CtrlK
BlogDocsLog inGet started
Tessl Logo

docx-shell-parse

Extract text from DOCX files using shell commands when python-docx is unavailable

55

Quality

61%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./benchmarks/gdpval/skills/docx-shell-parse/SKILL.md
SKILL.md
Quality
Evals
Security

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 skill is highly actionable with executable commands and a reusable function, and it is well-organized as a self-contained file. Its main weaknesses are repetition of the same command and a shallow verification step without an error-recovery feedback loop.

Suggestions

Collapse the repeated unzip|sed one-liner into a single canonical example and reference it from the variations, removing redundant sections.

Remove or shorten the "DOCX files are ZIP archives containing XML files" concept explanation, which Claude already knows.

Strengthen the verification step into an explicit feedback loop, e.g. check that output is non-empty and advise re-checking the file path or format if extraction returns nothing.

DimensionReasoningScore

Conciseness

The body explains a concept Claude already knows ("DOCX files are ZIP archives containing XML files") and repeats the same unzip|sed one-liner across five sections, so it could be tightened considerably.

2 / 3

Actionability

It provides fully executable shell commands and a complete, copy-paste-ready parse_docx function with error handling.

3 / 3

Workflow Clarity

Steps are sequenced (1-5) with a verification section, but the verification is shallow ("| head -20") and there is no validate->fix->retry feedback loop for the XML manipulation.

2 / 3

Progressive Disclosure

It is a single self-contained file organized into clear, well-labeled sections with no nested references and no need for external bundle files.

3 / 3

Total

10

/

12

Passed

Description

50%

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 concrete and names a clear niche, but it lists only one action, omits explicit "Use when..." trigger guidance, and has limited keyword coverage. It is solid but not comprehensive.

Suggestions

Add a "Use when..." clause listing natural triggers, e.g. "Use when python-docx is unavailable or when you need to extract text from Word (.docx) files in a constrained shell environment."

Broaden trigger terms to include "Word documents", "Word files", and ".docx" alongside "DOCX files".

Mention additional concrete actions if applicable (e.g. extracting to a temp directory) to raise specificity.

DimensionReasoningScore

Specificity

"Extract text from DOCX files" names a concrete action and domain, but only a single action is listed rather than multiple specific capabilities.

2 / 3

Completeness

It states what the skill does and a "when python-docx is unavailable" condition, but lacks an explicit "Use when..." trigger clause, which caps completeness at 2.

2 / 3

Trigger Term Quality

"DOCX files", "text", and "python-docx" are relevant keywords, but common natural variations like "Word documents", "Word files", or ".docx" are missing.

2 / 3

Distinctiveness Conflict Risk

The shell-fallback niche is somewhat distinct, but limited trigger terms mean it could still overlap with a general DOCX extraction skill.

2 / 3

Total

8

/

12

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
HKUDS/OpenSpace
Reviewed

Table of Contents

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.