doc-gen-unicode-diagnostic

Systematic document generation with unicode sanitization, engine fallback chain, and explicit error diagnosis

Quality

63%

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-3d3a9a/SKILL.md

Quality

Content

77%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is highly actionable with a clear, validated workflow and good error-recovery feedback loops, but it is verbose and redundant with no progressive disclosure of detail into separate files. Actionability and workflow clarity are strong; conciseness and file structure are the weak spots.

Suggestions

De-duplicate the pre-flight validation (it appears both as a top-level section and as Step 0) and remove the Complete Example that re-runs the same steps 0-6.

Move the Common pandoc Commands Reference and Troubleshooting Quick Reference table into a separate reference file linked one level deep from the body.

Trim the promotional preamble ("43% effectiveness... This skill fixes those gaps") and keep only the operational guidance.

Dimension	Reasoning	Score
Conciseness	The ~370-line body duplicates material (pre-flight validation appears twice, the Complete Example re-runs steps 0-6, the pandoc command reference and troubleshooting table repeat inline content) and includes promotional preamble, so it could be tightened substantially despite not explaining basic concepts.	2 / 3
Actionability	It provides fully executable, copy-paste-ready commands throughout (pandoc invocations with 2>&1, a complete sed sanitization script, and fpdf2/reportlab Python snippets), matching the top anchor.	3 / 3
Workflow Clarity	Steps 0-6 are explicitly sequenced with validation checkpoints (output verification, file checks) and a feedback loop (capture stderr, diagnose via decision tree, retry with fallback engine), which the rubric rewards for document/batch operations.	3 / 3
Progressive Disclosure	Content is well-sectioned but monolithic: the pandoc command reference and troubleshooting tables are detail that stays inline with no bundle files or one-level-deep references to split it out.	2 / 3
	Total	10 / 12 Passed

Description

50%

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 a clear niche and several concrete capabilities but is phrased procedurally rather than in natural user terms and omits an explicit "Use when..." trigger. It sits solidly at the middle anchor across all dimensions.

Suggestions

Add an explicit trigger clause, e.g. "Use when PDF generation fails with encoding/LaTeX errors or when converting markdown to .docx/.pdf/.html."

Reword procedural jargon ("engine fallback chain", "unicode sanitization") toward natural user phrasings like "generate PDF/Word/HTML documents" and "fix PDF encoding errors".

Lead with concrete enumerated actions (generate, sanitize, convert with fallback, diagnose errors) to lift specificity toward the top anchor.

Dimension	Reasoning	Score
Specificity	The description names the domain and several concrete aspects ("unicode sanitization", "engine fallback chain", "explicit error diagnosis") but describes approach rather than enumerating concrete file operations, so it stops short of the multiple-specific-actions anchor.	2 / 3
Completeness	It clearly answers what the skill does but lacks an explicit "Use when..." trigger clause, which the guidelines say caps completeness at 2.	2 / 3
Trigger Term Quality	"document generation" is a relevant keyword, but terms like "engine fallback chain" and "unicode sanitization" are procedural jargon and common natural phrasings (PDF, Word, .docx, convert markdown) are missing.	2 / 3
Distinctiveness Conflict Risk	The unicode-safe PDF/fallback niche is fairly specific, but "document generation" still overlaps with general document skills and no trigger context narrows it to a clear distinct niche.	2 / 3
	Total	8 / 12 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-3d3a9a/SKILL.md
Commit: c5a9c4b

Reviewed: 2 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.