docx-parse-resilient

Extract text from DOCX files with shell-primary approach and Python zipfile fallback for maximum reliability

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/docx-shell-parse-enhanced/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 body is highly actionable with executable code and a clearly sequenced, validated workflow, but it is hurt by repeated extraction logic across four near-duplicate sections and by keeping everything inline with no progressive disclosure into reference files.

Suggestions

De-duplicate the extraction logic: present the canonical shell and Python snippets once and have later sections reference them instead of re-pasting.

Move the full standalone Python script (and optionally the shell function) into a scripts/ bundle file referenced from the body to improve progressive disclosure.

Tighten or remove the 'Core Technique' section since it restates the 'Step-by-Step Instructions' intro.

Dimension	Reasoning	Score
Conciseness	The same unzip+sed and zipfile extraction logic is repeated roughly four times (step-by-step, save-to-file, shell function, and Python script), and the 'Core Technique' section restates the step-by-step intro; mostly efficient but could be tightened considerably.	2 / 3
Actionability	Provides fully executable, copy-paste-ready shell commands and a complete Python script with specific function definitions and concrete usage examples.	3 / 3
Workflow Clarity	The 5-step sequence is explicit with validation checkpoints (test shell output, check for empty content, fall back, verify output file size and content) plus dedicated Verification and Troubleshooting sections forming clear feedback loops.	3 / 3
Progressive Disclosure	No bundle/reference files exist and all content lives inline in a single ~260-line file; sections are well-labeled, but the full shell function and standalone Python script are content that could be split into separate reference files rather than inline.	2 / 3
	Total	10 / 12 Passed

Description

57%

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 distinct, naming a clear DOCX-extraction niche with a shell-plus-Python fallback approach, but it lacks an explicit 'when to use' trigger clause and misses common keyword variations like 'Word' and '.docx'.

Suggestions

Add an explicit 'Use when...' trigger clause, e.g. 'Use when extracting text from Word/.docx files, especially in constrained environments where unzip may be unavailable.'

Broaden trigger terms to include natural user phrasing such as 'Word documents' and '.docx'.

Optionally name additional concrete actions (e.g. strip XML tags, write extracted text to file) to lift specificity to 3.

Dimension	Reasoning	Score
Specificity	Names the domain ('DOCX files') and the concrete action ('Extract text') plus the two-tier method ('shell-primary approach and Python zipfile fallback'), but lists only one extraction action rather than multiple specific concrete actions.	2 / 3
Completeness	Clearly states what the skill does ('Extract text from DOCX files...'), but there is no 'Use when...' clause or equivalent trigger guidance, which caps completeness at 2 per the rubric guidelines.	2 / 3
Trigger Term Quality	Includes relevant natural terms ('DOCX files', 'Extract text', 'Python zipfile') but misses common user variations like 'Word documents', '.docx', or 'Word files'.	2 / 3
Distinctiveness Conflict Risk	The DOCX-specific niche combined with the explicit two-tier resilient-extraction method is clearly distinguishable and unlikely to trigger 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/docx-shell-parse-enhanced/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.