google-drive-automation

Lightweight Google Drive integration with standalone OAuth authentication. No MCP server required. Full read/write access.

Quality

70%

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 ./plugins/AI-Agents-Safe-Coding-Skills-claude/skills/google-drive-automation/SKILL.md

The canonical home for this skill is google-drive in sanjay3290/ai-skills

Quality

Content

76%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 an excellent, lean CLI reference with fully executable commands for every supported operation. Its weaknesses are the absence of verification steps around destructive operations (trash/move/rename) and references to script files that are not present in the bundle.

Suggestions

Add a verification step before destructive commands, e.g. 'Before trash/move, confirm the file ID with search or list, since trashed-file recovery is not covered by this skill.'

Ship the referenced scripts/auth.py and scripts/drive.py in the bundle, or note where they come from — every command in the skill depends on them.

Trim the repeated description line under the title and condense the OS-specific keyring details in Token Management.

Dimension	Reasoning	Score
Conciseness	The body is almost entirely lean, executable command examples with minimal prose, assuming Claude's competence. Minor trims are available: the frontmatter description is repeated verbatim as the opening line, and the Token Management section includes OS-by-OS keyring detail that could be condensed — matching the 'efficient; minor instances' anchor.	4 / 5
Actionability	Every operation (auth, search, list, download, upload, create-folder, move, copy, rename, trash) has a copy-paste-ready command with realistic arguments, and the search formats table covers the common cases — fully executable guidance.	5 / 5
Workflow Clarity	The sequence is present (first-time login, then per-task commands with auto-authentication), but destructive operations (trash, move, rename) and batch listings carry no verification steps — e.g., confirming a file ID via search/list before trashing. Per the judging guidelines, destructive operations without validation cap workflow clarity at 3.	3 / 5
Progressive Disclosure	Good single-file structure with clear sections (setup, read, write, query formats, limitations) and no nested references, appropriate for a CLI-reference skill. Scored against the actual bundle: the body references scripts/auth.py and scripts/drive.py, but no scripts/ directory exists in the bundle — dangling entry-point references prevent a 5.	4 / 5
	Total	16 / 20 Passed

Description

53%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 identifies the domain and a differentiating implementation detail (standalone OAuth, no MCP server), but it stops short of naming concrete operations and provides no 'when to use' trigger guidance. Adding a Use-when clause and concrete actions would lift it substantially.

Suggestions

Append an explicit trigger clause, e.g. 'Use when the user asks to search, upload, download, or organize files in Google Drive.'

Replace the generic 'Full read/write access' with named concrete operations (search, upload, download, create folders, move/copy/rename files).

Add natural trigger terms users actually say — 'Google Drive files', 'upload to Drive', 'Drive folder' — to improve keyword coverage.

Dimension	Reasoning	Score
Specificity	Names the domain ('Google Drive integration') and mentions 'OAuth authentication' and 'Full read/write access', but these are coarse capability claims rather than concrete operations like search, upload, or download — sitting between the generic-actions anchor (2) and the 1-2-concrete-actions anchor (3).	3 / 5
Completeness	The 'what' is clear (Google Drive integration with standalone OAuth, full read/write), but there is no 'Use when...' clause or equivalent explicit trigger guidance, capping completeness at 3 per the judging guidelines.	3 / 5
Trigger Term Quality	'Google Drive' is a strong natural keyword users would say, but common trigger variations are absent: no mention of 'files', 'upload', 'download', 'folders', or 'share' — matching the 'some relevant keywords but missing common variations' anchor.	3 / 5
Distinctiveness Conflict Risk	'Google Drive integration... No MCP server required' carves out a clear niche distinct from generic file skills, with only minor overlap risk against closely related Google Workspace/Docs skills.	4 / 5
	Total	13 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
referenced_paths_exist	Referenced path issues: 23 missing	Warning

	Total	14 / 16 Passed

Repository: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: plugins/AI-Agents-Safe-Coding-Skills-claude/skills/google-drive-automation/SKILL.md
Commit: 64adc55

Reviewed: 6 minutes 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.