CtrlK
BlogDocsLog inGet started
Tessl Logo

doc-gen-unicode-diagnostic

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

54

Quality

60%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

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
SKILL.md
Quality
Evals
Security

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 skill delivers a clear, actionable, well-validated document-generation workflow with strong feedback loops, but it is hampered by significant internal repetition and inlined bulk reference content that should be split into separate files.

Suggestions

De-duplicate the body: keep a single pre-flight check, a single sanitization recipe, and a single troubleshooting section, removing the repeated Step 0 pre-flight and the overlapping troubleshooting table.

Move the 'Common pandoc Commands Reference', 'Alternative: Python PDF Generation', and 'Troubleshooting Quick Reference' into separate reference files and link to them one level deep to improve progressive disclosure.

Use real shell fenced code blocks (```bash) consistently instead of the 'run_shell / command:' pseudo-format so examples are directly copy-paste executable.

DimensionReasoningScore

Conciseness

The body is mostly actionable rather than padded with basic concepts, but it repeats material substantially (pre-flight appears twice, sanitization is shown three times, troubleshooting appears as both a decision tree and an overlapping table), which fits 'mostly efficient but could be tightened' rather than the lean 4 or verbose 2.

3 / 5

Actionability

Provides concrete, copy-paste-ready pandoc commands, a sanitization sed script, and Python fpdf2/reportlab snippets with explicit stderr capture; the non-standard 'run_shell/command:' pseudo-format blocks and a shaky sed quoting pattern are minor gaps keeping it just below fully executable 5.

4 / 5

Workflow Clarity

A clear numbered Step 0-6 sequence with an explicit engine fallback chain (xelatex->pdflatex->wkhtmltopdf), an error-diagnosis decision tree, stderr capture, and a verification checklist provides the explicit validation steps, feedback loops, and checklist the 5 anchor requires for a fragile document/batch operation.

5 / 5

Progressive Disclosure

No bundle files exist and everything is inlined in one ~370-line file; bulk reference material (pandoc command reference, Python alternatives, troubleshooting table) that clearly belongs in separate files is inlined, matching 'some structure but content that should be separate is inline' despite good section headers.

3 / 5

Total

15

/

20

Passed

Description

51%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 states what the skill does with several concrete capabilities and is reasonably distinct, but it lacks a 'Use when...' trigger clause and relies on technical jargon rather than natural user phrases or file extensions.

Suggestions

Add an explicit 'Use when ...' clause naming natural triggers such as 'Use when generating .docx/.pdf/.html documents, when PDF conversion fails with encoding or LaTeX errors, or when shell_agent returns an unclear error'.

Replace jargon like 'engine fallback chain' with natural user terms and include file extensions (e.g. '.pdf', '.docx', 'pandoc') to improve trigger-term quality.

Tighten the capability list toward concrete actions (e.g. 'Generate .docx/.pdf/.html from markdown via pandoc, sanitize Unicode for LaTeX, fall back across xelatex/pdflatex/wkhtmltopdf') to push specificity toward 5.

DimensionReasoningScore

Specificity

Lists several concrete capabilities ('unicode sanitization', 'engine fallback chain', 'explicit error diagnosis') but stops short of naming concrete actions like specific formats or operations, fitting the 'several specific actions; minor gaps' anchor rather than the comprehensive 5.

4 / 5

Completeness

Provides a clear 'what' but no 'Use when...' trigger clause; per the guidelines a missing explicit 'when' caps completeness at 3, matching the 'clear what, when missing or weakly implied' anchor.

3 / 5

Trigger Term Quality

Uses technical jargon ('unicode sanitization', 'engine fallback chain') a user would not naturally say and omits natural phrases like 'generate a PDF' or file extensions like '.docx'/'PDF', landing just below the midpoint between generic and adequate keyword coverage.

2 / 5

Distinctiveness Conflict Risk

The combination of unicode sanitization plus an engine fallback chain carves a specific niche with only minor overlap against generic document-generation skills, fitting 'mostly distinct; minor overlap risk'.

4 / 5

Total

13

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
HKUDS/OpenSpace
Reviewed

Table of Contents

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.