paper-latex-sanitizer

Deterministically normalize safe LaTeX punctuation and replace unsupported forecast magnitudes with explicit placeholders before meta-paper-write publication gates run.

Quality

71%

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

Fix and improve this skill with Tessl

tessl review fix ./src/opensquilla/skills/bundled/paper-latex-sanitizer/SKILL.md

Quality

Content

80%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 an exceptionally lean, well-structured spec backed by a real executable script, scoring high on conciseness and progressive disclosure. Its main weakness is workflow clarity: a destructive atomic file-replacement step with no explicit validation/verification checkpoint is capped at 3 per the batch-operation rule.

Suggestions

Add an explicit verification checkpoint after the atomic MANUSCRIPT_PATH replacement (e.g. confirm the rewritten file parses and the manifest is returned) to lift the workflow-clarity cap.

Include one short before/after input-output example illustrating the punctuation and forecast-magnitude replacements to push actionability to 5.

Clarify the validate→fix→retry loop, or state explicitly that re-validation is delegated to paper-quality-gate as the next gated step.

Dimension	Reasoning	Score
Conciseness	The ~30-line body is lean and information-dense, assumes Claude's competence (no explaining what LaTeX/Unicode is), and every token earns its place, matching the lean-and-efficient anchor 5.	5 / 5
Actionability	Precise executable spec (exact codepoints U+2011/U+2013/U+2014, exact placeholders 'TBD'/'待实验确定', exact guard 'EVIDENCE_STATUS: not_supplied') backed by a real scripts/sanitize.py entrypoint, but lacks a before/after example, so anchor 4 with minor gaps fits better than 5.	4 / 5
Workflow Clarity	The two repairs and atomic MANUSCRIPT_PATH replacement are sequenced, but this destructive/batch file-rewrite has no in-skill validate→fix→retry checkpoint, so the missing-validation cap holds at 3 even though sequencing is present.	3 / 5
Progressive Disclosure	Under 50 lines, single-purpose, no references/assets dirs, the one external reference (scripts/sanitize.py) is real and clearly signaled via the entrypoint, with no nested references — matching the simple-skill anchor 5.	5 / 5
	Total	17 / 20 Passed

Description

62%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 specific and occupies a clearly distinct niche, but it is written in internal/meta jargon with no natural 'Use when...' user trigger, capping trigger-term quality and completeness at 3. It is strong on distinctiveness but misses the user-facing trigger phrasing the rubric rewards.

Suggestions

Add an explicit user trigger clause, e.g. 'Use when preparing a LaTeX manuscript for meta-paper-write publication and forecast evidence is not yet supplied'.

Include natural synonyms a user might say (e.g. 'LaTeX paper', 'manuscript', 'forecast numbers', 'results section') alongside the technical terms.

Consider framing the timing as a user condition rather than only a pipeline ordering constraint.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ('normalize safe LaTeX punctuation', 'replace unsupported forecast magnitudes with explicit placeholders', 'before publication gates run') with only minor coverage gaps, matching anchor 4 better than the 1-2-action anchor 3.	4 / 5
Completeness	The 'what' is clear, but the only 'when' is a process-ordering clause ('before publication gates run') rather than an explicit 'Use when...' user trigger, so per the missing-trigger-guidance cap it stays at 3.	3 / 5
Trigger Term Quality	Terms like 'LaTeX', 'forecast magnitudes', and 'publication gates' are domain-relevant but jargon-heavy and internal ('meta-paper-write'), missing the natural user phrasings and synonyms that anchor 4 requires.	3 / 5
Distinctiveness Conflict Risk	A narrow niche (LaTeX punctuation + forecast-magnitude placeholders tied to meta-paper-write) with minimal overlap risk matches the clear-niche anchor 5.	5 / 5
	Total	15 / 20 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	13 / 16 Passed

Repository: TokenRhythm/opensquilla
Path: src/opensquilla/skills/bundled/paper-latex-sanitizer/SKILL.md
Commit: 94ac35e

Reviewed: 3 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.