CtrlK
BlogDocsLog inGet started
Tessl Logo

pandoc-unicode-workaround

Handle LaTeX Unicode errors in pandoc PDF generation by normalizing special characters to ASCII

56

Quality

63%

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/pandoc-unicode-workaround/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

61%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 actionable and well-structured with a clear procedure, but redundancy in the replacement mapping and a lack of concrete validation/backup for destructive in-place edits limit its conciseness and workflow-clarity scores.

Suggestions

Consolidate the character-replacement table, sed commands, and Python dict into one canonical mapping to remove triple redundancy.

Add a concrete backup step before editing (e.g. 'cp input.md input.md.bak') and an explicit verification command (e.g. check pandoc exit code or grep for remaining Unicode) with a retry loop.

Fix the Python smart-quote dict entries, which currently show placeholder/identical characters rather than the curly quote glyphs.

DimensionReasoningScore

Conciseness

Avoids explaining basic concepts but repeats the same character-replacement mapping three times (table, sed block, Python dict), which is unnecessary padding that could be tightened.

3 / 5

Actionability

Provides concrete, copy-paste-ready bash/sed commands, a complete runnable Python script, a replacement table, and alternative engine commands, with only minor gaps (e.g. garbled smart-quote entries in the Python dict).

4 / 5

Workflow Clarity

Has a clear 5-step sequence with a final verify step, but the in-place file edits (sed -i, overwriting input.md) are destructive/batch operations lacking a concrete validation checkpoint or backup step, which caps the score at 3 per the rubric.

3 / 5

Progressive Disclosure

Single self-contained SKILL.md with well-organized sections (When to Use, Step-by-Step, Alternative Approaches, Tips, Error Indicators) and no nested references, though it is larger than the 50-line simple-skill threshold.

4 / 5

Total

14

/

20

Passed

Description

65%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 distinctive but omits an explicit 'Use when...' trigger clause, which caps its completeness. It clearly conveys the what but only weakly implies the when.

Suggestions

Add an explicit 'Use when...' clause, e.g. 'Use when pandoc PDF generation fails with LaTeX Unicode character errors.'

Mention common trigger phrases users actually say, such as 'Unicode character not set up for use with LaTeX', to improve trigger term coverage.

List a second concrete action (e.g. 'or switch to a Unicode-capable PDF engine like xelatex') to raise specificity beyond a single action.

DimensionReasoningScore

Specificity

Names the domain (pandoc PDF generation, LaTeX Unicode errors) and one concrete action ('normalizing special characters to ASCII'), but the action is singular rather than several specific actions.

3 / 5

Completeness

Has a clear 'what' but no explicit 'Use when...' trigger clause, and the rubric caps completeness at 3 when such guidance is absent.

3 / 5

Trigger Term Quality

Includes natural user-facing terms like 'pandoc', 'PDF generation', 'LaTeX', and 'Unicode' that a user would say when hitting this error, though a few synonyms and the .pdf extension are missing.

4 / 5

Distinctiveness Conflict Risk

Targets a narrow, clearly-defined niche (pandoc + LaTeX Unicode errors) with distinct triggers and minimal risk of overlapping other skills.

5 / 5

Total

15

/

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.