CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

huashu-article-to-x

长文精简为X平台内容(200-500字),保留核心观点和个人风格。当用户提到"转微博"、"发小红书"、"社交媒体"、"缩短文章"时使用。

Quality

83%

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

SKILL.md
Quality
Evals
Security

Quality

Content

82%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 tight, highly actionable single-purpose skill: concrete example openings for each post type, a word-budgeted structure template, and a verification checklist, with no filler explanations. The main improvements are removing redundant sections that repeat the description, dropping the promotional footer, and making the implicit workflow order explicit.

Suggestions

Remove or merge the "何时使用" and "核心目标" sections, which restate the frontmatter description, and drop the promotional footer ("花叔出品 | 公众号... ") — none of it guides execution.

Add a brief explicit step order (e.g., 1. 通读原文提炼核心观点 → 2. 选定切入角度 → 3. 按标准结构起草 → 4. 用检查清单校验) so the workflow is stated rather than implied.

DimensionReasoningScore

Conciseness

The body is lean and example-driven with no explanations of concepts Claude already knows, but "何时使用" and "核心目标" duplicate the frontmatter description, and the trailing promo footer ("花叔出品 | ... 30万+粉丝") plus "最后更新: 2025-11-07" are non-instructional padding. Not a 3 because the redundancy is minor relative to the whole; not a 5 because those sections and the footer could be trimmed.

4 / 5

Actionability

For an instruction-only skill the guidance is fully actionable: three concrete copy-paste example openings covering the common post types (金句/数据/价值主张), a word-budgeted structure template ("开头(1-2句,30-50字)... 结尾(1句,20-30字)"), and explicit style dos/don'ts with specific examples ("'3个'、'半年'、'100%'"). Not a 4 because no key detail is missing — the examples plus template cover the common cases end to end.

5 / 5

Workflow Clarity

The components are all present — three entry angles, a standard structure, and a closing checklist ("第一句话有冲击力?长度合适?...") that acts as a validation checkpoint — but they are never assembled into an explicit ordered procedure (read article → pick angle → draft → verify against checklist). Not a 5 because the sequence is implicit rather than stated; not a 3 because the checklist provides a real validation step and the task is not destructive or batch, so no cap applies.

4 / 5

Progressive Disclosure

No bundle files exist (no references/scripts/assets), and the ~85-line body is cleanly organized into well-labeled sections with everything appropriately inline for a skill of this size. Not a 5 because the under-50-line simple-skill exception does not strictly apply and there are no clearly signaled reference files; not a 3 because nothing that belongs in a separate file is inlined and navigation is easy.

4 / 5

Total

17

/

20

Passed

Description

75%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 complete description that clearly states what the skill does and when to use it, with concrete word-count parameters and natural Chinese trigger phrases. Its weaknesses are narrow action coverage and a trigger set that names platforms (Weibo, Xiaohongshu) the skill does not actually target, raising conflict risk.

Suggestions

Align trigger terms with the actual target platform: replace or qualify "转微博"/"发小红书" (the skill targets X), or state explicitly that X-style content also serves Weibo/Xiaohongshu reposting, to reduce misfires with platform-specific skills.

Expand the 'what' with 1-2 more concrete actions, e.g., "选择金句/数据/价值主张开头,生成互动引导结尾", to move specificity from a single condense action to comprehensive capability coverage.

Add missing natural synonyms such as "推特", "发推", or "X/Twitter" to the trigger list to improve keyword coverage.

DimensionReasoningScore

Specificity

The description names the domain and gives concrete parameters ("长文精简为X平台内容(200-500字)" with "保留核心观点和个人风格") but describes only one action — condensing — rather than several specific actions, matching the '1-2 concrete actions, not comprehensive' anchor. Not a 4 because no additional actions (e.g., drafting openings, adding interaction prompts) are listed.

3 / 5

Completeness

It explicitly answers 'what' ("长文精简为X平台内容(200-500字),保留核心观点和个人风格") and 'when' with concrete trigger phrases ("当用户提到'转微博'、'发小红书'、'社交媒体'、'缩短文章'时使用"), matching the anchor for clearly and explicitly answering both with concrete triggers. The 'Use when...' clause is present, so the completeness cap does not apply.

5 / 5

Trigger Term Quality

Natural phrases a user would actually say are present ("转微博", "发小红书", "缩短文章"), giving good keyword coverage. Not a 5 because obvious X-platform synonyms are missing (e.g., X, 推特, Twitter, 发推), and "社交媒体" alone is generic; not a 3 because the listed phrases are genuine natural utterances rather than jargon.

4 / 5

Distinctiveness Conflict Risk

The skill targets X platform content, yet its triggers include "转微博" (Weibo) and "发小红书" (Xiaohongshu) — different platforms with different formats — plus the broad term "社交媒体", creating overlap risk with any Weibo/Xiaohongshu formatting skills. Not a 4 because the trigger set actively invites cross-platform misfires rather than presenting only minor overlap with closely related skills.

3 / 5

Total

15

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

alchaincyf/huashu-skills

Path

huashu-article-to-x/SKILL.md

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.