reference-catalog

Maintain and validate SD.Next model reference catalogs in data/reference*.json, including schema consistency, deduplication, link checks, and thumbnail alignment.

Quality

76%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./.github/skills/reference-catalog/SKILL.md

Quality

Content

85%

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 and well-sequenced with explicit validation feedback loops, and it is appropriately self-contained with clear navigation. The only meaningful weakness is redundancy around the size-backfill procedure, which slightly undermines token efficiency.

Suggestions

Consolidate the size-backfill procedure into one authoritative section and cross-reference it elsewhere instead of restating it in Core Rules, the Validation Checklist, the Safe Edit Workflow, and Common Failure Modes.

Trim the repeated size-backfill failure-mode bullets to a single canonical list to reduce token cost.

Dimension	Reasoning	Score
Conciseness	The body is lean and directive with no concept-explanation fluff, but the size-backfill procedure is repeated across Core Rules Priority 3, Validation Checklist #7, Safe Edit Workflow step 3, and two failure-mode bullets, so it could be tightened to earn a 3.	2 / 3
Actionability	Concrete file paths, the explicit `cli/hf-info.py` invocation, `info.data.size` parsing of the "23933.4MB" format, and the formula `gb = round(mb / 1024, 2)` make the guidance copy-paste ready, matching the score-3 anchor for an actionable instruction skill.	3 / 3
Workflow Clarity	A phased approach plus the 6-step Safe Edit Workflow with an explicit step-5 "Re-validate JSON and duplicate checks" feedback loop, and unresolved-report handling for the batch size backfill, provide a clear sequence with validation checkpoints as required for score 3.	3 / 3
Progressive Disclosure	No bundle files are provided and none are needed; the single self-contained SKILL.md is well-organized into clear sections with one appropriately signaled one-level-deep external pointer (`.github/instructions/core.instructions.md`), satisfying the score-3 anchor.	3 / 3
	Total	11 / 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 a narrow SD.Next catalog-maintenance niche. Its main weakness is the missing explicit "Use when..." trigger guidance and somewhat technical rather than natural trigger terms.

Suggestions

Add an explicit "Use when..." clause listing natural user phrasings (e.g. deduping reference catalogs, checking broken links, syncing thumbnails) to raise completeness to 3.

Include more natural trigger keywords users would actually say alongside the technical terms to improve trigger-term quality.

Keep the concrete action list as-is; it is already a strength of the description.

Dimension	Reasoning	Score
Specificity	"Maintain and validate SD.Next model reference catalogs ... including schema consistency, deduplication, link checks, and thumbnail alignment" lists multiple specific concrete actions rather than vague language, matching the score-3 anchor.	3 / 3
Completeness	It clearly answers "what" the skill does but provides no "Use when..." clause or equivalent explicit trigger guidance, which per the judging guidelines caps completeness at 2.	2 / 3
Trigger Term Quality	Terms like "model reference catalogs", "deduplication", "link checks", and "thumbnail alignment" are relevant but technical, and natural user phrasings (e.g. "clean up duplicates", "fix thumbnails") are missing, so it sits at the score-2 anchor rather than full coverage.	2 / 3
Distinctiveness Conflict Risk	The narrow scope of "SD.Next model reference catalogs in data/reference*.json" defines a clear niche with distinct triggers that is unlikely to conflict with other skills, matching the score-3 anchor.	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/reference-catalog/SKILL.md
Commit: 058a7f0

Reviewed: 1 day 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.