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.
81
76%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Critical
Do not install without reviewing
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/skills-codex/paper-write/SKILL.mdQuality
Discovery
89%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a solid skill description that clearly communicates its purpose and provides explicit trigger guidance in both English and Chinese. Its main weakness is that the 'what' portion could be more specific about the concrete actions performed beyond 'draft section by section.' Overall, it would perform well in a multi-skill selection scenario.
Suggestions
Add more specific concrete actions to the capability description, e.g., 'generates section content with citations, equations, figures, and proper LaTeX formatting from an outline.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description names the domain (LaTeX paper drafting) and a key action (draft section by section from an outline), but doesn't list multiple specific concrete actions like formatting, adding citations, generating figures, or compiling. | 2 / 3 |
Completeness | Clearly answers both 'what' (draft LaTeX paper section by section from an outline) and 'when' (explicit 'Use when' clause with specific trigger phrases and a general condition about generating LaTeX from a paper plan). | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms in both English and Chinese: '写论文', 'write paper', 'draft LaTeX', '开始写', 'generate LaTeX content', 'paper plan'. These cover common variations users would naturally say. | 3 / 3 |
Distinctiveness Conflict Risk | The combination of LaTeX, paper drafting from an outline, and bilingual trigger terms creates a clear niche that is unlikely to conflict with general writing skills or generic LaTeX formatting skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
62%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a highly actionable and well-structured skill with excellent workflow clarity, clear validation checkpoints, and concrete executable examples throughout. However, it suffers significantly from verbosity — it's a monolithic document that explains many things Claude already knows (abstract structure, conclusion writing, basic LaTeX conventions) and repeats rules across multiple sections. The content would benefit greatly from aggressive trimming and splitting detailed guidelines into referenced sub-files.
Suggestions
Cut at least 40% of content by removing explanations of things Claude already knows (e.g., what an abstract should contain, how conclusions work, basic paragraph structure) and eliminating repeated rules (citation style appears 3+ times).
Move section-specific writing guidelines (§0-§5 details), the bibliography fetch chain, and the 5-pass quality audit into separate referenced files to reduce the main skill to an overview with clear pointers.
Remove the Acknowledgements section entirely — it wastes tokens and provides no actionable guidance for Claude.
Consolidate the de-AI patterns and scientific writing quality pass into a single concise checklist rather than listing them twice (once in Step 5 and again in the Writing Quality Reference section).
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose at ~400+ lines. It explains many concepts Claude already knows (what an abstract should contain, how to write a conclusion, basic LaTeX structure), includes lengthy acknowledgements, and repeats guidelines across multiple sections (e.g., citation style rules appear in at least 3 places). The de-AI writing patterns and scientific writing principles are things Claude inherently understands. | 1 / 3 |
Actionability | The skill provides highly concrete, executable guidance throughout: specific curl commands for DBLP/CrossRef fetching, complete LaTeX template snippets for each venue, a Python pattern for bib cleaning, exact file structures, specific spawn_agent syntax for cross-review, and detailed checklists. Nearly everything is copy-paste ready. | 3 / 3 |
Workflow Clarity | The workflow is clearly sequenced (Steps 0-8) with explicit validation checkpoints: backup before overwrite (Step 0), theory consistency pass (Step 3.5), five-pass quality audit (Step 5), cross-review with reviewer model (Step 6), reverse outline test (Step 7), and a comprehensive final checklist (Step 8). Error recovery is addressed (e.g., DBLP fallback chain, file size retry with bash). | 3 / 3 |
Progressive Disclosure | The skill references external files appropriately (writing-principles.md, venue-checklists.md, citation-discipline.md) with clear one-level-deep navigation. However, the main file itself is monolithic — the section-specific guidelines, bibliography workflow, and writing quality pass could each be separate referenced files. The inline content is far too long for a single SKILL.md. | 2 / 3 |
Total | 9 / 12 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 — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Commit
700fbe2
- 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.