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.

62

Quality

74%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Critical

Do not install without reviewing

Fix and improve this skill with Tessl

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

Quality

Content

70%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 multi-step workflow with strong validation checkpoints, but the single large SKILL.md inlines content that should be split into referenced files and repeats some guidance. Conciseness and progressive disclosure are the weakest dimensions.

Suggestions

Move the inlined venue template snippets and section-specific guideline blocks into the referenced templates/ and ../shared-references/ files, keeping SKILL.md a concise overview that points to them.

De-duplicate the writing-principles and de-AI watch-word lists, which appear both in Step 5 and in the 'Writing Quality Reference' section.

Replace the comment-pseudocode Python bib-cleaning block with an actual executable script under scripts/ so the guidance is copy-paste ready.

DimensionReasoningScore

Conciseness

Mostly actionable but padded: the writing-principles/de-AI watch-word lists appear twice (Step 5 and 'Writing Quality Reference'), and venue template snippets that the skill says live in templates/ are inlined, so it could be tightened.

3 / 5

Actionability

Rich concrete guidance — LaTeX documentclass snippets, DBLP/CrossRef curl commands, a spawn_agent block — but the Python bib-cleaning example is comment-pseudocode rather than executable code, a minor gap.

4 / 5

Workflow Clarity

Steps 0–8 are clearly sequenced with explicit validation checkpoints (backup before overwrite, Step 3.5 restatement audit, Step 6 review feedback loop, and the Step 8 final checklist), matching the top anchor.

5 / 5

Progressive Disclosure

References to ../shared-references/*.md are clearly signaled and one-level deep, but substantial content that belongs in separate files (venue templates, section guidelines, de-AI lists) is inlined in this ~400-line SKILL.md, and the referenced templates/ and shared-references/ paths are not part of the bundle.

3 / 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.

A well-constructed description that clearly states both capability and trigger conditions with bilingual natural-language phrases. It is concise and distinct, with only minor gaps in action specificity and trigger synonym coverage.

DimensionReasoningScore

Specificity

Names the domain ('Draft LaTeX paper section by section from an outline') with one concrete action, but lists no further specific actions, so it is not comprehensive.

3 / 5

Completeness

Explicitly answers both what ('Draft LaTeX paper section by section from an outline') and when ('Use when user says ... or wants to generate LaTeX content from a paper plan') with concrete trigger phrases.

5 / 5

Trigger Term Quality

Good natural-keyword coverage with bilingual synonyms ('写论文', 'write paper', 'draft LaTeX', '开始写'), though it misses common variants like '.tex' or 'write manuscript'.

4 / 5

Distinctiveness Conflict Risk

The LaTeX-from-outline niche is mostly distinct, but the generic 'write paper' trigger carries minor overlap risk with non-LaTeX writing 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

referenced_paths_exist

Referenced path issues: 1 missing

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.