gmail-automation

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

Quality

64%

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/gmail-automation/SKILL.md

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

Quality

Content

65%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 a strong, fully executable command reference with lean examples for every operation, but it inlines Gmail query-syntax and label-ID reference tables Claude already knows, and lacks validation steps for outward-facing operations like sending email. Moving reference material out of SKILL.md and adding pre-send verification would lift the weakest dimensions.

Suggestions

Move the Gmail query syntax and Common Label IDs tables into a reference file (e.g. references/query-syntax.md) and link to it, trimming SKILL.md to setup plus the command cookbook.

Add a validation step for destructive/outward-facing operations, e.g. create a draft and show it to the user for confirmation before `send-draft`, or verify MESSAGE_ID with a `get --format metadata` call before modifying labels.

Drop or compress the explanations of standard Gmail search operators that Claude already knows, keeping only skill-specific behavior like `--include-spam-trash` and the keyring service name.

Dimension	Reasoning	Score
Conciseness	The command sections are lean and comment-driven, but two sections restate knowledge Claude already has: the 16-row Gmail query-syntax table (from:, to:, is:unread, etc.) and the Common Label IDs table (INBOX, SENT, DRAFT, STARRED...). This is 'mostly efficient but includes some unnecessary explanation or could be tightened' (anchor 3) — the padding is compact tables rather than prose, keeping it above anchor 2.	3 / 5
Actionability	Every example is a fully executable copy-paste command with flags and realistic values, covering the common cases: search with query syntax and --limit/--label, get with --format variants, send with --cc/--bcc/--from/--html, draft creation and sending, and label modification. This matches the 'fully executable; copy-paste ready; specific examples cover the common cases' anchor.	5 / 5
Workflow Clarity	The setup sequence is present and ordered (login, status, logout, with auto-authentication on first use), but outward-facing/destructive operations (sending email, send-draft, batch label modification) have no validation or verification steps — no preview-before-send or confirm-before-modify guidance. Per the rubric guideline, missing validation for destructive/batch operations caps workflow clarity at 3 even though the command sections are clear.	3 / 5
Progressive Disclosure	The body is well-sectioned, but no bundle reference files exist and reference material (the Gmail query-syntax table and Common Label IDs) is inlined in SKILL.md where it belongs in a separate reference file. This matches anchor 3: 'some structure but could be better organized; content that should be separate is inline' — the skill exceeds the under-50-line simple-skill exception, so inline reference material cannot score higher.	3 / 5
	Total	14 / 20 Passed

Description

48%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 identifies a clear niche (Gmail with standalone OAuth, no MCP) but describes no concrete capabilities and gives no usage triggers, so Claude would have trouble knowing when to invoke it or what it can do. It is concise but underspecified.

Suggestions

List the concrete actions the skill performs, e.g. "Search, read, send, and draft Gmail messages; manage labels (archive, star, mark read/unread)".

Add an explicit trigger clause such as "Use when the user asks to search, send, or organize email in a Gmail / Google Workspace account".

Include natural synonyms (email, mail, inbox) alongside "Gmail" so the description matches how users actually phrase requests.

Dimension	Reasoning	Score
Specificity	The description names the domain ("Gmail integration") and a technical property ("standalone OAuth authentication") but lists zero concrete actions such as search, send, read, or label management. This matches the anchor 'Names the domain but actions are minimal or generic', not score 3, which requires 1-2 concrete actions to be listed.	2 / 5
Completeness	The 'what' is only domain-level ('Lightweight Gmail integration' with no enumerated capabilities) and the 'when' is entirely missing — there is no 'Use when...' clause, which caps completeness at 3. It sits above anchor 2 (a real what exists rather than pure vagueness) but has no when guidance at all.	3 / 5
Trigger Term Quality	"Gmail", "OAuth", and "MCP server" are relevant keywords, but the natural phrases users say ("email", "send email", "inbox", "search mail") are missing. Some relevant keywords are present with synonyms and common variations absent, matching anchor 3 rather than 4's 'good keyword coverage'.	3 / 5
Distinctiveness Conflict Risk	"Gmail" is a clear niche and "No MCP server required" distinguishes it from MCP-based Gmail skills, giving minor overlap risk only with closely related email skills. Trigger terms are too thin for the minimal-conflict profile of anchor 5.	4 / 5
	Total	12 / 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: 28 missing	Warning

	Total	14 / 16 Passed

Repository: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: plugins/AI-Agents-Safe-Coding-Skills-claude/skills/gmail-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.