document-gen-unicode-safe

Unicode-safe fallback workflow for multi-format document generation with character sanitization and explicit error capture

Quality

69%

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/SKILL.md

Quality

Content

63%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 actionable, well-sequenced guidance with a genuine error-recovery feedback loop, but it is padded by a duplicated worked example and repeated engine guidance, and it keeps ~300 lines monolithically inline rather than splitting reference material into bundle files.

Suggestions

Remove or drastically trim the 'Complete Example' section, which restates the Step-by-Step Workflow; consolidate the xelatex/wkhtmltopdf guidance so it appears once.

Move the reusable sanitization script and the troubleshooting catalog into ./scripts/ and ./references/ files referenced one level deep, leaving SKILL.md as an overview.

Strengthen verification (Step 4) beyond `ls -lh` — e.g., check non-zero size / valid file type — and add an explicit recovery action when verification fails.

Dimension	Reasoning	Score
Conciseness	The core material (character table, sanitization sed script, fallback logic) is efficient and useful, but the 'Complete Example' largely duplicates the Step-by-Step Workflow and the xelatex/wkhtmltopdf guidance is repeated across Steps, Common pandoc Commands, and Troubleshooting.	3 / 5
Actionability	Provides concrete, executable pandoc and sed commands plus a full sanitization script; the main gap is that write_file/run_shell blocks use a tool-invocation format rather than copy-paste shell.	4 / 5
Workflow Clarity	Clear sequence (source -> sanitize -> convert -> verify) with an explicit stderr-capture feedback loop (xelatex -> examine error -> wkhtmltopdf), but the verification step is shallow (ls -lh only) with no guidance on what to do if verification fails.	4 / 5
Progressive Disclosure	The ~300-line body is well-headered but is a monolith with no external references, and content that could live in separate files (the sanitization script, the troubleshooting catalog, the duplicated full example) is inlined.	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 is third-person and names several concrete capabilities with a clear niche, but it omits any explicit 'when to use' trigger guidance and lacks natural user-facing trigger phrases and file extensions.

Suggestions

Add a 'Use when ...' clause naming concrete triggers (e.g., 'Use when shell_agent returns unclear errors on .docx/.pdf/.html generation, or when PDF conversion fails on special/non-ASCII characters').

Include natural trigger terms and file extensions users would say (PDFs, .docx, .html, special characters, encoding errors).

Replace the abstract 'fallback workflow' framing with one or two more concrete actions to push specificity toward 5.

Dimension	Reasoning	Score
Specificity	Names the domain (multi-format document generation) and several concrete actions ('character sanitization', 'explicit error capture', 'Unicode-safe fallback workflow'); not a 5 because 'fallback workflow' is more of a pattern than a fully enumerated set of actions.	4 / 5
Completeness	Clearly states what the skill does but provides no 'Use when...' clause or equivalent trigger guidance, so completeness is capped at 3 per the rubric guideline.	3 / 5
Trigger Term Quality	Contains relevant keywords ('document generation', 'Unicode-safe') but is missing the natural phrases users actually say ('PDF generation fails', 'special characters won't render') and any file extensions (.pdf, .docx).	3 / 5
Distinctiveness Conflict Risk	The 'Unicode-safe fallback workflow' niche with character-sanitization triggers is mostly distinct, with only minor overlap risk against sibling document-generation 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/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.