, or validating a ported custom pipeline before a PR').

Soften jargon with user-facing synonyms alongside internal terms (e.g., 'model loaders', 'detection and routing', 'model reference catalogs', 'pipeline contracts') to improve trigger-term coverage.

DimensionReasoningScore

Specificity

The description enumerates multiple concrete audit surfaces ("loaders, detect/routing, reference catalogs, and pipeline API contracts"), matching the anchor that lists several specific concrete actions rather than vague language.

3 / 3

Completeness

It clearly states what the skill does but provides no 'Use when...' trigger clause, so per the judging guidelines a missing explicit trigger caps completeness at 2 rather than 3.

2 / 3

Trigger Term Quality

Terms like "model integrations", "detect/routing", and "pipeline API contracts" are internal SD.Next jargon rather than phrases a user would naturally say; common user-facing variations are missing, so it sits at 'some relevant keywords but missing common variations' rather than full natural-term coverage.

2 / 3

Distinctiveness Conflict Risk

The niche (SD.Next end-to-end model-integration audits) is distinct and specific enough that it is unlikely to trigger for unrelated skills, matching the 'clear niche with distinct triggers' anchor.

3 / 3

Total

10

/

12

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
vladmandic/sdnext
Reviewed

Table of Contents

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.