baoyu-compress-image

Compresses images to WebP (default) or PNG with automatic tool selection. Use when user asks to "compress image", "optimize image", "convert to webp", or reduce image file size.

Quality

80%

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 ./skills/baoyu-compress-image/SKILL.md

Quality

Content

76%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 lean, well-structured, and actionable with accurate references to a real script. The main weakness is the absence of a validation checkpoint for a destructive/batch operation, which caps workflow clarity at 3.

Suggestions

Add an explicit validation/safety checkpoint before overwriting originals (e.g. recommend --keep by default or verify the output file is non-empty/valid before deleting the source), to satisfy the destructive/batch feedback-loop requirement.

Provide a one-line resolved example (e.g. "bun /abs/path/scripts/main.ts image.png") so users have a true copy-paste-ready command without first substituting placeholders.

State the compressor-selection outcome (which tool was used) in the example output block so the "automatic tool selection" claim is observable.

Dimension	Reasoning	Score
Conciseness	Tables for scripts/options/preferences and terse examples convey everything with no padding; it never explains concepts Claude already knows and the runtime-resolution prose earns its place, matching the lean anchor 5.	5 / 5
Actionability	Commands are concrete and executable with a full options table and four copy-pasteable examples, but the {baseDir} and ${BUN_X} placeholders must be resolved before use, a minor gap versus pure copy-paste-ready anchor 5.	4 / 5
Workflow Clarity	The single action is unambiguous, but the skill defaults to replacing originals ("replaces original") and supports batch -r, so the rubric's destructive/batch validation cap of 3 applies: no verify-before-overwrite checkpoint is documented.	3 / 5
Progressive Disclosure	Well-organized sections with an accurate single bundle reference (scripts/main.ts) and one-level-deep EXTEND.md paths; content is appropriately inline for a simple skill but offers no progressive reference docs to navigate, so it is not the split-and-signaled anchor 5.	4 / 5
	Total	16 / 20 Passed

Description

78%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.

A strong description that clearly answers both what the skill does and when to invoke it, with natural trigger phrases. Specificity is the weakest dimension because only a single core action is named despite format and tool-selection detail.

Suggestions

Add one or two more concrete actions (e.g. resize/batch-optimize) to lift specificity beyond a single core action.

Include common synonyms such as "shrink image", "make image smaller", and relevant file extensions (.webp, .png, .jpg) to round out trigger-term coverage toward anchor 5.

Dimension	Reasoning	Score
Specificity	"Compresses images to WebP (default) or PNG with automatic tool selection" names the domain and a concrete action with format variants, but does not list several distinct actions, matching anchor 3 rather than 4.	3 / 5
Completeness	It explicitly states what ("Compresses images to WebP (default) or PNG with automatic tool selection") and when ("Use when user asks to ..."), with concrete trigger phrases, matching the anchor-5 example.	5 / 5
Trigger Term Quality	Includes four natural user phrases ("compress image", "optimize image", "convert to webp", "reduce image file size") giving good coverage, but omits common synonyms like "shrink image" and file extensions, so it is not the comprehensive anchor 5.	4 / 5
Distinctiveness Conflict Risk	The image-compression niche with specific WebP/PNG triggers is mostly distinct with only minor overlap risk against generic image skills, fitting anchor 4 rather than the more elaborated anchor 5.	4 / 5
	Total	16 / 20 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	13 / 16 Passed

Repository: JimLiu/baoyu-skills
Path: skills/baoyu-compress-image/SKILL.md
Commit: 1567581

Reviewed: 13 days 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.