document-gen-unicode-safe

Unicode-safe fallback workflow for multi-format document generation with character sanitization

Quality

37%

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 ./benchmarks/gdpval/skills/document-gen-fallback-enhanced-enhanced-c5d426/SKILL.md

Quality

Content

32%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 delivers real, concrete pandoc-based guidance but is severely overweight, contains duplicate sections, a corrupted embedded second-skill frontmatter (lines 346-347), and truncates mid-workflow. Validation is weak for a fragile batch/conversion process and no progressive disclosure is used despite ample content that belongs in separate files.

Suggestions

Remove the verbatim duplicate of the 4-step manual path (lines 67-70) and the stray embedded frontmatter (lines 346-347 'name: document-gen-adaptive-workflow / description: ...'), which appear to be a botched paste of a second skill.

Add a real validate->fix->retry loop for PDF conversion (check pandoc exit code, on failure retry with --pdf-engine=xelatex then wkhtmltopdf) instead of an 'ls -lh' existence check, and complete the truncated 'Manual Path: Step-by-Step Workflow' section at the end of the file.

Move the reusable sanitize_for_pdf.sh script, the Unicode replacement table, and the troubleshooting list into separate reference files under ./references/ and link to them, cutting the inline body roughly in half.

Dimension	Reasoning	Score
Conciseness	The 360-line body is noticeably verbose: it re-explains pandoc/LaTeX basics, repeats the 4-step manual path verbatim (lines 53-56 and again 67-70), and inlines a full bash sanitization script plus large duplicated example blocks that pad the context window.	2 / 5
Actionability	Concrete pandoc/sed commands and write_file blocks are provided, but several examples are placeholders ('[Content with original unicode...]', '[Content...]') rather than copy-paste-ready content, and the inline sed one-liner has unbalanced quotes that would fail to execute.	3 / 5
Workflow Clarity	A rough Quick/Manual path sequence exists with a verification step, but validation is shallow ('ls -lh' existence checks only), there is no validate->fix->retry feedback loop for the fragile LaTeX/PDF path, and the body truncates mid-section ('### Manual Path: Step-by-Step Workflow' at line 366 with no content), leaving the manual workflow incomplete.	2 / 5
Progressive Disclosure	No bundle files exist (references/scripts/assets absent), yet the skill inlines everything into a single monolithic 360-line wall: a reusable script, command reference tables, troubleshooting, and multiple full examples that clearly belong in separate files are all stuffed inline with buried navigation.	2 / 5
	Total	9 / 20 Passed

Description

42%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 grammatical and names a niche (Unicode-safe document generation with sanitization), but it lacks a 'Use when...' trigger clause and natural user-facing terms like 'Word', 'PDF', or 'docx'. It reads as a domain label rather than a complete, distinctive trigger statement.

Suggestions

Add an explicit 'Use when...' clause naming natural triggers, e.g. 'Use when generating Word/PDF/HTML documents that contain Unicode or special characters, or when pandoc/LaTeX PDF conversion fails on non-ASCII text.'

Include concrete output formats and file extensions (docx, .pdf, .html) so the description matches what users actually say.

Tighten distinctiveness by contrasting with the parent skill, e.g. 'Use instead of document-gen-fallback when content contains non-ASCII characters.'

Dimension	Reasoning	Score
Specificity	Names the domain ('multi-format document generation') and a concrete action ('character sanitization'), plus a fallback framing, but stops short of the multiple concrete actions (e.g. convert to docx/pdf/html) needed for a 4-5.	3 / 5
Completeness	It states clearly what the skill does but contains no 'Use when...' trigger clause, so the 'when' is only weakly implied — the missing trigger guidance caps completeness at 3 per the rubric.	3 / 5
Trigger Term Quality	'Unicode-safe' and 'multi-format document generation' are technical phrases; the description omits natural user terms like 'Word', 'PDF', 'docx', or 'convert markdown' that a user would actually say.	2 / 5
Distinctiveness Conflict Risk	'Unicode-safe ... character sanitization' carves a niche, but 'multi-format document generation' is broad enough to overlap with sibling document-gen skills, so overlap risk remains.	3 / 5
	Total	11 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: HKUDS/OpenSpace
Path: benchmarks/gdpval/skills/document-gen-fallback-enhanced-enhanced-c5d426/SKILL.md
Commit: 3827781

Reviewed: 17 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.