document-gen-resilient-workflow

Multi-engine document generation with cascading PDF fallbacks and robust Unicode handling

Quality

68%

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-2794b4/SKILL.md

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.

The content is highly actionable with a clear, validated multi-step workflow and strong error-recovery fallback chains. Its weaknesses are verbosity from an inlined duplicate 'Complete Example' and the lack of progressive disclosure — large scripts and reference tables sit inline rather than in separate files.

Suggestions

Move the reusable Python sanitizer, reportlab, and fpdf2 scripts plus the Unicode/engine reference tables into separate files under scripts/ and references/, linking to them from SKILL.md to improve progressive disclosure.

Remove or collapse the 'Complete Example' section, which duplicates the Step-by-Step workflow, or replace it with a pointer and only the few lines that differ.

Make the Complete Example fully self-contained by replacing the '[Python sanitizer script from Step 2 above]' placeholder with the actual script or an explicit import reference.

Dimension	Reasoning	Score
Conciseness	The 382-line body is mostly useful but padded: the 'Complete Example' (lines 262-314) largely duplicates the Step-by-Step workflow, and full Python scripts (sanitizer, reportlab, fpdf2) are inlined. It is not 2 because it does not explain concepts Claude already knows (what a PDF/LaTeX is), and not 4 because the duplication and inline scripts could clearly be trimmed.	3 / 5
Actionability	It provides concrete, executable guidance — exact pandoc commands with --pdf-engine flags, full Python scripts, and explicit run_shell/write_file invocations. It is not 5 because the 'Complete Example' contains a non-executable placeholder ('[Python sanitizer script from Step 2 above]') and the reportlab block is labeled a 'basic implementation' rather than complete.	4 / 5
Workflow Clarity	Steps 1-4 are clearly sequenced with explicit validation checkpoints (Step 4 runs four checks including fitz-based PDF validation and python-docx DOCX validation) and explicit fallback feedback loops ('If pdflatex fails... Attempt 2'). This matches the anchor for clear sequence with explicit validation and error-recovery loops.	5 / 5
Progressive Disclosure	The body is well-sectioned (When to Use, Core Technique, Unicode Guide, Step-by-Step, Troubleshooting) but all content lives in one inline 382-line file with no bundle files or external references; the Python scripts and engine tables that belong in separate reference files are inlined. It is not 4 because there is no offloading of bulk content to one-level-deep references.	3 / 5
	Total	15 / 20 Passed

Description

66%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 fairly distinctive, naming multi-engine generation, cascading PDF fallbacks, and Unicode handling. Its main weakness is the missing 'Use when...' trigger clause, which caps completeness at 3.

Suggestions

Add an explicit 'Use when...' trigger clause naming the situations and terms that should activate this skill (e.g., 'Use when PDF generation fails, when documents contain non-ASCII characters, or when the user mentions .docx/.pdf/.html generation with encoding issues').

Include natural trigger synonyms and file extensions (.pdf, .docx, .html, LaTeX, encoding errors) to broaden keyword coverage toward a 5.

Use action verbs ('Generates documents across engines, falls back through PDF engines, sanitizes Unicode') to turn noun-phrase features into concrete actions.

Dimension	Reasoning	Score
Specificity	The description names several specific capabilities — 'Multi-engine document generation', 'cascading PDF fallbacks', 'robust Unicode handling' — giving concrete feature coverage. It stays at 4 rather than 5 because capabilities are noun-phrase features with no action verbs, and coverage of the multi-format scope (docx/html) is implied rather than listed.	4 / 5
Completeness	It clearly states 'what' (multi-engine document generation with cascading PDF fallbacks and Unicode handling) but has no 'when'/'Use when...' clause, so per the judging guideline a missing explicit trigger caps completeness at 3. It is not 4 because 'when' guidance is entirely absent rather than merely weak.	3 / 5
Trigger Term Quality	It includes natural terms users would say — 'document generation', 'PDF', 'fallbacks', 'Unicode' — giving good keyword coverage. It is not 5 because file extensions (.pdf, .docx, .html) and common synonyms like 'LaTeX' or 'encoding' are absent.	4 / 5
Distinctiveness Conflict Risk	'Multi-engine document generation with cascading PDF fallbacks' carves a fairly distinct niche unlikely to trigger generic skills. It is not 5 because the body references closely related siblings ('document-gen-unicode-safe', 'document-gen-fallback') indicating real overlap risk with that skill family.	4 / 5
	Total	15 / 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-2794b4/SKILL.md
Commit: 3827781

Reviewed: 8 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.