docx-read-fallback

Use run_shell with python-docx as reliable fallback when read_file fails on .docx files

Quality

74%

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-read-fallback/SKILL.md

Quality

Content

86%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 content is highly actionable with copy-paste-ready extraction commands covering the common docx cases and a clear fallback workflow. Its only real weaknesses are minor command duplication and an implicit rather than explicit error-recovery loop in the workflow.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean code with brief section intros and no padding about what a docx is, but the basic extraction command is duplicated in both a bash block and a run_shell block and a couple of tips slightly over-explain, keeping it just below anchor 5.	4 / 5
Actionability	Provides fully executable, copy-paste-ready commands covering the common cases (text, paragraphs with indices, tables, headings) plus a prerequisite check and install step, matching the anchor 5 example.	5 / 5
Workflow Clarity	The 'Example Workflow' gives a clear 5-step sequence with a verification checkpoint (verify python-docx availability), but explicit error-recovery feedback for a second failure is only implicit, so it does not reach the validation-loop anchor 5; the destructive/batch cap does not apply since this is read-only.	4 / 5
Progressive Disclosure	The skill is self-contained in a single, well-sectioned file (When to Use, How to Use, Prerequisites, Tips, Example Workflow) with clear headers and easy navigation, and no content needs splitting into external references, fitting the well-organized simple-skill anchor 5.	5 / 5
	Total	18 / 20 Passed

Description

62%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 clearly states a concrete fallback action and an explicit trigger condition, giving it solid what/when coverage. It is held back from the top band by a single named action, a tool-internal trigger phrase, and missing user-facing synonyms like 'Word document'.

Suggestions

Broaden the trigger to user-facing language, e.g. 'when read_file fails on Word/.docx files or the user needs text from a Word document'.

Mention additional concrete actions (e.g. extract paragraphs, tables, and headings) to lift specificity from 1-2 actions to several.

Add common synonyms such as 'Word document' alongside '.docx files' to improve natural keyword coverage.

Dimension	Reasoning	Score
Specificity	Names the domain (reading .docx files) and one concrete method ('Use run_shell with python-docx as reliable fallback'), but does not enumerate multiple specific actions, fitting the '1-2 concrete actions' anchor rather than the multi-action anchor 4.	3 / 5
Completeness	Explicitly answers both 'what' (run_shell with python-docx fallback) and 'when' ('when read_file fails on .docx files'), but the 'when' is technical rather than a broad user-facing trigger phrase, so it sits below anchor 5.	4 / 5
Trigger Term Quality	Includes the natural file extension '.docx files' and a trigger ('when read_file fails'), but the trigger is tool-internal jargon and it omits common synonyms like 'Word document' that users would say, matching anchor 3.	3 / 5
Distinctiveness Conflict Risk	Targets a clear niche (docx read-fallback) with a distinct trigger condition, with only minor overlap risk against a general docx-handling skill, matching anchor 4 rather than the minimal-conflict anchor 5.	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-read-fallback/SKILL.md
Commit: 3827781

Reviewed: 25 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.