gws-docs

Read and write Google Docs.

Quality

45%

Does it follow best practices?

Impact

Pending

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Optimize this skill with Tessl

npx tessl skill review --optimize ./skills/gws-docs/SKILL.md

Quality

Discovery

32%

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 minimal and underspecified. While it correctly identifies the platform (Google Docs) and two high-level actions, it lacks specific capabilities, natural trigger terms, and any explicit 'Use when...' guidance that would help Claude reliably select this skill from a large pool.

Suggestions

Add a 'Use when...' clause with explicit triggers, e.g., 'Use when the user asks to create, edit, read, or format a Google Doc, or mentions Google Docs, gdocs, or Google documents.'

List more specific concrete actions such as 'create documents, edit content, format text, insert tables, add comments, and export Google Docs.'

Include natural keyword variations users might say, such as 'Google document', 'gdoc', 'Google Drive document', or '.gdoc'.

Dimension	Reasoning	Score
Specificity	Names the domain (Google Docs) and two actions (read and write), but does not list more specific concrete actions like formatting, commenting, sharing, or template creation.	2 / 3
Completeness	The description answers 'what' at a basic level but completely lacks any 'when' clause or explicit trigger guidance, which per the rubric caps completeness at 2, and since the 'what' is also quite thin, a score of 1 is appropriate.	1 / 3
Trigger Term Quality	'Google Docs' is a strong natural keyword users would say, but the description misses common variations like 'gdocs', 'Google document', 'Docs API', or related terms like 'editing', 'drafting', or 'sharing'.	2 / 3
Distinctiveness Conflict Risk	'Google Docs' is fairly specific and distinguishes it from generic document skills, but 'read and write' is broad enough that it could overlap with other Google Workspace or document-handling skills.	2 / 3
	Total	7 / 12 Passed

Implementation

57%

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

The skill is reasonably well-structured with good progressive disclosure and clear references to related skills. However, it lacks concrete executable examples of actual document operations (create, get, batchUpdate) and includes verbose API description text that could be trimmed. Adding at least one complete end-to-end example would significantly improve actionability.

Suggestions

Add at least one complete executable example showing a full command, e.g., `gws docs documents create --params 'title=My Doc'` and `gws docs documents get --params 'documentId=abc123'`

Trim the verbose batchUpdate description to essentials—Claude doesn't need the explanation of validation behavior; a one-line summary suffices

Add an explicit workflow sequence for common tasks like 'create a doc then write to it' with validation steps (e.g., verify document was created before writing)

Dimension	Reasoning	Score
Conciseness	Mostly efficient, but the `batchUpdate` description is overly verbose with explanations Claude doesn't need (e.g., 'Each request is validated before being applied. If any request is not valid, then the entire request will fail...'). These read like API docs copy-pasted verbatim rather than distilled for Claude.	2 / 3
Actionability	Provides concrete CLI commands for discovery (`gws docs --help`, `gws schema`), but lacks executable examples of actually creating, getting, or updating a document. There's no example of a complete `--params` or `--json` invocation.	2 / 3
Workflow Clarity	The discovery workflow (inspect → build params → call) is implied but not explicitly sequenced. For batchUpdate, which is a potentially destructive batch operation, there are no validation or verification steps mentioned, which should cap this at 2.	2 / 3
Progressive Disclosure	Good structure with clear references: prerequisite points to shared skill, helper command links to a separate write skill, and the discovering commands section is well-placed. Navigation is one level deep and clearly signaled.	3 / 3
	Total	9 / 12 Passed

Validation

90%

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 — 10 / 11 Passed

Validation for skill structure

Criteria	Description	Result
metadata_field	'metadata' should map string keys to string values	Warning

	Total	10 / 11 Passed

Repository: googleworkspace/cli
Commit: c7c6646

Reviewed: about 7 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.