pandoc-pdf-error-diagnosis

Systematic diagnostic workflow for resolving pandoc PDF conversion errors

Quality

62%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Medium

Suggest reviewing before use

Fix and improve this skill with Tessl

tessl review fix ./benchmarks/gdpval/skills/pandoc-pdf-error-diagnosis/SKILL.md

Quality

Content

56%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 executable commands and a useful error-pattern table, but it is somewhat padded (duplicate diagnostic script, over-explained engines) and lacks explicit validation/retry checkpoints in its fallback sequence. As a simple single-file skill it organizes content reasonably well.

Suggestions

Remove or shorten the standalone 'Quick Reference Diagnostic Script' since it duplicates Steps 1-3, or move it to a bundled scripts/ file referenced from the body to improve conciseness.

Trim the engine-characteristics bullets and explanatory lines like 'This verifies pandoc is available' that state what Claude can already infer from the command.

Add an explicit validation/retry checkpoint between engine attempts (e.g., 'If conversion fails, read conversion.log, apply the matching table fix, then retry the same engine before moving to the next') to lift workflow clarity.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with executable commands and a compact error-pattern table, but it restates obvious facts ('This verifies pandoc is available'), includes a full duplicate diagnostic shell script that re-covers earlier steps, and the engine-characteristics list over-explains engines Claude already knows.	3 / 5
Actionability	Most guidance is concrete and executable: version/engine checks, explicit pandoc commands with stderr capture, a categorized error-to-solution table, and a copy-pasteable diagnostic script; only minor gaps (e.g., placeholder package names) keep it just below fully executable.	4 / 5
Workflow Clarity	The seven numbered steps give a clear sequence, but the workflow involves running conversions and installing dependencies with no explicit validation checkpoint or fix-retry feedback loop before proceeding between engines, which caps workflow clarity at 3 for a batch/troubleshooting operation.	3 / 5
Progressive Disclosure	The skill is a single self-contained SKILL.md with well-organized sections and no bundle files to reference; for a sub-50-line-equivalent simple skill the structure is clean and navigation is easy, though the inline diagnostic script and engine list could arguably live in a bundled script file.	4 / 5
	Total	14 / 20 Passed

Description

50%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 states a clear what (diagnosing/resolving pandoc PDF conversion errors) but lacks an explicit 'Use when' trigger clause and comprehensive natural trigger terms, which caps completeness and trigger quality. It is reasonably distinct within its niche.

Suggestions

Add an explicit 'Use when...' trigger clause naming natural phrasings such as 'pandoc reports an unknown error', 'PDF conversion failed', or 'could not produce PDF output'.

Include natural synonyms and file extensions users actually say (e.g., 'pandoc', 'PDF export', 'latex/xelatex engine', '.md to .pdf') to broaden trigger coverage.

Enumerate the concrete diagnostic actions (e.g., 'checks installed PDF engines, analyzes stderr, suggests engine fallbacks and missing-package fixes') to lift specificity above the midpoint.

Dimension	Reasoning	Score
Specificity	Phrases like 'diagnostic workflow' and 'resolving pandoc PDF conversion errors' name the domain and a concrete action (resolving errors) but do not enumerate the specific diagnostic actions performed; coverage is not comprehensive.	3 / 5
Completeness	It clearly states what the skill does (a diagnostic workflow for resolving pandoc PDF errors) but provides no 'Use when...' clause; the 'when' is only weakly implied, capping completeness at 3 per the rubric.	3 / 5
Trigger Term Quality	It surfaces 'pandoc PDF conversion errors' but omits the natural phrasing a user would say ('unknown error', 'PDF export failed', 'latex engine') and any file extensions, so coverage of natural terms is partial.	3 / 5
Distinctiveness Conflict Risk	The pandoc + PDF conversion niche is fairly specific with minimal overlap risk against other skills, though it could still rub against a generic pandoc or LaTeX skill; mostly distinct.	4 / 5
	Total	13 / 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/pandoc-pdf-error-diagnosis/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.