CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

61

Quality

73%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/skills-codex-gemini-review/paper-write/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

67%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.

The content is a thorough, mostly actionable workflow with strong sequencing and several validation checkpoints. Its main weaknesses are length/repetition that could be trimmed and a referenced templates/ bundle directory that does not exist in the skill package.

Suggestions

Trim rationale padding and the testing anecdote, and deduplicate the De-AI watch-words between Step 5 and the Writing Quality Reference section to improve conciseness.

Add an explicit compile-validation feedback loop in Step 8 (run latexmk, on error fix and recompile) to close the workflow-clarity gap for this destructive/batch skill.

Resolve the templates/ reference: either bundle the venue template files or reword the body so it does not imply a bundled directory that is absent, since no bundle files ship with the skill.

DimensionReasoningScore

Conciseness

The body is ~340 lines with useful domain-specific guidance, but includes rationale padding ('Why this matters'), a testing anecdote ('948 lines → 215 lines in testing'), and repetition between Step 5, the Key Rules, and the Writing Quality Reference section that could be tightened.

3 / 5

Actionability

Provides concrete executable LaTeX snippets, real curl commands for DBLP/CrossRef, and an MCP review-call block; the only gap is the Python bib-cleaning block which is comment-style pseudocode rather than runnable code.

4 / 5

Workflow Clarity

Steps 0-8 are clearly sequenced with a backup checkpoint for the destructive overwrite, a Gemini review feedback loop (Step 6), a reverse-outline check (Step 7), and a final checklist (Step 8); the minor gap is that an explicit compile-and-fix loop (run latexmk → fix → recompile) is stated as a goal rather than a verified step.

4 / 5

Progressive Disclosure

Good section structure with well-signaled one-level-deep references (shared-references/output-versioning.md, output-manifest.md, output-language.md) and external attribution links; the gap is that the body references a bundled templates/ directory and figures/latex_includes.tex that are not present in the bundle.

4 / 5

Total

15

/

20

Passed

Description

78%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.

The description is well-structured in third person with an explicit 'Use when' trigger clause and concrete bilingual trigger phrases, giving strong completeness and trigger quality. Specificity is the weakest dimension since it names only one high-level action rather than several concrete capabilities.

Suggestions

Expand the action list to mention concrete capabilities (e.g., compile-ready section generation, verified DBLP/CrossRef bibliography fetching, Gemini cross-review) so specificity reaches the top anchor.

Add a natural file-extension trigger like '.tex' or 'compile LaTeX' to round out trigger-term coverage.

Sharpen distinctiveness by foregrounding the LaTeX/outline-from-plan specificity earlier to reduce overlap with generic paper-writing skills.

DimensionReasoningScore

Specificity

Names the domain ('LaTeX paper') and one concrete action ('Draft ... section by section from an outline'), but does not enumerate several distinct actions like compiling, citation handling, or review iteration.

3 / 5

Completeness

Explicitly states what it does ('Draft LaTeX paper section by section from an outline') and gives a concrete 'Use when ...' trigger clause listing specific phrases, satisfying both what and when.

5 / 5

Trigger Term Quality

Includes multiple natural trigger phrases users would actually say ('write paper', 'draft LaTeX', '开始写', '写论文') with bilingual synonyms, though it omits file-extension terms like '.tex' or 'compile'.

4 / 5

Distinctiveness Conflict Risk

The LaTeX-drafting-from-plan niche is fairly distinct with specific triggers, though 'write paper' has minor overlap risk with general academic-writing or planning skills.

4 / 5

Total

16

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 3 suspicious

Warning

Total

15

/

16

Passed

Repository
wanshuiyin/Auto-claude-code-research-in-sleep
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.