docx-shell-workaround

Handle docx files using shell-based XML extraction and python-docx via run_shell when standard tools fail

Quality

64%

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-workaround/SKILL.md

Quality

Content

72%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is highly actionable with complete, executable code and a clear sequenced workflow, but it is padded with repeated XML-parsing examples and lacks a validation feedback loop for the document-creation path. Progressive disclosure is fine for a self-contained, well-sectioned workaround skill.

Suggestions

Consolidate the redundant XML-parsing blocks (Step 2, Step 3, and the Full Workflow extraction step) into one canonical example and reference it, rather than restating near-identical ElementTree code three times.

Add an explicit validation checkpoint after docx creation (e.g., reopen with python-docx or re-unzip to confirm word/document.xml is well-formed) with a fix-and-retry loop, since this is XML/document manipulation.

Trim incidental commentary such as restating that DOCX is a ZIP archive inline; keep only what Claude cannot already infer.

Dimension	Reasoning	Score
Conciseness	The body is mostly executable code that earns its place, but it repeats near-duplicate XML-parsing blocks across Step 2, Step 3, and the Full Workflow Example, which is padding that could be tightened, matching 'mostly efficient but could be tightened'.	2 / 3
Actionability	Every step provides complete, copy-paste-ready commands and Python heredocs (unzip -p, ElementTree parsing, python-docx construction, pip install), matching the 'fully executable code/commands; copy-paste ready' anchor.	3 / 3
Workflow Clarity	Steps are clearly numbered (Step 1/2/3) for extract→parse→create, but an XML/document-creation workflow has no validate→fix→retry feedback loop, which per the rubric scoring notes caps workflow clarity at 2.	2 / 3
Progressive Disclosure	The skill is a single self-contained file with clear sections (When to Use, Reading, Creating, Full Workflow, Key Points, Troubleshooting) and no nested external references, so it is well-organized and easy to navigate with one-level-deep (here zero-level) structure.	3 / 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 as a docx fallback skill, but its trigger terms lean technical and its 'when' clause is thin and underdefined. It conveys what and when but not at the comprehensive, user-natural level of the top anchors.

Suggestions

Add natural user-facing trigger terms such as '.docx' and 'Word documents' alongside 'docx files' to improve trigger-term coverage.

Expand the 'when' clause to name the specific failing tools or scenarios (e.g., 'Use when read_file or execute_code_sandbox fail on .docx files') so the trigger is explicit rather than abstract.

Reframe the action list around user-facing outcomes (e.g., 'Extract text from, create, and modify .docx files') instead of tool/means phrasing to lift specificity.

Dimension	Reasoning	Score
Specificity	Names the docx domain plus two mechanisms ('shell-based XML extraction' and 'python-docx via run_shell'), but these are tool/means descriptors rather than a comprehensive list of distinct concrete actions, matching the 'names domain and some actions, but not comprehensive' anchor.	2 / 3
Completeness	It states what the skill does and includes an explicit 'when' trigger ('when standard tools fail'), but that trigger is narrow and 'standard tools' is undefined, so it does not clearly match the comprehensive what-AND-when anchor at level 3.	2 / 3
Trigger Term Quality	'docx files' is a natural user term, but 'python-docx', 'run_shell', and 'XML extraction' are technical jargon, and common variations like '.docx' or 'Word documents/files' are missing, fitting the 'some relevant keywords but missing common variations' anchor.	2 / 3
Distinctiveness Conflict Risk	It carves a clear niche as a fallback ('when standard tools fail') for docx specifically, with a distinct trigger unlikely to fire for unrelated skills, matching the 'clear niche with distinct triggers' anchor.	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-workaround/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.