natural-rewrite

在保持事实、语气和含义的前提下，把消息、邮件、评论、解释、社交媒体内容或文案改写得自然流畅。用于中文或英文润色、去除机器翻译感、微信回复、私信、邮件草稿、评论和简洁改写；不得添加未经确认的事实。

Quality

85%

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

Quality

Content

78%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 concise, well-structured instruction skill with an explicit output contract and validation step. Its main weakness is a broken reference to a missing examples file, which hurts progressive disclosure and leaves a small actionability gap.

Suggestions

Create the missing examples/chinese-message.md file (or remove the broken reference), so the 验证 section's link resolves and users can see a worked input→output example.

Add one short worked example inline (original → 直接版/温和版/轻松版) to make the skill fully copy-paste ready without relying on the external reference.

Make the validation step an explicit checkpoint (e.g., '在输出前逐项核对：事实、否定、数字、日期、URL、语气、格式') instead of a silent check, to strengthen the feedback loop.

Dimension	Reasoning	Score
Conciseness	Lean ~40-line body with well-organized sections, no explanations of concepts Claude already knows, and the forbidden-template list ('希望这封邮件找到你安好' etc.) is genuinely non-obvious, high-value guidance where every token earns its place.	5 / 5
Actionability	Provides a concrete output-contract template (直接版/温和版/轻松版 blocks), default style variants, and a forbidden-template list, but a worked input→output example is deferred to a referenced file rather than shown inline, leaving a small gap versus fully copy-paste-ready guidance.	4 / 5
Workflow Clarity	Clear 5-step 工作流程 with explicit validation in step 5 ('静默检查所有事实性约束仍然存在') and a dedicated 验证 section, but the validation is described as silent/implicit rather than a hard checkpoint feedback loop, so just below 5.	4 / 5
Progressive Disclosure	Sections are well-organized for a simple under-50-line skill, but the body references [chinese-message.md](examples/chinese-message.md) and no examples/ directory exists, so the reference is broken/dangling — a real navigation defect that prevents a higher score.	3 / 5
	Total	16 / 20 Passed

Description

91%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 use it, with abundant natural trigger terms. Minor room to enumerate multiple distinct concrete actions to push specificity higher.

Dimension	Reasoning	Score
Specificity	Names the domain (messages, emails, comments, social media, copy) and the concrete action of rewriting for naturalness, plus an explicit constraint '不得添加未经确认的事实'; multiple concrete targets but essentially a single transformation action rather than a list of distinct actions, so below 5.	4 / 5
Completeness	Explicitly states both what it does ('把消息、邮件…改写得自然流畅' under a fact/tone/meaning constraint) and when to use it (a concrete '用于…' trigger clause listing scenarios), satisfying the 'Use when…' requirement that would otherwise cap at 3.	5 / 5
Trigger Term Quality	Rich natural user phrasing — '润色', '去除机器翻译感', '微信回复', '私信', '邮件草稿', '评论', '简洁改写' — covering synonyms and platform-specific terms a user would actually say.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear natural-rewriting/polishing niche with distinctive triggers (润色, 去除机器翻译感, 微信回复); minor overlap risk with general translation or editing skills keeps it just below 5.	4 / 5
	Total	18 / 20 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
relative_links	Relative link issues: 1 missing	Warning

	Total	15 / 16 Passed

Repository: ooooooooooooooooooop/agent-tools
Path: skills/natural-rewrite/SKILL.md
Commit: 3677cfc

Reviewed: ~8 hours 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.