pdf-checklist-workflow

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

Quality

65%

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

71%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.

This is a highly actionable, well-sequenced workflow with strong executable examples and sensible fallback/validation paths. Its main weaknesses are redundant near-duplicate code templates that hurt conciseness and a monolithic inline structure with no progressive disclosure.

Suggestions

Consolidate the ~4 near-duplicate basic-generation code blocks (fpdf2 example, fallback heredoc, quick-start template, shell-fallback template) into one canonical snippet referenced by the others.

Factor the repeated workspace-detection logic into a single shown-once helper instead of restating it in each example.

Move the full reportlab example and the template gallery into a references/ file (e.g. EXAMPLES.md) and link to it from the main body to improve progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient procedural content without concept-explanation padding, but the basic fpdf generation recipe recurs in ~4 near-duplicate blocks and workspace-detection logic repeats 3+ times, so it could be meaningfully tightened.	3 / 5
Actionability	Fully executable, copy-paste-ready code is provided for both the simple (fpdf2) and professional (reportlab) paths, plus a shell heredoc fallback, with specific pip/python/ls commands and concrete output paths covering the common cases.	5 / 5
Workflow Clarity	Steps 1–5 (plus 3b fallback) give a clear sequence with an explicit verification checkpoint (Step 4) and error-recovery feedback loops (retry then shell fallback, troubleshooting table); validation is somewhat shallow (size check only), keeping it just below 5.	4 / 5
Progressive Disclosure	The ~290-line body is well-sectioned but entirely inline with no bundle references, and full library examples plus multiple templates that could live in separate files are inlined; the under-50-line simple-skill exception does not apply.	3 / 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 is specific about what it produces but omits any explicit "when to use" trigger guidance, costing it on completeness and trigger-term quality. Adding a "Use when..." clause with natural synonyms like checklist, report, or assessment would raise the score.

Suggestions

Add an explicit trigger clause, e.g. "Use when generating PDF checklists, reports, or assessments with scoring criteria."

Include natural user-facing synonyms (checklist, report, assessment) and the .pdf extension alongside "PDF documents".

Drop the tool-implementation detail ("using Python libraries in execute_code_sandbox") from the description, since it is jargon that does not help users discover the skill.

Dimension	Reasoning	Score
Specificity	Names the PDF domain and several concrete output elements ("tables, sections, and scoring"), though the single verb "Generate" keeps it just short of comprehensive multi-action coverage.	4 / 5
Completeness	The description gives a clear "what" but includes no "Use when..." clause or equivalent explicit trigger guidance, which caps completeness at 3 per the rubric guidelines.	3 / 5
Trigger Term Quality	"PDF documents" is a natural term, but the actual use-case synonyms users would say ("checklist", "report", "assessment") and the ".pdf" extension are absent, while "execute_code_sandbox" is technical jargon rather than a user trigger.	3 / 5
Distinctiveness Conflict Risk	The niche of structured PDF generation with tables, sections, and scoring is mostly distinct, with only minor overlap risk against general PDF skills.	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-checklist-workflow/SKILL.md
Commit: 3827781

Reviewed: 13 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.