pandoc-unicode-sanitize

Pre-process Markdown to replace non-ASCII characters before pandoc PDF conversion

Quality

61%

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/pandoc-unicode-sanitize/SKILL.md

Quality

Content

65%

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 ready-to-run scripts and alternative approaches, but it is monolithic with no external references, duplicates the character list against the sed script, and lacks validation checkpoints in its sanitization workflow.

Suggestions

Add an explicit validation/feedback step to the workflow, e.g. run the sanitized output through pandoc and check for 'Package inputenc Error' before proceeding, with a fix-and-retry loop.

Move the sed substitution script into a bundled scripts/ file referenced from SKILL.md, and drop the duplicative Step 1 character list so the substitutions live in one place.

Trim the Problem/Solution preamble, which restates concepts Claude already knows, to tighten token efficiency.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient, but the Step 1 character list duplicates exactly what the sed script substitutes, and the Problem/Solution preamble restates concepts Claude already knows (what LaTeX/pandoc does), so it could be tightened rather than earning the lean 'every token earns its place' anchor.	2 / 3
Actionability	It provides a complete executable sed script, copy-paste inline usage, an iconv command, and concrete --pdf-engine flags, all of which are runnable as written, matching the 'fully executable code/commands; copy-paste ready' anchor.	3 / 3
Workflow Clarity	Steps are numbered and sequenced, but there are no validation checkpoints and sanitization is a batch operation; per the rubric, missing validation/feedback loops for batch operations caps workflow clarity at 2.	2 / 3
Progressive Disclosure	Sections are well-organized, but at ~94 lines it exceeds the simple-skill threshold and is monolithic with no one-level-deep references; the inlined sed script is even used as an external file ("./sanitize-for-pdf.sh") in the examples, indicating content that should be split out, matching the 'content that should be separate is inline' anchor.	2 / 3
	Total	9 / 12 Passed

Description

57%

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 clearly targets a distinct niche, but it states only a single action, omits common trigger variations like "Unicode", and lacks an explicit 'Use when...' clause, leaving the invocation trigger merely implied.

Suggestions

Add an explicit 'Use when...' trigger clause, e.g. 'Use when converting Markdown to PDF with pandoc and encountering Unicode/non-ASCII or LaTeX inputenc errors.'

Broaden trigger terms to include natural variations users would say, such as "Unicode", "LaTeX error", "inputenc", and "Markdown to PDF".

Optionally enumerate more concrete actions (e.g. sanitize, transliterate via iconv, or switch to a Unicode-capable engine) to lift specificity to the multiple-actions anchor.

Dimension	Reasoning	Score
Specificity	The description names a concrete action ("replace non-ASCII characters") and domain (Markdown, pandoc PDF conversion), but describes only a single action rather than multiple, so it does not reach the 'lists multiple specific concrete actions' anchor.	2 / 3
Completeness	It clearly states what the skill does ("Pre-process Markdown to replace non-ASCII characters before pandoc PDF conversion") but provides no 'Use when...' clause or explicit trigger for when to invoke it, so the 'when' is only implied and completeness is capped at 2.	2 / 3
Trigger Term Quality	Terms like "Markdown", "non-ASCII characters", "pandoc", and "PDF conversion" are natural, but coverage lacks common variations a user would say such as "Unicode", "LaTeX error", or "emoji", matching the 'some relevant keywords but missing common variations' anchor.	2 / 3
Distinctiveness Conflict Risk	The niche is narrow and specific (pandoc PDF conversion plus non-ASCII sanitization), with distinct triggers that are unlikely to overlap with other skills, matching the 'clear niche with distinct triggers' anchor.	3 / 3
	Total	9 / 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/pandoc-unicode-sanitize/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.