docx-parse-resilient

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

Quality

71%

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

67%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.

The body is highly actionable with executable code and a clear fallback workflow including validation, but it is noticeably verbose due to the same extraction logic being restated three times. Consolidating the redundant shell/Python blocks into a single canonical form would improve token efficiency without losing clarity.

Suggestions

Consolidate the repeated shell pipeline and Python fallback into one canonical example; the step-by-step, shell function, and Python script largely restate the same logic.

Trim the redundant step-by-step (Steps 2, 3, and 5 repeat the identical unzip|sed command) in favor of the complete shell function as the primary reference.

Remove concept reminders Claude already knows (e.g. 'DOCX files are ZIP archives containing XML files') to tighten the token budget.

Dimension	Reasoning	Score
Conciseness	The same shell pipeline ('unzip -p ... \| sed') appears ~5 times and the Python zipfile fallback ~3 times across the step-by-step, complete shell function, and Python script alternative — noticeably verbose padded sections, though it avoids explaining basic concepts at length.	2 / 5
Actionability	Provides fully executable, copy-paste-ready code and commands (unzip/sed pipeline, Python zipfile fallback, a complete shell function, and a standalone Python script) covering the common cases concretely.	5 / 5
Workflow Clarity	Clear numbered sequence with an explicit validation checkpoint (Step 3 checks for empty output) and a shell→Python fallback feedback loop, plus verification and troubleshooting sections; held back from 5 by the three overlapping presentations of the same workflow diluting the checklist feel.	4 / 5
Progressive Disclosure	Well-organized into logical sections (When to Use, Core Technique, Step-by-Step, Limitations, Verification, Troubleshooting, Environment Detection) with no external references needed for this scope; the redundant parallel code blocks are the main organization gap.	4 / 5
	Total	15 / 20 Passed

Description

61%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 and actionable about what it does, with decent natural keyword coverage, but it omits any 'when to use' trigger guidance and lists only a single concrete action. Adding a 'Use when...' clause and synonyms like 'Word documents' would lift completeness and trigger quality.

Suggestions

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

Include the synonym 'Word documents' and the '.docx' extension to broaden natural trigger coverage.

Drop or sharpen 'for maximum reliability' — it reads as mild fluff and adds no concrete capability.

Dimension	Reasoning	Score
Specificity	Names the domain ('DOCX files') and one concrete action ('Extract text') plus the method ('shell-primary approach and Python zipfile fallback'), but offers only a single capability rather than several specific actions, matching the '1-2 concrete actions' anchor.	3 / 5
Completeness	Clearly states the 'what' ('Extract text from DOCX files...') but contains no 'Use when...' clause or equivalent trigger guidance, which per the rubric caps completeness at 3.	3 / 5
Trigger Term Quality	Includes natural terms a user would say ('DOCX files', 'extract text') with clear action+target coverage; sits above the generic score-3 example but misses common synonyms like 'Word documents' and the '.docx' extension.	4 / 5
Distinctiveness Conflict Risk	The 'shell-primary with Python zipfile fallback' framing carves a distinctive niche, but the trigger 'extract text from DOCX' would overlap with a general DOCX skill, giving minor overlap risk.	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/docx-shell-parse-enhanced/SKILL.md
Commit: 3827781

Reviewed: 9 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.