gmail-automation
Automate Gmail tasks via Rube MCP (Composio): send/reply, search, labels, drafts, attachments. Always search tools first for current schemas.
76
65%
Does it follow best practices?
Impact
96%
1.52xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/all-skills/skills/gmail-automation/SKILL.mdQuality
Discovery
67%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 concise and lists specific Gmail capabilities, making it clear what the skill does. However, it lacks an explicit 'Use when...' clause and misses common trigger terms like 'email' or 'inbox' that users would naturally say. The technical reference to 'Rube MCP (Composio)' adds distinctiveness but doesn't help with user-facing discoverability.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user asks about sending emails, managing their inbox, or working with Gmail.'
Include common user-facing trigger terms like 'email', 'e-mail', 'inbox', 'compose', 'mail' to improve discoverability alongside the existing 'Gmail' keyword.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: send/reply, search, labels, drafts, attachments. These are clear, actionable capabilities within the Gmail domain. | 3 / 3 |
Completeness | Clearly answers 'what' (automate Gmail tasks including send/reply, search, labels, drafts, attachments) but lacks an explicit 'Use when...' clause. The 'when' is only implied by the capabilities listed, capping this at 2. | 2 / 3 |
Trigger Term Quality | Includes good keywords like 'Gmail', 'send', 'reply', 'search', 'labels', 'drafts', 'attachments', but misses common user variations like 'email', 'e-mail', 'inbox', 'compose', 'mail'. The mention of 'Rube MCP (Composio)' is technical jargon unlikely to be used by end users. | 2 / 3 |
Distinctiveness Conflict Risk | Clearly scoped to Gmail via Rube MCP/Composio, which is a distinct niche. The specific platform (Gmail) and integration method (Rube MCP/Composio) make it unlikely to conflict with other skills. | 3 / 3 |
Total | 10 / 12 Passed |
Implementation
62%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 Gmail automation skill with clear workflow sequences and comprehensive coverage of pitfalls and edge cases. Its main weaknesses are repetition of warnings across sections (inflating token count), lack of executable call examples, and monolithic structure that could benefit from splitting reference material into separate files. The workflow clarity is strong with good prerequisite identification and sequencing.
Suggestions
Deduplicate pitfalls — consolidate repeated warnings (hex ID formats, thread_id behavior, mimetype format) into the 'Known Pitfalls' section only, and reference it from individual workflows instead of restating.
Add at least one concrete, copy-paste-ready MCP tool call example showing exact parameter structure (e.g., a complete RUBE_SEARCH_TOOLS or GMAIL_SEND_EMAIL invocation with realistic parameters).
Split the Gmail query syntax reference and quick reference table into a separate REFERENCE.md file to reduce the main skill's token footprint and improve progressive disclosure.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is fairly comprehensive but has significant repetition — pitfalls are repeated across sections (e.g., hex ID formats, thread_id behavior, attachment mimetype requirements appear multiple times). The 'Known Pitfalls' section largely duplicates warnings already given in each workflow section. The Gmail query syntax reference is useful but could be more compact. Some explanations like 'User wants to compose and send a new email' are unnecessary. | 2 / 3 |
Actionability | The skill provides specific tool names, parameter names, and key details, which is good. However, there are no executable code examples or copy-paste ready MCP call examples — the 'Common Patterns' section uses pseudocode-like numbered steps rather than actual tool invocation syntax. The guidance is concrete enough to follow but lacks the executable specificity of a score-3 skill. | 2 / 3 |
Workflow Clarity | Each workflow has a clear tool sequence with numbered steps, prerequisite identification, and explicit ordering. The setup section includes a verification step before proceeding. Batch operations note chunking requirements. The label management workflow correctly sequences LIST_LABELS before modifications. Validation is implicit through the prerequisite steps (e.g., always list labels first to get IDs). | 3 / 3 |
Progressive Disclosure | The content is a monolithic single file with no bundle files or references to supplementary documents. At ~250+ lines, the detailed pitfalls, query syntax reference, and quick reference table could be split into separate files. The external link to Composio docs is helpful but the skill itself would benefit from splitting the reference material (query syntax, pitfalls, quick reference) into separate files. | 2 / 3 |
Total | 9 / 12 Passed |
Validation
90%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
- davepoon/buildwithclaude
- Commit
d065ead
- Reviewed
Table of Contents
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.