gmail-automation

Automate Gmail tasks via Rube MCP (Composio): send/reply, search, labels, drafts, attachments. Always search tools first for current schemas.

1.52x

Quality

73%

Does it follow best practices?

Impact

96%

1.52x

Average score across 3 eval scenarios

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./plugins/all-skills/skills/gmail-automation/SKILL.md

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 content is highly actionable and well-structured but loses points for duplicated material, missing feedback loops on destructive/batch operations, and lack of any external reference offloading despite its length.

Suggestions

Add an explicit validate->fix->retry loop to the destructive/batch workflows (e.g. after BATCH_MODIFY_MESSAGES, verify label changes via FETCH_EMAILS; confirm before DELETE_LABEL).

Deduplicate the 'Known Pitfalls' section against each workflow's Pitfalls block, or move the consolidated pitfall reference into a separate file referenced once.

Offload the full Gmail Query Syntax reference and the Quick Reference table into a one-level-deep reference file (e.g. REFERENCE.md) to improve progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The body is dense and reference-style without explaining basics Claude knows, but the 'Known Pitfalls' section duplicates pitfalls already stated in each workflow and the Quick Reference table repeats tool/param info, so it could be tightened.	3 / 5
Actionability	Concrete tool names, exact parameter formats (e.g. thread_id hex string, mimetype must contain '/'), and hard limits (1000 messages, 25MB) give fully executable, copy-ready guidance across common cases.	5 / 5
Workflow Clarity	Workflows are well sequenced with [Required]/[Optional]/[Prerequisite]/[Fallback] tags and a connection-status checkpoint, but destructive (DELETE_LABEL) and batch (BATCH_MODIFY_MESSAGES) operations lack an explicit validate->fix->retry feedback loop, which the rubric caps at 3.	3 / 5
Progressive Disclosure	No bundle files exist and the ~266-line body is well sectioned, but bulk reference content (full query-syntax reference, Quick Reference table, a second Known Pitfalls section) is inlined rather than offloaded to a one-level-deep reference file.	3 / 5
	Total	14 / 20 Passed

Description

82%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 is specific, distinctive, and trigger-rich, but it lacks an explicit 'when to use' clause, which the rubric caps at 3 for completeness. Adding a 'Use when...' sentence would likely raise completeness and the overall score.

Suggestions

Append an explicit trigger clause, e.g. 'Use when the user asks to send, reply to, search, label, or draft Gmail emails.'

Optionally include common phrasings users say ('email someone', 'find unread emails', 'organize my inbox') to strengthen trigger-term naturalness further.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ('send/reply, search, labels, drafts, attachments') giving comprehensive coverage of the Gmail toolkit surface, matching the score-5 anchor.	5 / 5
Completeness	The 'what' is concrete and specific, but there is no 'Use when...' clause or equivalent trigger guidance; per the rubric, a missing trigger clause caps completeness at 3.	3 / 5
Trigger Term Quality	Natural user-facing terms (Gmail, send, reply, search, labels, drafts, attachments) appear with synonym coverage, matching the comprehensive score-5 anchor.	5 / 5
Distinctiveness Conflict Risk	'Automate Gmail tasks via Rube MCP (Composio)' carves a clear niche with distinct triggers and minimal conflict risk with other skills.	5 / 5
	Total	18 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: davepoon/buildwithclaude
Path: plugins/all-skills/skills/gmail-automation/SKILL.md
Commit: a9fa86d

Reviewed: about 21 hours 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.