document-gen-resilient-multiformat

Resilient multi-format document generation with environment checks, auto-sanitization, and fallback engines

Quality

60%

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-618c9b/SKILL.md

Quality

Content

62%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 skill is highly actionable with a well-sequenced, validated workflow and explicit error-recovery feedback loops, but it is noticeably verbose with repeated sections and keeps all reference material inline rather than splitting it into bundle files. Tightening duplication and externalizing reference content would materially improve it.

Suggestions

Remove the duplicated pre-flight check (it appears in 'Pre-Flight Environment Check', 'Step 0', and the 'Complete Example') — keep one canonical version and reference it.

Move the pandoc command reference, troubleshooting quick reference, and the sanitization script into separate files under scripts/ and references/, linking to them from SKILL.md to improve progressive disclosure.

Delete or condense the near-redundant 'When to Use shell_agent vs Manual Workflow' and 'Common pandoc Commands Reference' sections, which restate guidance already covered elsewhere.

Dimension	Reasoning	Score
Conciseness	At ~470 lines the body is noticeably verbose with redundant sections — the pre-flight check appears three times (Pre-Flight Environment Check, Step 0, and the Complete Example) and the troubleshooting/error-handling/pandoc-reference material repeats guidance already covered.	2 / 5
Actionability	Concrete, mostly copy-paste-ready pandoc commands, Python fallback code, and a full bash sanitization script cover the common cases; the only gap is Option C which is explicitly labeled 'simplified' and does not actually parse the markdown into the story.	4 / 5
Workflow Clarity	Steps 0–4 are explicitly sequenced with a verification checkpoint (Step 4 checks outputs exist and are non-empty) and a clear engine-fallback feedback loop (xelatex → pdflatex → wkhtmltopdf → Python) plus a decision tree and error-recovery workflow.	5 / 5
Progressive Disclosure	No bundle files exist (references/scripts/assets absent) and all content is inlined in one monolithic SKILL.md; section headers give some structure, but reference-style material (pandoc command reference, troubleshooting, sanitization script, Python examples) that belongs in separate files is inlined with no one-level-deep references signaled.	3 / 5
	Total	14 / 20 Passed

Description

58%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 clearly conveys what the skill does and lists several specific features, but it omits any explicit 'when to use' trigger guidance and lacks natural user-facing keywords like file extensions. It is mostly distinct but would benefit from a Use-when clause.

Suggestions

Add an explicit 'Use when...' clause with concrete triggers (e.g., 'Use when generating .docx/.pdf/.html from one source, or when pandoc/LaTeX PDF generation fails with encoding errors').

Include natural file-extension keywords (.docx, .pdf, .html) and synonyms users actually say to raise trigger-term quality.

Replace jargon like 'auto-sanitization' and 'fallback engines' with user-facing phrasing such as 'handles special characters' and 'falls back to Python when pandoc is missing'.

Dimension	Reasoning	Score
Specificity	Names the domain ('multi-format document generation') and several specific concrete features ('environment checks, auto-sanitization, and fallback engines'), though these are feature attributes rather than a comprehensive list of discrete actions.	4 / 5
Completeness	The 'what' is clear (multi-format document generation with environment checks, auto-sanitization, fallback engines) but there is no 'Use when...' trigger clause, so 'when' is missing and completeness is capped at 3 per the rubric guideline.	3 / 5
Trigger Term Quality	'document generation' and 'multi-format' are natural terms, but file extensions (.docx/.pdf/.html) and common synonyms are absent, and 'auto-sanitization'/'fallback engines' read as technical jargon rather than phrases users say.	3 / 5
Distinctiveness Conflict Risk	The 'resilient/multi-format/auto-sanitization/fallback' framing carves a fairly distinct niche, with only minor overlap risk against closely related document-gen skills.	4 / 5
	Total	14 / 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-618c9b/SKILL.md
Commit: 3827781

Reviewed: 25 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.