CtrlK
BlogDocsLog inGet started
Tessl Logo

check-paths

Audit SD.Next model-loading code for cache_dir routing on from_pretrained/from_single_file calls and verify diffusers vs HF cache path selection.

56

Quality

65%

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

Fix and improve this skill with Tessl

tessl review fix ./.github/skills/check-paths/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

68%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 concise, well-structured, and actionable with concrete file lists, option names, and a clear audit procedure. Its main weakness is the absence of an explicit validation/retry feedback loop for a batch audit operation.

Suggestions

Add an explicit validation/retry loop, e.g. after flagging a mismatch: 'Confirm the minimal fix resolves the mismatch by re-checking the loader call before moving on.'

Clarify how to handle ambiguous or wrapper-forwarded calls where the final cache root cannot be statically resolved (e.g., trace and re-audit at the final loader).

DimensionReasoningScore

Conciseness

Lean and efficient with no padding or explanation of concepts Claude already knows; only minor wording could be trimmed.

4 / 5

Actionability

Provides concrete, specific guidance — named files, exact option names (shared.opts.diffusers_dir / hfcache_dir), a classified procedure, and a structured reporting format — with only minor gaps.

4 / 5

Workflow Clarity

A clear sequenced procedure and pass criteria exist, but this batch audit operation lacks an explicit validate→fix→retry feedback loop, which caps workflow clarity at 3.

3 / 5

Progressive Disclosure

Well-organized into clearly signaled sections with one-level-deep reference to .github/instructions/core.instructions.md and no nested references; minor gaps only.

4 / 5

Total

15

/

20

Passed

Description

62%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 concrete and narrowly scoped to a distinct niche, but it lacks an explicit 'Use when...' trigger clause and natural-language synonyms, which limits completeness and trigger term quality.

Suggestions

Add an explicit 'Use when...' clause naming concrete triggering situations (e.g., 'Use when a loader changes and cache routing must be verified, or before a PR touching model-loading code').

Include a few natural-language synonyms alongside the technical jargon so users can trigger the skill without knowing exact API names.

DimensionReasoningScore

Specificity

Names the domain and several concrete actions — 'Audit SD.Next model-loading code for cache_dir routing' and 'verify diffusers vs HF cache path selection' — with only minor coverage gaps.

4 / 5

Completeness

Has a clear 'what' (audit routing, verify cache path selection) but no explicit 'Use when...' trigger clause, which caps completeness at 3 per the judging guidelines.

3 / 5

Trigger Term Quality

Includes technically precise terms a developer on this codebase would say ('from_pretrained', 'from_single_file', 'cache_dir', 'diffusers') but lacks natural synonyms or common variations.

3 / 5

Distinctiveness Conflict Risk

Targets a narrow niche (SD.Next model-loading cache_dir routing) with distinct triggers and minimal overlap risk with other skills.

5 / 5

Total

15

/

20

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.