writing-core

Use when writing or revising academic papers, especially Chinese journal manuscripts, that need natural prose, de-AI-ification, Markdown formatting, or quality checks

Quality

72%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Medium

Suggest reviewing before use

Fix and improve this skill with Tessl

tessl review fix ./skills/writing-core/SKILL.md

Quality

Content

62%Weight 40%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured, domain-rich instruction skill with a clear three-round QA workflow, weakened by a missing referenced script, some basic-concept padding, and lack of progressive disclosure splitting for a file of this length.

Suggestions

Add the referenced style_check.sh / style_check.ps1 to a scripts/ bundle (or remove the commands) so the headline executable guidance is not broken.

Move the禁用词 and症状→处理 tables into a references/ file (e.g. DEAI_RULES.md) and keep SKILL.md as a concise overview pointing to them, improving progressive disclosure.

Trim the basic paragraph-construction section (主题句/支撑句/收束句) and the long 1.4 prose, which restate general writing knowledge Claude already has.

Dimension	Reasoning	Score
Conciseness	Most content is domain-specific and earns its place (禁用词/症状处理 tables, three-round checklist), but the standard paragraph-construction section (主题句/支撑句/收束句) explains basics Claude already knows and the long 1.4 prose plus repeated emphasis blocks could be tightened.	2 / 3
Actionability	Concrete禁用词 lists, a症状→处理 table, checkbox checklists, and exact bash/PowerShell commands are actionable, but the headline executable artifact (research-writing-skill/scripts/style_check.sh) is referenced without existing in the bundle, leaving the main script guidance incomplete.	2 / 3
Workflow Clarity	The three-round quality check (结构→语言→排版) is a clearly sequenced verification workflow with explicit checkboxes, and section 1.4 gives a defined handling order (补回信息→调整语序→收束判断) that acts as a feedback loop.	3 / 3
Progressive Disclosure	The file is well-organized into eight sections with no nested references, but at ~160 lines it is monolithic — the禁用词/症状 tables and style-check details are inline rather than split into reference files, and the referenced scripts/ and plan/ paths are not present in the bundle.	2 / 3
	Total	9 / 12 Passed

Description

82%Weight 40%Scale 1-3

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, explicit "Use when ..." description with good natural trigger coverage and a clear niche, slightly held back by listing quality dimensions rather than discrete concrete actions and by some overlap with generic writing/formatting skills.

Dimension	Reasoning	Score
Specificity	It names the domain ("writing or revising academic papers", "Chinese journal manuscripts") and lists capability concerns ("natural prose, de-AI-ification, Markdown formatting, or quality checks"), but the concrete verbs are only writing/revising while the rest are quality dimensions rather than discrete operations as in the 3-anchor "fill forms, merge documents" example.	2 / 3
Completeness	It opens with an explicit "Use when ..." trigger and states what the skill handles (natural prose, de-AI-ification, Markdown formatting, quality checks), clearly answering both what and when.	3 / 3
Trigger Term Quality	Natural user phrasing is well covered — "academic papers", "journal manuscripts", "writing", "revising", "Markdown formatting", "quality checks" — alongside the niche "de-AI-ification" term its target users would actually say.	3 / 3
Distinctiveness Conflict Risk	The Chinese-journal and de-AI-ification niche is fairly specific, but "Markdown formatting" and "quality checks" overlap with general writing/formatting skills, so it could still trigger for adjacent skills.	2 / 3
	Total	10 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: Norman-bury/research-writing-skill
Path: skills/writing-core/SKILL.md
Commit: 6f79595

Reviewed: 10 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.