tech-writing

技术文章对外写作：从内部实践到读者能代入的叙事。 Use when: 写技术博客、公众号文章、社区分享、对外 longform、技术文章 review、写推广语。 Not for: 内部文档/spec（直接写）、PPT（用 ppt-forge）。 Output: 有呼吸感的技术文章 + 读者反馈聚类分析。

Quality

86%

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

77%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-organized, actionable instruction skill with a clear phased workflow and explicit gates, but it references bundle files (范本 lessons and the AI-taste checklist) that are not present in the skill bundle, breaking the progressive-disclosure structure it advertises.

Suggestions

Ship the referenced bundle files (cat-cafe-tutorials/docs/lessons/12-no-boss-agent.md, 01-sdk-to-cli.md, and refs/ai-taste-checklist.md) or remove/inline the references so they resolve.

Convert a few of the slogan-level principles (e.g. '给原则取名', '用人物的嘴说') into one concrete fill-in template each to push actionability toward copy-paste-ready.

Tighten the opening aphoristic framing ('为什么读者能闻到AI味') to reduce emphasis prose without losing the '解压过程' metaphor.

Dimension	Reasoning	Score
Conciseness	Dense and mostly lean, assuming Claude's competence without explaining basic concepts; a few aphoristic/emphatic framing lines ('AI 写作像是在发送一个逻辑自洽的压缩包') could be trimmed without losing the actionable guidance.	4 / 5
Actionability	Provides concrete before/after examples ('AI 味' vs '猫咖味'), specific guidance ('丢具体时间戳或 commit hash…2026-02-04 23:47'), and translation句 examples, but some guidance stays at principle/slogan level rather than fully copy-paste-ready templates.	4 / 5
Workflow Clarity	Phases 0→5 are clearly sequenced with an explicit gate (Phase 3 '每章门禁' checklist), feedback→fix loops (Phase 5 feedback table), and a concrete '下一步' sequence (写完一章 → 听呼吸感 → 过门禁 → 审钩子 → 发布) with validation checkpoints.	5 / 5
Progressive Disclosure	The body is reasonably sectioned and signals one-level-deep references (范本 lessons and 'refs/ai-taste-checklist.md'), but none of the referenced bundle files actually exist (no references/, refs/, or cat-cafe-tutorials/ directories), so the navigation the body promises does not resolve.	3 / 5
	Total	16 / 20 Passed

Description

95%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, well-structured description that clearly states what it does, when to use it, and what to avoid, with a rich set of natural Chinese trigger terms. The only mild weakness is that the stated actions are slightly abstract rather than maximally concrete.

Dimension	Reasoning	Score
Specificity	Names the domain ('技术文章对外写作') and concrete deliverables ('有呼吸感的技术文章 + 读者反馈聚类分析') plus task verbs via triggers, but the actions stay at a fairly abstract level rather than the comprehensive concrete-action list of a 5.	4 / 5
Completeness	Explicitly answers what (技术文章对外写作 narrative + Output deliverable), when (explicit 'Use when:' with concrete triggers), and even a 'Not for:' boundary — matching the anchor that requires clear what AND when with concrete trigger phrases.	5 / 5
Trigger Term Quality	Comprehensive natural-term coverage including synonyms ('博客'/'longform', '公众号'/'对外发布', '社区分享', '推广语', '技术分享') in both the triggers list and the 'Use when' clause — phrases a user would naturally say.	5 / 5
Distinctiveness Conflict Risk	Clear niche (对外技术文章写作) with an explicit 'Not for:' boundary disambiguating internal docs/spec and PPT (cross-referencing ppt-forge), demonstrating deliberate conflict avoidance and minimal overlap risk.	5 / 5
	Total	19 / 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: zts212653/clowder-ai
Path: cat-cafe-skills/tech-writing/SKILL.md
Commit: 090626a

Reviewed: ~23 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.