CtrlK
BlogDocsLog inGet started
Tessl Logo

paper-compile

Compile LaTeX paper to PDF, fix errors, and verify output. Use when user says \"编译论文\", \"compile paper\", \"build PDF\", \"生成PDF\", or wants to compile LaTeX into a submission-ready PDF.

72

Quality

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Quality

Content

77%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A highly actionable, well-sequenced compile workflow with strong validation feedback loops, though it leans monolithic and repeats venue page-count guidance in several places that could be tightened or moved to a reference file.

Suggestions

Consolidate the venue page-count rules (stated in Constants, Step 6, Key Rules, and the table) into a single source to reduce repetition and save tokens.

Extract the error-message-to-fix catalog and the Common Venue Requirements table into a references/ file (e.g. VENUES.md) and link to it, improving progressive disclosure.

Trim the inline pdftotext Python snippet to the essential logic or move it to a script, since the surrounding prose already explains the page-boundary detection.

DimensionReasoningScore

Conciseness

Mostly efficient with executable commands and tables, but venue page-limit rules and style-file tables are restated in multiple places and the inline pdftotext Python is heavier than needed, leaving room to tighten.

2 / 3

Actionability

Provides copy-paste-ready shell commands, concrete error-message-to-fix mappings, and a venue requirements table — fully executable guidance throughout.

3 / 3

Workflow Clarity

Eight clearly sequenced steps with validation checkpoints, an iterative fix loop, automated post-compile checklists, and a RESCUE_ON_REPEAT_FAILURE feedback loop for error recovery.

3 / 3

Progressive Disclosure

Well-organized into sections, but it is a monolithic single-file skill with no bundle files to offload the lengthy venue table, error-fix catalog, or page-count logic that would fit better in references.

2 / 3

Total

10

/

12

Passed

Description

100%

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 tight, third-person description with concrete actions and explicit bilingual trigger phrases that cleanly answer both what and when. It is distinct from sibling paper skills and avoids over-claiming.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — "Compile LaTeX paper to PDF, fix errors, and verify output" — naming the exact build/fix/verify cycle rather than vague language.

3 / 3

Completeness

Explicitly states both what it does (compile/fix/verify) and when to use it via the "Use when user says..." trigger clause, satisfying the full what-and-when bar.

3 / 3

Trigger Term Quality

Covers natural phrasings a user would actually say: "编译论文", "compile paper", "build PDF", "生成PDF", giving good coverage including bilingual variations.

3 / 3

Distinctiveness Conflict Risk

A clear LaTeX-to-PDF niche with distinct, compilation-specific triggers unlikely to fire for unrelated skills like paper-writing.

3 / 3

Total

12

/

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

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.