aris-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

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

77%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 body is highly actionable with executable commands, real error patterns, and a well-sequenced iterative workflow with validation checkpoints. Its weaknesses are conciseness (some boilerplate Claude already knows) and progressive disclosure (everything inlined with no bundle files for the large venue/error reference data).

Suggestions

Move the Common Venue Requirements table and the Step 3 error-diagnosis catalog into a separate references/ file (e.g., VENUES.md) and link to it, improving progressive disclosure and token efficiency.

Trim the LaTeX installation instructions (brew/apt/conda) and the lengthy ML-vs-IEEE page-count prose to one-line pointers, since Claude already understands these concepts.

Condense the Key Rules section, which repeats page-count rules already detailed in Step 6 and the venue table, to reduce redundancy.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with concrete commands, but includes content Claude likely already knows (LaTeX install instructions for macOS/Ubuntu/conda, extended ML vs IEEE page-count rules), matching anchor 3 rather than 4.	3 / 5
Actionability	It provides fully executable, copy-paste-ready commands (latexmk, pdftotext + python3 snippet, grep checks) and concrete error snippets with specific fixes across common cases, matching anchor 5.	5 / 5
Workflow Clarity	An explicit 8-step sequence with an iterative fix loop (compile -> parse errors -> fix -> recompile, capped at MAX_COMPILE_ATTEMPTS) and validation checklists in Steps 5 and 7 matches anchor 5's clear sequence with feedback loops.	5 / 5
Progressive Disclosure	No bundle files exist (references/, scripts/, assets/ are absent) and all ~250 lines are inlined in SKILL.md, including a venue-requirements table and an error-diagnosis catalog that could be split into separate files; this matches anchor 3 rather than 4.	3 / 5
	Total	16 / 20 Passed

Description

95%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: it states concrete capabilities and provides explicit, natural (bilingual) trigger phrases covering both "what" and "when". It is distinct and low conflict risk. Minor room for more comprehensive action enumeration but otherwise excellent.

Dimension	Reasoning	Score
Specificity	"Compile LaTeX paper to PDF, fix errors, and verify output" names the domain and three concrete actions (compile, fix errors, verify), matching anchor 4; not a 5 because the actions are not exhaustively comprehensive (e.g., page-limit verification is implied, not listed).	4 / 5
Completeness	It clearly answers "what" (compile to PDF, fix errors, verify output) and explicitly answers "when" via the "Use when user says..." clause with concrete trigger phrases, matching anchor 5.	5 / 5
Trigger Term Quality	"编译论文", "compile paper", "build PDF", "生成PDF" provide comprehensive natural synonyms including bilingual variants users would actually say, matching anchor 5's coverage of natural terms and synonyms.	5 / 5
Distinctiveness Conflict Risk	It targets a clear niche (LaTeX-to-submission-ready-PDF compilation) with distinct, specific triggers, giving minimal overlap risk with other skills per anchor 5.	5 / 5
	Total	19 / 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: OpenLAIR/dr-claw
Path: skills/aris-paper-compile/SKILL.md
Commit: 4b35756

Reviewed: 5 days 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.