direct-reportlab-pdf-generation

Generate complex multi-page PDFs by running reportlab Python code directly via run_shell when shell_agent fails on document creation

Quality

68%

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/direct-reportlab-pdf-generation/SKILL.md

Quality

Content

77%

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

The skill is highly actionable with executable code and a clear sequenced workflow including verification. The main weaknesses are repeated import boilerplate and a large inline code block that could be offloaded to a reference file for better token efficiency and progressive disclosure.

Suggestions

Dedupe the reportlab import block: show it once in Step 2 and have Step 3 reference or reuse that script rather than re-listing imports.

Move the full create_pdf reference implementation into a references/ file and keep only a minimal example inline in SKILL.md.

Trim the 'Advantages Over shell_agent' section to one line or fold it into 'When to Use This Skill' to reduce promotional padding.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean and avoids explaining concepts Claude knows, but it repeats the reportlab import boilerplate in both Step 2 and Step 3 and includes a somewhat promotional 'Advantages Over shell_agent' section that could be trimmed.	2 / 3
Actionability	It provides a complete, copy-paste-ready create_pdf function plus concrete heredoc and file-based execution examples and verification commands, giving fully executable guidance.	3 / 3
Workflow Clarity	A clear five-step sequence (prepare, write, execute, handle content, verify) includes an explicit verification checkpoint in Step 5; PDF generation is non-destructive so the destructive/batch feedback-loop cap does not apply.	3 / 3
Progressive Disclosure	No bundle files exist and sections are well-organized, but the large inline create_pdf code block (~70 lines) is content that could live in a separate reference file, leaving the overview heavier than ideal for a single-file skill.	2 / 3
	Total	10 / 12 Passed

Description

60%

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 distinguishes a clear niche, but its trigger language leans heavily on internal agent jargon ('shell_agent', 'run_shell', 'when shell_agent fails') rather than natural user phrasing. Rewording the 'when' clause around user-facing situations would raise trigger quality.

Suggestions

Reframe the trigger around natural user situations (e.g., 'Use when generating a multi-page PDF with custom layout, tables, or pagination') instead of the internal fallback condition 'when shell_agent fails'.

Add natural keyword variations users actually say ('PDF', 'PDF document', '.pdf', 'report', 'formatted document') alongside 'reportlab'.

Keep the fallback-to-shell_agent rationale in the body rather than the description to avoid jargon cluttering the trigger.

Dimension	Reasoning	Score
Specificity	Names the domain and a concrete action ('Generate complex multi-page PDFs by running reportlab Python code directly via run_shell') but describes a single technique path rather than enumerating multiple distinct actions, so it is not fully comprehensive.	2 / 3
Completeness	It explicitly answers both what (generate PDFs via reportlab/run_shell) and when ('when shell_agent fails on document creation'), providing an explicit trigger condition even though it is framed as a fallback.	3 / 3
Trigger Term Quality	The trigger phrasing ('when shell_agent fails on document creation', 'run_shell', 'shell_agent') is internal agent jargon a user would never naturally say; only 'PDFs' is a natural term, which is not enough to lift it above the jargon anchor.	1 / 3
Distinctiveness Conflict Risk	It carves a clear niche (direct reportlab execution as a fallback when shell_agent fails) with distinct, narrowly-scoped triggers, making it unlikely to fire for unrelated skills.	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/direct-reportlab-pdf-generation/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.