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
88%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
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.
This is a strong skill description that concisely covers specific capabilities, includes bilingual trigger terms, and clearly delineates both what the skill does and when it should be used. It occupies a distinct niche (LaTeX compilation) that minimizes conflict risk with other skills. The third-person voice is used correctly throughout.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Compile LaTeX paper to PDF', 'fix errors', and 'verify output'. These are clear, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers both 'what' (compile LaTeX to PDF, fix errors, verify output) and 'when' (explicit 'Use when' clause with specific trigger phrases and a general condition about compiling LaTeX). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms in both English and Chinese: '编译论文', 'compile paper', 'build PDF', '生成PDF', 'compile LaTeX', 'submission-ready PDF'. These are terms users would naturally say. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche: LaTeX paper compilation to PDF. The specific mention of LaTeX, compilation, and submission-ready PDF makes it unlikely to conflict with general document or PDF manipulation skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a strong, highly actionable skill with excellent workflow clarity and concrete executable guidance for LaTeX compilation. Its main weakness is length — the venue table, installation instructions, and some explanatory text could be trimmed or split into reference files. The error diagnosis section is particularly well done, mapping exact log patterns to specific fixes.
Suggestions
Move the venue requirements table to a separate VENUES.md reference file and link to it, reducing the main skill's token footprint.
Trim installation instructions to a single line (e.g., 'If not installed, tell user to install texlive') since Claude can provide platform-specific instructions on demand.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is fairly comprehensive but includes some unnecessary verbosity — e.g., explaining what latexmk and pdflatex are, listing installation instructions Claude could infer, and the venue requirements table adds bulk. However, most content is genuinely useful domain-specific knowledge (page counting rules, IEEE vs ML conference differences) that Claude wouldn't inherently know. | 2 / 3 |
Actionability | The skill provides fully executable bash commands, concrete error messages with specific fixes, real code for page count verification, and copy-paste ready compilation commands. The error diagnosis section maps exact log output patterns to specific remediation steps. | 3 / 3 |
Workflow Clarity | The workflow is clearly sequenced (Steps 1-8) with explicit validation checkpoints: post-compilation checks with checklists, an iterative fix loop with MAX_COMPILE_ATTEMPTS, a rescue mechanism for repeated failures, and verification of undefined references/citations via log grep. The feedback loop (compile → parse errors → fix → recompile) is explicit. | 3 / 3 |
Progressive Disclosure | The content is a single monolithic file with no references to supporting documents, despite being ~200 lines long. The venue requirements table and detailed error diagnosis catalog could be split into separate reference files. However, the section structure is clear and well-organized with headers. | 2 / 3 |
Total | 10 / 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
a425a71
- 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.