pdf-gen-fallback

Reliable PDF generation using shell-based Python execution when sandbox fails

Quality

67%

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-gen-fallback/SKILL.md

Quality

Content

85%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is well-structured with executable code, a clear sequenced workflow, and explicit validation and feedback steps; its main weakness is mild redundancy from the duplicated example workflow and restated library alternatives.

Suggestions

Remove the duplicated 'Complete Example Workflow' section (it restates Steps 1-5) and consolidate 'Library Alternatives' with the Step 1 availability checks to tighten the body.

Fix the corrupted non-ASCII text in 'Common Pitfalls' ('often it's环境 issues') by replacing it with 'environment'.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean and avoids explaining concepts Claude already knows, but the 'Complete Example Workflow' duplicates the step-by-step procedure and 'Library Alternatives' re-lists libraries already checked in Step 1.	2 / 3
Actionability	It provides concrete, executable code and commands throughout (library availability checks, reportlab generation, file verification), which is copy-paste ready rather than pseudocode.	3 / 3
Workflow Clarity	A clear 5-step sequence is paired with an explicit verification checkpoint (Step 5) and a feedback loop from error detection (Step 3) into the shell fallback (Step 4).	3 / 3
Progressive Disclosure	This is a single-file, single-purpose skill with no need for external references, organized into clearly labeled sections with no deep nesting or monolithic wall of text.	3 / 3
	Total	11 / 12 Passed

Description

50%

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 concise and names a concrete action with a clear method, but it leans on technical jargon, lacks an explicit 'Use when...' trigger clause, and could overlap with general PDF skills. It lands at a mid-level 2 across all four dimensions.

Suggestions

Add an explicit 'Use when...' trigger clause naming user-facing situations, e.g., 'Use when generating PDFs or reports and the code sandbox returns opaque errors.'

Soften internal jargon ('shell-based Python execution', 'sandbox fails') into natural user terms and add common variations such as 'create PDFs', 'documents', and 'reports'.

List one or two more concrete capabilities (e.g., generate reports or structured documents) to sharpen distinctiveness from a general PDF skill.

Dimension	Reasoning	Score
Specificity	Names the domain ('PDF generation') and a concrete method ('shell-based Python execution'), but describes a single action rather than listing multiple specific capabilities as the score-3 anchor requires.	2 / 3
Completeness	It states what it does, and 'when sandbox fails' gives a partial trigger, but there is no explicit 'Use when...' clause, which the guidelines say caps completeness at 2.	2 / 3
Trigger Term Quality	'PDF generation' is a natural user term, but 'shell-based Python execution' and 'when sandbox fails' are internal/technical jargon, and common variations like 'create PDFs', 'documents', or 'reports' are absent.	2 / 3
Distinctiveness Conflict Risk	The sandbox-failure fallback niche is somewhat distinctive, but 'PDF generation' is broad enough to overlap with a general PDF skill and the distinctiveness rests on an internal condition rather than distinct user-facing triggers.	2 / 3
	Total	8 / 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/pdf-gen-fallback/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.