pdf-generation-troubleshooting

Systematic fallback workflow for PDF generation through pandoc, reportlab, and fpdf2 with installation verification

Quality

63%

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/pdf-generation-troubleshooting/SKILL.md

Quality

Content

67%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 delivers a clear, actionable three-tool fallback workflow with executable code and verification checkpoints. Its main weakness is redundancy: the same workflow is restated across four sections, inflating token usage without adding guidance value.

Suggestions

Consolidate the redundant restatements: keep the step-by-step sections and one checklist, and drop or merge the Workflow Overview, Example Fallback Implementation pseudocode, and Key Principles sections that restate the same sequence.

Replace the fixed-position reportlab example with a parameterized script that writes multi-line/wrapped content, so the example covers a realistic common case.

Add an explicit 'if the output PDF is missing or zero bytes, move to the next tool' verification gate with a concrete test command to strengthen the feedback loop toward a fix-retry pattern.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with concrete code, but the fallback sequence is restated four times (Workflow Overview, Error Handling Pattern, Example Fallback Implementation, Key Principles), adding noticeable redundancy; not a 4 because the repetition could be trimmed, not a 2 because it avoids explaining concepts Claude already knows.	3 / 5
Actionability	Provides executable bash checks, install commands, and copy-paste Python scripts for all three tools, fitting 'mostly executable guidance; concrete code with minor gaps'; not a 5 because the reportlab script hardcodes a single fixed-position string rather than covering realistic content cases.	4 / 5
Workflow Clarity	A clear Step 1/2/3 sequence with per-step availability checks, install-if-needed, and 'verify output file exists' checkpoints plus a fallback-on-failure loop; not a 5 because the feedback loop is 'move to next tool' rather than a fix-and-revalidate retry, leaving a minor validation gap.	4 / 5
Progressive Disclosure	The single-file skill is well organized with clear section headers and no nested references, and no bundle files exist to require external splitting; not a 5 because the body exceeds ~50 lines and some content (full per-tool scripts, decision matrix) could live in references if the skill grew.	4 / 5
	Total	15 / 20 Passed

Description

58%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 and names specific tools, but it lacks any explicit 'when to use' trigger guidance, which caps its completeness. Trigger-term coverage is adequate but missing common synonyms and file extensions.

Suggestions

Add an explicit 'Use when...' clause naming natural triggers, e.g. 'Use when the user asks to generate or create a PDF and tool availability is uncertain.'

Include common synonyms and the .pdf extension in the description (e.g. 'generate PDFs', 'create a PDF', '.pdf files') to broaden trigger-term coverage.

Sharpen the action list beyond the fallback framing (e.g. 'convert markdown/HTML to PDF, generate PDFs programmatically') to push specificity toward comprehensive.

Dimension	Reasoning	Score
Specificity	Names the domain (PDF generation) plus three concrete tools (pandoc, reportlab, fpdf2) and an installation-verification action, matching the 'lists several specific actions; minor gaps' anchor; not a 5 because it stops short of enumerating the full set of conversion/creation actions.	4 / 5
Completeness	The 'what' is clear (fallback workflow for PDF generation through named tools) but there is no 'Use when...' or equivalent trigger clause, so per the cap completeness cannot exceed 3; not a 2 because the 'what' is explicit rather than vague.	3 / 5
Trigger Term Quality	'PDF generation' is a natural term but the description omits common variations and file extensions (e.g. 'generate PDFs', 'create a PDF', '.pdf'), fitting 'some relevant keywords but missing common variations'; not a 4 because coverage of natural user phrasing is thin.	3 / 5
Distinctiveness Conflict Risk	The fallback-through-three-named-tools framing carves a clear niche with minor overlap risk against generic PDF skills; not a 5 because 'PDF generation' alone is still broad enough to invite some overlap.	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-generation-troubleshooting/SKILL.md
Commit: 3827781

Reviewed: 17 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.