CtrlK
BlogDocsLog inGet started
Tessl Logo

word-analysis

Word (.docx/.doc) 文档全量解析。覆盖:正文/段落文本提取、表格数据提取、高亮/颜色格式读取、多文件汇总对比、嵌入图片转 caption。

60

Quality

70%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/sn-da-non-spreadsheet-analysis/capability/word-analysis/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

68%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 a lean, code-dense reference with strong actionability and good section structure, but it relies on an unresolved placeholder path for image captioning and lacks explicit validation checkpoints for its batch and format-conversion operations.

Suggestions

Resolve the placeholder CAPTION path to the real sn-da-image-caption script (or document the dependency and how to locate it) so Method 5 is directly executable.

Add explicit validation checkpoints for fragile/batch operations — e.g., verify the libreoffice .doc→.docx conversion produced a valid file before loading, and add a validate→fix→retry note for multi-file processing.

Add a short table of contents or 'When to use which method' overview at the top to aid navigation across the five core methods in this 270-line skill.

DimensionReasoningScore

Conciseness

The body is almost entirely executable code with brief, useful framing and no padding or concept explanations Claude already knows; a few '# Usage' preview blocks and obvious inline comments could be trimmed, keeping it just below the leanest anchor.

4 / 5

Actionability

Provides concrete, mostly copy-paste-ready functions for every method, but Method 5 depends on a placeholder CAPTION path ('/path/to/skills/sn-da-image-caption/scripts/caption.py') that does not resolve, and the multi-file example references an undefined 'all_files' variable — minor execution gaps.

4 / 5

Workflow Clarity

The content is organized as five parallel recipes with implicit error handling (try/except, check=True), but there are no explicit validate→fix→retry checkpoints for the batch multi-file and fragile .doc-conversion operations, so the batch-operations cap holds at 3.

3 / 5

Progressive Disclosure

No bundle files exist and the body is well-organized into clearly headed sections (Environment, Core Methods 1–5, Common Patterns, Pitfalls); at ~270 lines it lacks a table of contents or navigation aid, a minor organization gap that keeps it below 5.

4 / 5

Total

15

/

20

Passed

Description

71%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 capability-rich, clearly conveying what the skill does across five concrete Word-analysis actions, but it omits any explicit 'when to use' trigger guidance, which caps completeness and slightly weakens trigger-term quality and distinctiveness.

Suggestions

Add an explicit 'Use when...' clause naming natural trigger phrases users would say (e.g., 'Use when parsing Word documents, extracting tables or highlighted text, comparing multiple .docx files, or captioning embedded images').

Include a few more natural synonyms/variations alongside the capability list (e.g., '批量处理', '全文检索', '.doc 兼容') to broaden trigger-term coverage.

Reframe the capability list slightly toward user-utterance phrasing so the trigger terms read as things a user would actually say rather than a feature inventory.

DimensionReasoningScore

Specificity

Lists five concrete actions — '正文/段落文本提取', '表格数据提取', '高亮/颜色格式读取', '多文件汇总对比', '嵌入图片转 caption' — giving comprehensive coverage of the skill's capabilities, matching the anchor for multiple specific concrete actions.

5 / 5

Completeness

The 'what' is clearly and explicitly stated, but there is no 'Use when...' clause or equivalent explicit trigger guidance for when to invoke the skill; the missing-when guideline caps this at 3.

3 / 5

Trigger Term Quality

Includes file extensions (.docx/.doc) and natural terms (文档, 表格, 高亮/颜色), but the phrasing is a capability list rather than user-utterance trigger phrases and a few natural synonyms are missing, so it sits just below the comprehensive-coverage anchor.

4 / 5

Distinctiveness Conflict Risk

The Word (.docx/.doc) framing and format-aware features (highlight/color, embedded-image caption) make it mostly distinct with only minor overlap risk against generic document-extraction skills; absence of explicit trigger phrases keeps it just below a 5.

4 / 5

Total

16

/

20

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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
OpenSenseNova/SenseNova-Skills
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.