document-direct-python

Use direct Python execution for reliable document creation including spreadsheets, PDFs, and structured reports

Quality

56%

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/spreadsheet-direct-python-merged/SKILL.md

Quality

Content

65%

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 strong executable examples and a clear write-to-file pattern, but it leans verbose, lacks explicit validation feedback loops for batch document operations, and is monolithic with no progressive disclosure into separate reference files.

Suggestions

Add an explicit validate-fix-retry feedback loop for batch/destructive document operations (e.g., verify the output file opens/has expected row count before declaring success).

Trim concept-level padding and remove the speculative 'Handling Web Research Failures' contingency plus the embedded task ID to tighten token efficiency.

Move the library reference tables and longer examples into separate reference files (e.g., LIBRARIES.md, EXAMPLES.md) and link to them from the overview for better progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The body is mostly actionable but padded with concept-level padding such as 'The context window is a public good' style rationale and the speculative 'Handling Web Research Failures' contingency section plus a named task ID that a reader does not need.	2 / 3
Actionability	Provides multiple complete, copy-paste-ready Python examples (reportlab, FPDF, openpyxl, pandas) and concrete write-to-file-then-execute patterns with specific commands.	3 / 3
Workflow Clarity	Steps are sequenced (write to file first, then execute) and a try/except error-handling pattern appears, but there is no explicit validate-then-fix-then-retry feedback loop for the batch/destructive document operations the rubric flags.	2 / 3
Progressive Disclosure	Content is well-sectioned with clear headers, but it is a monolithic single-file document with no bundle files or one-level-deep references to split out the lengthy library reference tables and examples.	2 / 3
	Total	9 / 12 Passed

Description

47%

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 the document domain and uses natural trigger terms, but it lacks an explicit 'Use when...' trigger clause, which under the guidelines caps completeness and limits its overall score.

Suggestions

Add an explicit 'Use when...' clause stating the situations that should trigger this skill (e.g., 'Use when generating spreadsheets, PDFs, or structured reports that need reliable file-based Python execution').

Enumerate more concrete actions — such as filling forms, merging documents, or applying formulas — to lift specificity from a single broad activity to multiple specific operations.

Sharpen distinctiveness by contrasting with iterative/agent-based execution so it is less likely to trigger for ordinary document tasks.

Dimension	Reasoning	Score
Specificity	Names the domain (document creation) and several concrete actions (spreadsheets, PDFs, structured reports) but stops at a single broad activity rather than listing multiple specific operations like filling forms or merging.	2 / 3
Completeness	It states what the skill does ('Use direct Python execution for reliable document creation') but contains no explicit 'Use when...' trigger clause, which the guidelines say caps completeness at 2; with no when-guidance at all it falls to the lower band.	1 / 3
Trigger Term Quality	Includes natural terms users would actually say — 'spreadsheets', 'PDFs', 'structured reports', 'document creation' — with good coverage of common phrasings.	3 / 3
Distinctiveness Conflict Risk	The phrase 'direct Python execution' carves a modest niche but 'document creation including spreadsheets, PDFs, and structured reports' could still overlap with general document-handling skills.	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/spreadsheet-direct-python-merged/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.