document-gen-resilient-workflow

Robust document generation with engine fallback chain, error diagnostics, and Python alternatives

Quality

69%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Medium

Suggest reviewing before use

Fix and improve this skill with Tessl

tessl review fix ./benchmarks/gdpval/skills/document-gen-fallback-enhanced-enhanced/SKILL.md

Quality

Content

66%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 clear, well-validated fallback workflow, but it is verbose and inlines large reference-style material (Unicode table, sanitization script, full example) that should live in separate bundle files. Trimming duplication and splitting references would materially raise the score.

Suggestions

Move the full Unicode replacement table and the sanitization script into a references/ file (e.g., references/unicode-sanitization.md) and link to it from the body, keeping only a short inline summary.

Remove the redundant 'Complete Example' and 'Quick Reference Card' sections, or collapse them into a single concise quick-start — they restate the step-by-step workflow already present.

Cut explanatory prose about what 'unknown error' or sandbox contexts mean; assume Claude's competence and keep only the diagnostic commands and the fallback decision logic.

Dimension	Reasoning	Score
Conciseness	The ~500-line body is noticeably verbose: the 'Complete Example' and 'Quick Reference Card' largely duplicate the step-by-step workflow, the Unicode table appears twice, and troubleshooting prose explains concepts (sandbox context, 'unknown error') Claude already knows.	2 / 5
Actionability	Fully executable, copy-paste-ready guidance throughout — concrete pandoc commands with stderr capture, a complete sed sanitization script, and working fpdf2/python-docx fallback code covering the common PDF/DOCX cases.	5 / 5
Workflow Clarity	A clearly sequenced 7-step core process with progressive engine fallback (pandoc → xelatex → wkhtmltopdf → Python), explicit validation in Step 5, and an error-diagnosis guide providing feedback loops (try → check log → next engine).	5 / 5
Progressive Disclosure	No bundle files exist and the entire skill is one inlined monolith; the full Unicode table, sanitization script, complete example, and error guide are content that clearly belongs in separate reference files but are not split out.	2 / 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 conveys concrete capabilities and a reasonably distinct niche, but it lacks any 'when to use' trigger guidance and uses procedural language over natural user keywords. Adding a 'Use when...' clause with format-specific terms would substantially improve it.

Suggestions

Append a 'Use when...' clause naming concrete triggers, e.g. 'Use when PDF/DOCX generation fails with LaTeX or engine errors, or when pandoc conversion needs a fallback.'

Add natural user keywords and file extensions (PDF, DOCX, .pdf, .docx, 'convert to PDF') so the skill matches how users phrase the request.

Lead with the primary outcome ('Generate PDF/DOCX/HTML documents') before the resilience mechanics so the core capability is immediately clear.

Dimension	Reasoning	Score
Specificity	Lists several concrete capabilities — 'engine fallback chain', 'error diagnostics', and 'Python alternatives' for document generation — with only minor gaps in format coverage (no explicit PDF/DOCX mention).	4 / 5
Completeness	Clearly states the 'what' (resilient document generation with fallback and diagnostics) but provides no 'Use when...' or equivalent trigger guidance, capping completeness at 3 per the rubric.	3 / 5
Trigger Term Quality	Includes relevant terms like 'document generation' and 'error diagnostics' but leans technical/procedural and omits natural user phrases and file extensions (e.g., PDF, DOCX, .pdf) that users would actually say.	3 / 5
Distinctiveness Conflict Risk	The fallback-chain and error-diagnostics framing carves a mostly distinct niche with only minor overlap risk against generic document-generation skills.	4 / 5
	Total	14 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (503 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

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

Reviewed: 9 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.