CtrlK
BlogDocsLog inGet started
Tessl Logo

google-docs

Google Docs via gws: read, append text, structured batch edits.

56

Quality

66%

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/google/google-docs/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

65%Weight 40%Scale 1-3

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 executable `gws` commands and complete batchUpdate examples, but it carries redundancy between the "When NOT to Use" section and Rules 5–6, lacks a full validation feedback loop for batch operations, and keeps all detail inline in one file. Tightening the duplicate guidance, adding an explicit verify step for batch edits, and splitting account-selection/API detail into referenced files would lift the weaker dimensions.

Suggestions

De-duplicate Rules 5–6 against the "When NOT to Use" section, or fold them into a single "Boundaries" reference.

Add an explicit validation step for batchUpdate (e.g. re-read the doc or verify the reply contains the expected replies before proceeding).

Move the shared "Selecting a Google account" guidance and detailed batchUpdate request catalog into referenced files (e.g. ACCOUNTS.md, BATCHUPDATE.md) so the body stays a lean overview.

DimensionReasoningScore

Conciseness

The body is mostly concrete commands, but Rules 5–6 duplicate the "When NOT to Use" guidance (google-drive, apple-notes/obsidian) and the Prerequisites and account-selection prose could be tightened.

2 / 3

Actionability

It provides copy-paste-ready `gws docs` commands, full `batchUpdate` JSON request examples, a `jq` plain-text recipe, and `gws schema` introspection — fully executable guidance.

3 / 3

Workflow Clarity

The setup flow is numbered and batchUpdate has a "check the reply" checkpoint, but there is no explicit validate→fix→retry feedback loop for batch or destructive edits, which the rubric emphasizes.

2 / 3

Progressive Disclosure

Sections are well-organized, but this is a single monolithic ~150-line file with no external references, and the account-selection and detailed API examples are inline content that could be split out.

2 / 3

Total

9

/

12

Passed

Description

67%Weight 40%Scale 1-3

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 distinctive, naming three concrete Google Docs content actions, but it omits any explicit "Use when..." trigger and leans on one piece of technical jargon ("structured batch edits"). Adding a brief trigger clause and a more natural phrasing for batch edits would raise completeness and trigger-term quality.

Suggestions

Add an explicit trigger clause, e.g. "Use when reading, drafting, or editing the body of a Google Doc."

Replace or supplement the technical phrase "structured batch edits" with natural terms like "apply formatting or make batch edits."

Include common user verbs such as "create" alongside read/append to broaden trigger coverage.

DimensionReasoningScore

Specificity

The description lists three concrete actions — "read, append text, structured batch edits" — matching the score-3 anchor for multiple specific concrete actions.

3 / 3

Completeness

It states what the skill does (read, append, batch edits on Google Docs) but includes no "Use when..." trigger clause, so per the guideline a missing explicit trigger caps completeness at 2.

2 / 3

Trigger Term Quality

"Google Docs" and "read"/"append text" are natural terms, but "structured batch edits" is technical jargon and common user variations such as "edit" or "create a doc" are missing.

2 / 3

Distinctiveness Conflict Risk

"Google Docs via gws" combined with content-only verbs carves a clear niche unlikely to conflict with google-drive, sheets, or slides.

3 / 3

Total

10

/

12

Passed

Validation

87%

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

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

Total

14

/

16

Passed

Repository
Open-Curiosity/gini-agent
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.