shogun-screenshot

スクリーンショットの取得・加工を行う。ローカルスクショから最新画像を取得、 PlaywrightでWebページをキャプチャ、画像のトリミング・リサイズ、機微情報を黒塗りマスキング。記事執筆、レポート作成、UI確認、画像加工時に起動。「スクショ」「スクリーンショット」「画面キャプチャ」「最新のスクショ」「画像加工」「トリミング」「マスク」「写メ」「写メ撮った」「スクショ撮った」で起動。 Do NOT use for: 画像生成（shogun-imagegenを使え）。

Quality

87%

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

Quality

Content

75%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.

A well-structured, mostly actionable skill body with real helper scripts and a proper validation loop for its destructive masking operation. The main gaps are minor: a padded North Star rationale, a non-executable Mode 2, and inline option detail that could be offloaded to the scripts.

Suggestions

Trim or remove the 'North Star' section—it states product strategy rather than execution guidance Claude needs.

Add a copy-paste-ready Playwright MCP example for Mode 2 (e.g. a concrete playwright_navigate + playwright_screenshot invocation) and a step to verify the saved PNG path exists.

Move the detailed flag tables for trim_image.py and mask_sensitive.py into the scripts' own --help output, keeping only the canonical one-line usage in SKILL.md.

Dimension	Reasoning	Score
Conciseness	Largely lean and command-focused, but the 'North Star' section explains a strategic rationale (コンテンツ差別化) Claude does not need for execution, and the Overview restates the four modes already in the description.	4 / 5
Actionability	Modes 1, 3, and 4 give copy-paste-ready commands with real flags and common-case variants (single/multi regions, --preview), but Mode 2 only describes Playwright MCP parameters rather than giving an executable example and does not verify the saved output.	4 / 5
Workflow Clarity	Sequences are clear and the destructive masking mode has an explicit validation feedback loop (Read → --preview → confirm → execute), avoiding the destructive-cap; minor gaps are that trim and Mode 1 lack an explicit output-verification step.	4 / 5
Progressive Disclosure	Well-organized into clear sections with one-level-deep, clearly signaled references to real bundle scripts (capture_local.sh, trim_image.py, mask_sensitive.py), though substantial option detail is inlined rather than living in the scripts.	4 / 5
	Total	16 / 20 Passed

Description

100%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.

An excellent description: concrete actions, rich natural trigger terms including colloquial synonyms, explicit what/when guidance, and a clear negative boundary against the sibling image-generation skill. Voice is appropriately impersonal (third person).

Dimension	Reasoning	Score
Specificity	Lists four concrete actions—「ローカルスクショから最新画像を取得」「PlaywrightでWebページをキャプチャ」「画像のトリミング・リサイズ」「機微情報を黒塗りマスキング」—giving comprehensive coverage of the skill's capabilities.	5 / 5
Completeness	Explicitly answers both 'what' (screenshot acquisition and processing across four modes) and 'when' (「記事執筆、レポート作成、UI確認、画像加工時に起動」 plus explicit trigger phrases), and adds a 'Do NOT use for' boundary.	5 / 5
Trigger Term Quality	Comprehensive natural trigger terms including colloquial synonyms—「スクショ」「スクリーンショット」「画面キャプチャ」「最新のスクショ」「画像加工」「トリミング」「マスク」「写メ」「写メ撮った」「スクショ撮った」—matching phrases users would actually say.	5 / 5
Distinctiveness Conflict Risk	A clear screenshot niche with distinct triggers and an explicit negative boundary—「Do NOT use for: 画像生成（shogun-imagegenを使え）」—minimizes conflict with the related image-generation skill.	5 / 5
	Total	20 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: yohey-w/multi-agent-shogun
Path: skills/shogun-screenshot/SKILL.md
Commit: aff8dc8

Reviewed: 17 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.