pdf-engine-fallback

Retry PDF generation with alternative engines when pandoc fails

Quality

75%

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/pdf-engine-fallback/SKILL.md

Quality

Content

75%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 body is highly actionable and well-structured with a concrete fallback script and clear workflow. Its main weakness is redundancy between the inline steps and the complete script, which costs token efficiency.

Suggestions

Collapse the duplicate commands: either reference the complete script from the Steps section or keep the script and trim the inline command repetitions.

Add an explicit output-validation checkpoint (e.g., verify output.pdf is non-empty/valid) to strengthen the workflow's feedback loop.

Move the full fallback script into a scripts/ file and reference it from SKILL.md to improve progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with executable commands, but the "Complete Fallback Script" largely re-states the commands already shown in the Steps section, introducing noticeable redundancy.	3 / 5
Actionability	It provides copy-paste ready, fully executable commands and a complete bash script with engine detection, plus OS-specific install commands covering the common cases.	5 / 5
Workflow Clarity	The attempt → diagnose → retry → install sequence is clearly numbered, and the script implements a retry feedback loop with exit-status checks, though output integrity is not explicitly verified.	4 / 5
Progressive Disclosure	Content is well-organized into clearly headed sections (When to Use, Steps, Script, Usage, Guide, Troubleshooting) with no nested references, though the full script could arguably live in a scripts/ file.	4 / 5
	Total	16 / 20 Passed

Description

62%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 clear and reasonably distinct, answering both what it does and when to use it via the pandoc-failure trigger. It is somewhat thin on capability breadth and natural trigger-term coverage.

Suggestions

Add a "Use when..." clause enumerating concrete triggers (e.g., pandoc errors, Unicode/CJK documents, CI/CD PDF pipelines) to lift completeness and trigger coverage.

List a few more specific actions (check available engines, install missing engines) to increase specificity.

Include common synonyms/file extensions users might say (e.g., "PDF conversion", ".md to PDF") to improve trigger term quality.

Dimension	Reasoning	Score
Specificity	The description names the domain (PDF generation) and one concrete action ("Retry PDF generation with alternative engines") but offers only a single action rather than a comprehensive list of capabilities.	3 / 5
Completeness	It states both what ("Retry PDF generation with alternative engines") and when ("when pandoc fails"), though the when clause could be more explicit with additional trigger contexts.	4 / 5
Trigger Term Quality	It includes relevant natural terms ("PDF generation", "pandoc", "fails") but misses common variations and synonyms, and lacks the fuller trigger phrasing users might say.	3 / 5
Distinctiveness Conflict Risk	The pandoc-failure trigger carves a clear niche with low conflict risk, though it is not as comprehensively scoped as the top anchor.	4 / 5
	Total	14 / 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/pdf-engine-fallback/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.