google-workspace

Access Google Workspace APIs (Drive, Docs, Calendar, Gmail, Sheets, Slides, Chat, People) via local helper scripts without MCP. Handles OAuth login and direct API calls.

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Critical

Do not install without reviewing

Quality

Content

85%

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

Highly actionable content with executable examples, a clear error-recovery workflow, and clean progressive disclosure to two real bundle scripts; the only weakness is mild redundancy between the Agent guidance list and the unauthorized playbook.

Suggestions

Merge the 'Unauthorized/account-switch playbook' into the relevant Agent guidance items (or link from them) to remove the duplicated enumerate -> retry -> re-login sequence.

Consider trimming the long Gmail counting example or moving it to a separate examples reference file so the main SKILL.md stays a lean overview.

Dimension	Reasoning	Score
Conciseness	The body is lean and avoids explaining concepts Claude already knows (no OAuth/Google-Workspace tutorials), but the 'Unauthorized/account-switch playbook' restates the enumerate -> retry -> re-login sequence already covered by Agent guidance items 5-8, leaving redundancy that could be tightened.	2 / 3
Actionability	Every example is fully executable and copy-paste ready: 'node scripts/auth.js accounts', 'node scripts/workspace.js exec --email ... <<JS', and complete JS using workspace.call/whoAmI, with no pseudocode.	3 / 3
Workflow Clarity	The unauthorized playbook gives an explicit numbered sequence (enumerate profiles -> retry with intended account -> re-login if stale/missing scopes -> retry original request) with validation via workspace.whoAmI() and feedback loops for 401/403 recovery.	3 / 3
Progressive Disclosure	A clear overview with a 'Files' section that one-line describes and links to scripts/auth.js and scripts/workspace.js (both verified to exist), keeping executable logic in the bundle and SKILL.md as the well-signaled, one-level-deep overview.	3 / 3
	Total	11 / 12 Passed

Description

82%

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, specific description that names concrete services and actions and occupies a clear niche, but it omits an explicit 'Use when' trigger clause, capping completeness at 2.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user asks to read or send Gmail, list/edit Drive or Docs files, manage Calendar events, or work with Sheets/Slides/Chat/People data.'

Drop or soften the implementation detail 'without MCP' from the description since it is a transport note rather than a user-facing trigger.

Dimension	Reasoning	Score
Specificity	Enumerates eight concrete Google services (Drive, Docs, Calendar, Gmail, Sheets, Slides, Chat, People) plus explicit actions 'Handles OAuth login and direct API calls', matching the anchor for multiple specific concrete actions rather than just a named domain.	3 / 3
Completeness	Clearly answers 'what' (access the listed APIs, OAuth login, direct API calls) but lacks any 'Use when...' or equivalent explicit trigger guidance, so per the rubric guideline completeness is capped at 2 with 'when' only implied.	2 / 3
Trigger Term Quality	Includes natural terms users say ('Google Workspace', 'Drive', 'Gmail', 'Calendar', 'Sheets', 'OAuth'); the 'local helper scripts without MCP' framing is mildly jargon-ish but the broad service-name coverage matches the good-coverage anchor.	3 / 3
Distinctiveness Conflict Risk	'Google Workspace APIs via local helper scripts without MCP' is a distinct niche tied to a named product family with service-specific triggers, making it unlikely to fire for unrelated skills.	3 / 3
	Total	11 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: mitsuhiko/agent-stuff
Path: skills/google-workspace/SKILL.md
Commit: d265b8e

Reviewed: 5 days 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.