pdf-checklist-workflow

Generate structured PDF documents with tables, sections, and scoring using Python libraries in execute_code_sandbox

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/pdf-checklist-workflow/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 content is highly actionable with executable examples and a well-sequenced, verified workflow, but it is monolithic and somewhat redundant. Splitting reference material into separate files and deduplicating examples would improve token efficiency and structure.

Suggestions

Move the full reportlab example and shell-fallback templates into a reference file (e.g. references/advanced-examples.md) and link to it from the body to reduce inline bulk.

Remove the 'Template for Quick Start' section or consolidate it with the Step 2 fpdf2 example to eliminate near-duplicate code.

Collapse the dual bash/Python workspace-detection snippets into one canonical dynamic-path approach.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and avoids explaining basics, but the 'Template for Quick Start' largely duplicates the fpdf2 example and both bash and Python workspace-detection snippets are shown, so it could be tightened.	2 / 3
Actionability	It provides fully executable fpdf2 and reportlab code, concrete execute_code_sandbox and shell-fallback commands, and copy-paste-ready verification steps, matching the score-3 anchor.	3 / 3
Workflow Clarity	A clear five-step sequence includes an explicit Step 4 verification checkpoint, a Step 3b fallback feedback loop, and a Step 5 troubleshooting table, satisfying the score-3 anchor.	3 / 3
Progressive Disclosure	The skill is a well-organized but monolithic 290-line file with no bundle references; substantial content like the full reportlab example and shell-fallback templates is inline rather than split out, fitting the score-2 anchor.	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 conveys concrete capabilities but lacks an explicit 'Use when...' trigger clause, capping completeness and trigger quality. Adding natural trigger terms and removing internal jargon would materially improve it.

Suggestions

Append a 'Use when...' clause naming natural triggers, e.g. 'Use when generating PDF checklists, reports, or scored assessments.'

Replace or de-emphasize the internal tool name 'execute_code_sandbox' with user-facing terms like 'checklists, reports, scoring tables, and downloadable PDFs'.

Add common natural variations (.pdf, reports, checklists) to broaden trigger-term coverage.

Dimension	Reasoning	Score
Specificity	The description lists multiple concrete output elements — 'structured PDF documents with tables, sections, and scoring' — matching the score-3 anchor that lists several specific concrete actions.	3 / 3
Completeness	It clearly states what the skill does but has no 'Use when...' clause or explicit trigger guidance, which per the judging guidelines caps completeness at 2.	2 / 3
Trigger Term Quality	'PDF documents' is a natural term, but 'execute_code_sandbox' is internal jargon and common user variations (checklists, reports, .pdf) are absent, fitting the score-2 anchor of some relevant keywords but missing common variations.	2 / 3
Distinctiveness Conflict Risk	PDF generation is a reasonably distinct niche, but without explicit triggers it could still overlap with PDF-extraction skills, matching the score-2 anchor of somewhat specific but possible overlap.	2 / 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/pdf-checklist-workflow/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.