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 (e.g., generating sections, handling citations, formatting equations). Overall, it performs well on completeness and trigger terms.
Suggestions
Add more specific concrete actions to the capability description, e.g., 'generates title, abstract, introduction, methods, results, conclusion sections with proper LaTeX formatting, citations, and equations.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | It names the domain (LaTeX paper) and a key action (draft section by section from an outline), but doesn't list multiple concrete actions like compiling, formatting tables, adding citations, etc. | 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 excellent 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 comprehensive and highly actionable skill with excellent workflow structure and validation checkpoints. However, it suffers significantly from verbosity — it's essentially an entire paper-writing manual inlined into a single file, repeating information Claude already knows (academic writing conventions, what abstracts should contain) and duplicating rules across sections. The content would benefit greatly from aggressive trimming and splitting detailed guidelines into referenced sub-files.
Suggestions
Reduce verbosity by removing section-specific writing guidelines that Claude already knows (e.g., 'Abstract must be self-contained', 'Related work should synthesize not just list') — keep only project-specific rules like page targets and venue-specific formatting.
Eliminate repeated information: IEEE citation style (\cite vs \citep/\citet) is stated 3+ times, page limit rules are duplicated in Constants and Key Rules. State each rule once.
Move the De-AI polish word lists, section-specific guidelines, and citation verification rules into separate referenced files to reduce the main skill to a concise overview with clear pointers.
Remove the Acknowledgements section entirely — it wastes tokens and provides no actionable guidance for Claude.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose at ~400+ lines. It explains concepts Claude already knows (what an abstract is, what related work should do, basic LaTeX structure), includes lengthy acknowledgements, repeats rules in multiple places (e.g., IEEE vs natbib citation commands mentioned 3+ times), and includes unnecessary context like Python pseudocode comments for bib cleaning. Much of the section-specific guidelines are standard academic writing knowledge. | 1 / 3 |
Actionability | The skill provides highly concrete, executable guidance: specific curl commands for DBLP/CrossRef fetching, exact LaTeX document class declarations for each venue, complete file structures, specific spawn_agent syntax for cross-review, and a detailed checklist. Code examples are copy-paste ready and commands are specific. | 3 / 3 |
Workflow Clarity | The 8-step workflow is clearly sequenced with explicit validation checkpoints: Step 0 backs up before destructive operations, Step 4 has a 3-step fallback chain with verification, Step 6 provides cross-review with specific severity levels, Step 7 is a reverse outline validation test, and Step 8 is a comprehensive final checklist. Error recovery is addressed (e.g., DBLP → CrossRef → [VERIFY] fallback). | 3 / 3 |
Progressive Disclosure | The skill references external files appropriately (shared-references/writing-principles.md, venue-checklists.md, citation-discipline.md) and mentions templates in templates/. However, the main file itself is monolithic — the section-specific guidelines, de-AI polish patterns, citation verification rules, and venue templates could all be split into separate reference files. The inline content is far too long for a SKILL.md overview. | 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
dc00dfb
- 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.