CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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
SecuritybySnyk

Passed

No findings from the security scan

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 highly actionable, well-sequenced compile workflow with excellent validation and feedback loops. Its weaknesses are redundancy — the venue page-count rule is repeated three times — and the absence of any progressive disclosure: a 250-line monolith where the venue table and error catalog could live in reference files.

Suggestions

State the ML-vs-IEEE page-count rule once (e.g., in the MAX_PAGES bullet or the venue table) and reference it from Step 6 and Key Rules instead of repeating it verbatim three times.

Move the Common Venue Requirements table and the Step 3 error-diagnosis catalog into references/ files (e.g., references/venues.md, references/error-fixes.md) with one-line pointers from SKILL.md.

Replace the pseudocode loop in Step 4 with an executable equivalent (a bash while-loop over compile attempts or a small script) so every instruction block is copy-paste runnable.

DimensionReasoningScore

Conciseness

Mostly efficient — dense commands, checklists, and tables with no concept-teaching padding — but the ML-vs-IEEE page-count distinction is stated three times (MAX_PAGES bullet, Step 6, Key Rules) in addition to the venue table, and the stale-file rationale paragraph could be trimmed. Anchor 3 rather than 4 because the repetition is a genuine tightening target, not a minor trim.

3 / 5

Actionability

Nearly all guidance is copy-paste executable (latexmk, grep, pdfinfo, pdftotext+python3, pdffonts, the shell loop in Step 6.5), with real error-message examples mapped to fixes. Not a 5 because Step 4's fix loop is pseudocode ("for attempt in 1..MAX_COMPILE_ATTEMPTS: compile()...") rather than an executable command or script.

4 / 5

Workflow Clarity

Eight clearly sequenced steps with an explicit iterative fix loop capped at MAX_COMPILE_ATTEMPTS, a rescue-on-repeat-failure checkpoint, post-compilation verification checklists, and a precise page-count validation procedure. This matches the top anchor: feedback loops, checkpoints, and checklists are all present.

5 / 5

Progressive Disclosure

No bundle files exist and the skill is a single ~250-line document. Structure within the file is good (numbered steps, section headers), but content that would fit a separate reference — the venue requirements table and the per-error diagnosis catalog — is inlined. Anchor 3 rather than 2 because the inline organization is clear and navigable, not a wall of text.

3 / 5

Total

15

/

20

Passed

Description

87%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 strong description: concrete actions, explicit bilingual trigger phrases, and a clear what+when structure in third person. The only weaknesses are modest — a few natural synonyms are absent and the description undersells the submission-readiness checks the body actually performs.

DimensionReasoningScore

Specificity

Names the LaTeX domain and three concrete actions ("Compile LaTeX paper to PDF, fix errors, and verify output"). Not a 5 because coverage has minor gaps — page-limit verification and submission-readiness checks done by the skill are absent from the description.

4 / 5

Completeness

Clearly answers both questions: the "what" is three explicit actions and the "when" is a concrete "Use when user says [phrases]" clause with natural trigger terms. Matches the top anchor exactly.

5 / 5

Trigger Term Quality

Good natural trigger coverage with bilingual variants ("编译论文", "compile paper", "build PDF", "生成PDF") plus the explicit phrase "compile LaTeX into a submission-ready PDF". Not a 5 because common synonyms like "recompile", "pdflatex", or "compile the tex" are missing.

4 / 5

Distinctiveness Conflict Risk

Clear niche (LaTeX-to-PDF compilation) with distinct, unambiguous triggers that would not fire for adjacent paper-writing or PDF-extraction skills. Minimal conflict risk.

5 / 5

Total

18

/

20

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

wanshuiyin/Auto-claude-code-research-in-sleep

Path

skills/skills-codex/paper-compile/SKILL.md

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.