gmail-automation

Lightweight Gmail integration with standalone OAuth authentication. No MCP server required.

Quality

53%

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 ./skills/gmail-automation/SKILL.md

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

Quality

Content

71%Scale 1-5

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

This is a well-structured CLI reference skill with excellent actionability — every command is concrete and copy-paste ready. Its main weakness is including substantial reference material (Gmail query syntax, label IDs) that Claude already knows, which hurts both conciseness and progressive disclosure. The workflow is clear but could benefit from brief error handling or verification guidance.

Suggestions

Remove or drastically reduce the Gmail Query Syntax table and Common Label IDs table — Claude already knows Gmail search operators and standard label names. At most, include 2-3 non-obvious examples.

Add brief verification guidance after send/modify operations (e.g., 'Verify send success by checking the returned message ID' or 'If auth fails, re-run scripts/auth.py login').

Consider extracting the query syntax and label reference into a separate REFERENCE.md file if you want to preserve it, keeping SKILL.md focused on the command interface.

Dimension	Reasoning	Score
Conciseness	The skill is mostly efficient with concrete commands, but the Gmail Query Syntax table and Common Label IDs table are reference material Claude already knows well. The query syntax section in particular adds significant token cost for information that's standard Gmail knowledge.	3 / 5
Actionability	Every command is fully executable and copy-paste ready with realistic examples covering common use cases. The CLI interface is clearly documented with flags and arguments for all operations including search, send, draft, and label modification.	5 / 5
Workflow Clarity	The setup flow (auth → commands) is clear and the commands are well-organized by operation type. However, there are no validation steps or error handling guidance for potentially problematic operations like sending emails or modifying labels (e.g., confirming send success, handling auth failures). Since send is not destructive/batch in the traditional sense, this doesn't trigger the cap at 3, but some verification guidance would improve it.	4 / 5
Progressive Disclosure	The content is reasonably structured with clear section headers, but the Gmail Query Syntax table and Common Label IDs table are reference material that would be better placed in a separate reference file. The skill inlines ~40 lines of reference content that inflates the main file. No bundle files are provided to offload this content.	3 / 5
	Total	15 / 20 Passed

Description

36%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 identifies the domain (Gmail) and differentiates its implementation approach (standalone OAuth, no MCP), but fails to describe any concrete capabilities or provide trigger guidance. It reads more like a technical architecture note than a skill description, leaving Claude unable to determine when to select it over other skills.

Suggestions

Add concrete actions the skill performs, e.g., 'Send, read, search, and draft emails in Gmail'

Add a 'Use when...' clause with natural trigger terms like 'Use when the user asks to send email, check inbox, read messages, or compose mail via Gmail'

Include common synonyms and related terms like 'email', 'inbox', 'messages', 'mail' to improve trigger matching

Dimension	Reasoning	Score
Specificity	Names the domain (Gmail) but describes no concrete actions. 'Integration' is vague—it doesn't specify whether it sends, reads, searches, or drafts emails. The only specifics are about the implementation approach (OAuth, no MCP server), not capabilities.	2 / 5
Completeness	The 'what' is vague ('Gmail integration' without specifying actions), and there is no 'when' clause at all. The description focuses on implementation details (OAuth, no MCP server) rather than answering what it does or when to use it.	2 / 5
Trigger Term Quality	'Gmail' is a strong natural keyword users would say, and 'OAuth' is relevant for developers. However, it's missing common user-facing terms like 'email', 'send email', 'inbox', 'read messages', 'compose', or 'mail'.	3 / 5
Distinctiveness Conflict Risk	'Gmail' is fairly specific and distinguishes it from generic email skills, but 'integration' is broad enough that it could overlap with other Gmail-related skills (e.g., a Gmail MCP skill). The 'no MCP server' qualifier helps differentiate somewhat but is an implementation detail.	3 / 5
	Total	10 / 20 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	10 / 11 Passed

Repository: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: skills/gmail-automation/SKILL.md
Commit: 57c135b

Reviewed: 4 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.