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.

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

85%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 well-structured, executable LaTeX compilation workflow with strong validation feedback loops and clear progressive structure. Conciseness and actionability are slightly held back by minor explanatory prose and a couple of pseudocode/templated elements.

Suggestions

Replace the Step 4 pseudocode loop with an actual shell loop or concrete retry sequence to make it fully executable.

Tighten the explanatory prose around error patterns and venue page-count rules to reduce token overhead while keeping the operational specifics.

Dimension	Reasoning	Score
Conciseness	The body is largely efficient commands, tables, and error-pattern fixups assuming Claude's competence; minor explanatory prose and venue-specific date detail could be trimmed, placing it just below anchor 5.	4 / 5
Actionability	Concrete, copy-paste-ready bash and python snippets plus specific error-message fixes cover common cases; the for-loop in Step 4 is pseudocode and $ARGUMENTS is templated, leaving minor gaps versus anchor 5.	4 / 5
Workflow Clarity	A clear eight-step sequence with explicit validation checkpoints (Step 5 checklists, pdftotext page verification in Step 6) and a feedback loop ("Stuck after 2 attempts?" / iterative fix loop) matches anchor 5.	5 / 5
Progressive Disclosure	No bundle files exist and the skill is self-contained with well-organized sections (Constants, numbered Workflow steps, Key Rules, Venue table) and no nested references, satisfying the simple-skill exception at anchor 5.	5 / 5
	Total	18 / 20 Passed

Description

82%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 strong, with an explicit what/when structure and concrete bilingual trigger phrases that minimize conflict risk. Specificity is the weakest dimension because the listed actions are somewhat generic compared to a fully enumerated capability list.

Suggestions

Expand the action list with more specific capabilities (e.g., "resolve missing packages and undefined references, embed fonts, verify page limits") to lift specificity toward anchor 4-5.

Consider adding the .tex file extension and a phrase like "LaTeX submission" to round out trigger term coverage.

Dimension	Reasoning	Score
Specificity	"Compile LaTeX paper to PDF, fix errors, and verify output" names the domain plus three actions, matching anchor 3's domain-plus-concrete-actions pattern; the actions are somewhat generic ("fix errors", "verify output") and lack the comprehensive specificity of anchor 4.	3 / 5
Completeness	Both "what" (compile, fix, verify) and "when" ("Use when user says...") are answered explicitly with concrete trigger phrases, matching the anchor 5 example pattern.	5 / 5
Trigger Term Quality	Explicit natural phrases "编译论文", "compile paper", "build PDF", "生成PDF" give good keyword coverage with synonyms and bilingual variants, though the .tex extension and a few common phrasings are absent.	4 / 5
Distinctiveness Conflict Risk	A clear LaTeX-paper-compilation niche with distinct triggers and minimal overlap with other skills.	5 / 5
	Total	17 / 20 Passed

Validation

87%

Warnings & errors only

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

Validation — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: wanshuiyin/Auto-claude-code-research-in-sleep
Path: skills/paper-compile/SKILL.md
Commit: f4f20f9

Reviewed: 1 day ago

Table of Contents

Discovery Implementation Validation

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.