word-read-write

Create and read Microsoft Word (.docx) documents. Use this skill when you need to generate reports/letters/templates as .docx or extract readable text from existing .docx files.

Quality

73%

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 ./scientific-skills/Other/word-read-write/SKILL.md

Quality

Content

65%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.

Highly actionable with an excellent complete code example, but weakened by generic boilerplate padding, a lack of integrated validation checkpoints in the create workflow, and a disconnect between the body and the bundled office scripts it never surfaces.

Suggestions

Remove or collapse the generic boilerplate tail (Required Inputs, Output Contract, Failure Handling, User Checkpoints, Input Validation, Quick Validation) into skill-specific guidance, keeping only what is unique to word-read-write.

Add an explicit numbered create workflow with a validation checkpoint (e.g., open/verify output.docx, or run scripts/office/validate.py) before declaring success.

Surface the bundled scripts/office tooling (pack/unpack/validate, comment.py, templates) with one-level-deep links from the body so the existing bundle is discoverable rather than orphaned.

Dimension	Reasoning	Score
Conciseness	The core (executable code example + DXA/table gotchas) is efficient, but a long tail of generic boilerplate ("Required Inputs", "Output Contract", "Failure Handling", "User Checkpoints", "Input Validation", "Quick Validation") adds tokens that apply to any skill and could be trimmed.	3 / 5
Actionability	The complete, copy-paste-ready create-doc.js example covers TOC, lists, tables, images, headers/footers, and page breaks, and the pandoc read command is concrete and immediately runnable.	5 / 5
Workflow Clarity	The create (install → write → node) and read (pandoc) sequences are implied but not presented as an explicit ordered workflow, and no output-validation checkpoint is embedded in the create flow despite overwriting being a stated concern.	3 / 5
Progressive Disclosure	Section structure is present, but the ~215-line inlined code example could be a reference file, and the rich bundled scripts/office tooling (pack/unpack/validate, comment tools, templates, schemas) is never referenced or linked from the body.	3 / 5
	Total	14 / 20 Passed

Description

82%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.

A strong description that explicitly pairs a clear 'what' with a concrete 'when' clause and distinct .docx triggers. Minor gaps in action coverage and the second-person 'you' phrasing prevent a perfect score on specificity.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ("Create and read", "generate reports/letters/templates", "extract readable text") but omits supported features the body covers (tables, images, TOC, headers), and the second-person phrasing "when you need to" incurs the rubric's -1 voice penalty from a base of 4.	3 / 5
Completeness	Explicitly answers both what ("Create and read Microsoft Word (.docx) documents") and when ("Use this skill when you need to generate reports/letters/templates as .docx or extract readable text from existing .docx files") with concrete trigger phrases.	5 / 5
Trigger Term Quality	Good natural-term coverage including "Microsoft Word", ".docx", "reports/letters/templates", and "extract readable text", but lacks common synonyms like "Word docs" or "Word files" for full comprehensiveness.	4 / 5
Distinctiveness Conflict Risk	Clearly scoped to Microsoft Word/.docx with distinct triggers (reports, letters, templates, .docx extraction), giving it a clear niche and minimal conflict risk with unrelated skills.	5 / 5
	Total	17 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: aipoch/medical-research-skills
Path: scientific-skills/Other/word-read-write/SKILL.md
Commit: 63c61d3

Reviewed: 3 hours 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.