paper-write

Draft LaTeX paper section by section from an outline. Use when user says "写论文", "write paper", "draft LaTeX", "开始写", or wants to generate LaTeX content from a paper plan.

Quality

81%

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

81%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 thorough, highly actionable skill with excellent workflow clarity and validation loops for a fragile multi-step task. Its main weakness is length and some redundancy, plus progressive-disclosure structure that relies on out-of-tree shared references rather than bundled files.

Suggestions

Collapse the 'Key Rules' list and the 'CONFIDENT PROSE, HONEST LIMITS' block, which restate each other, into a single section to cut ~60 lines of redundancy.

Move the bulk of the 'CONFIDENT PROSE, HONEST LIMITS' rules and the acknowledgements into a shared-references file linked once, keeping the inline body lean.

Bundle the referenced ../shared-references/*.md files (or at least writing-principles.md and venue-checklists.md) inside the skill so the one-level-deep references resolve within the skill directory.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and packed with domain-specific guidance Claude would not already know (venue templates, bib fetch chains, writing audits), but the ~670-line body has some redundancy — the CONFIDENT PROSE block is restated in Key Rules and acknowledgements add length — and could be tightened.	3 / 5
Actionability	Provides copy-paste-ready LaTeX, bash, and Python snippets (venue setup, DBLP/CrossRef fetch chain, bib-hygiene validator) covering the common cases exhaustively.	5 / 5
Workflow Clarity	Eight clearly sequenced steps with explicit validation checkpoints and feedback loops (Step 3.5 restatement audit, bib hygiene validation, Step 6 cross-review, Step 8 final checklist) for destructive/batch operations like overwriting paper/ and rebuilding the bibliography.	5 / 5
Progressive Disclosure	Body signals one-level-deep references (../shared-references/*.md, templates/, helper scripts) and splits content into well-organized sections, but no bundle files are present in the skill directory and references point outside it, with some referenceable bulk (the full Key Rules / CONFIDENT PROSE blocks) kept inline.	4 / 5
	Total	17 / 20 Passed

Description

82%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 concise, third-person description that clearly states capability and trigger conditions with concrete multilingual trigger phrases. Its only weakness is that the 'what' names a single composite action rather than enumerating the specific sub-tasks the skill performs.

Dimension	Reasoning	Score
Specificity	"Draft LaTeX paper section by section from an outline" names the domain and one concrete action, but coverage is limited to a single drafting action without listing sub-actions (bibliography, figures, review passes).	3 / 5
Completeness	Explicitly answers both what (draft LaTeX paper section by section from an outline) and when (a full "Use when..." clause with concrete trigger phrases).	5 / 5
Trigger Term Quality	Includes natural multilingual triggers users would actually say ("写论文", "write paper", "draft LaTeX", "开始写") plus a paraphrased intent, giving good keyword coverage with only minor synonym gaps.	4 / 5
Distinctiveness Conflict Risk	Targets a clear niche (LaTeX paper drafting from an outline) with distinct triggers unlikely to fire for unrelated skills.	5 / 5
	Total	17 / 20 Passed

Validation

75%

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 — 12 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (683 lines); consider splitting into references/ and linking	Warning
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
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	12 / 16 Passed

Repository: wanshuiyin/Auto-claude-code-research-in-sleep
Path: skills/paper-write/SKILL.md
Commit: f1bd907

Reviewed: 5 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.