docx-dual-parse

Extract text from DOCX files using shell or Python zipfile, with environment-aware fallback

Quality

68%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./benchmarks/gdpval/skills/docx-shell-parse-enhanced-4bba79/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 skill body is highly actionable with executable, well-guarded code and a clear method-selection workflow, but it is verbose for a single-purpose extraction skill due to repeated logic across multiple near-duplicate sections and lacks any use of separate reference files.

Suggestions

Consolidate the Shell, Python, Unified, and Alternative sections so each extraction method appears once; reference the reusable functions instead of restating full step-by-step snippets.

Drop redundant trivial steps such as the repeated `ls -la document.docx` verification lines.

Move the reusable parse_docx_* functions and the temp-dir alternative into a scripts/ or references/ file and link to them from the overview to improve both conciseness and progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The ~270-line body repeats near-identical extraction logic across the Shell, Python, Unified, and Alternative sections and restates trivial checks like `ls -la document.docx`, which is noticeably verbose with several padded/duplicated sections rather than the mostly-efficient anchor.	2 / 5
Actionability	It provides copy-paste-ready, executable shell and Python snippets plus complete reusable functions with file-existence and command-availability checks, covering the common extraction cases fully rather than just mostly-executable.	5 / 5
Workflow Clarity	Method selection is clearly sequenced with environment detection, a selection-guide table, a shell-then-Python fallback in parse_docx, and a Verification section; it stops short of explicit validate->fix->retry feedback loops, fitting the clear-sequence-with-most-checkpoints anchor.	4 / 5
Progressive Disclosure	It is a single, well-organized SKILL.md with clear section headers and no nested references, but content that could be split into reference files (the reusable functions and the temp-dir alternative) is inlined, fitting the good-structure-with-minor-organization-gaps anchor.	4 / 5
	Total	15 / 20 Passed

Description

53%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 states a clear capability and a distinctive dual-method angle, but it omits any explicit "Use when..." trigger guidance and lacks synonyms like "Word" or ".docx", which limits completeness and trigger-term coverage.

Suggestions

Add a 'Use when...' clause naming natural triggers, e.g. 'Use when extracting text from DOCX/Word (.docx) files in containers, sandboxes, or minimal images without python-docx'.

Include synonyms and the file extension (Word, .docx) so the description matches phrases users actually say.

Optionally list one more concrete action (e.g. 'save extracted text to file') to push specificity toward comprehensive coverage.

Dimension	Reasoning	Score
Specificity	It names the DOCX domain and two concrete methods ("using shell or Python zipfile") but does not enumerate the fuller set of actions like saving to file or batch extraction, so it lands at the anchor listing domain and 1-2 concrete actions rather than the comprehensive anchor above.	3 / 5
Completeness	The "what" is clear (extract text from DOCX via shell or Python with environment-aware fallback) but there is no "Use when..." or equivalent trigger clause, and per the judging guidelines a missing trigger clause caps completeness at 3.	3 / 5
Trigger Term Quality	It includes the relevant term "DOCX files" but omits common natural variations and synonyms users say ("Word", "Word documents", ".docx", "Word files"), fitting the anchor with some relevant keywords missing common variations rather than the good-coverage anchor above.	3 / 5
Distinctiveness Conflict Risk	"Extract text from DOCX files using shell or Python zipfile" carves a specific dual-method niche with minimal overlap risk; it is mostly distinct from generic document skills, fitting the mostly-distinct anchor just below the clear-niche anchor.	4 / 5
	Total	13 / 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-4bba79/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.