gmail-automation
Automate Gmail tasks via Rube MCP (Composio): send/reply, search, labels, drafts, attachments. Always search tools first for current schemas.
80
72%
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 strong on specificity and distinctiveness, listing concrete Gmail actions and naming the specific integration. However, it lacks an explicit 'Use when...' clause and misses common trigger terms like 'email' or 'inbox' that users would naturally say. The operational instruction about searching tools first, while useful, takes space that could be used for trigger guidance.
Suggestions
Add a 'Use when...' clause, e.g., 'Use when the user asks about sending email, managing their inbox, or any Gmail-related task.'
Include common user-facing trigger terms like 'email', 'e-mail', 'inbox', 'compose', 'mail' alongside 'Gmail' to improve matching on natural user language.
| 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: send/reply, search, labels, drafts, attachments) but lacks an explicit 'Use when...' clause. The 'when' is only implied by the domain mention. The instruction to 'always search tools first' is operational guidance, not a trigger condition. | 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 technical term 'Rube MCP (Composio)' is internal jargon unlikely to be used by users. | 2 / 3 |
Distinctiveness Conflict Risk | Clearly scoped to Gmail via a specific integration (Rube MCP/Composio), making it highly distinct. The combination of Gmail + specific MCP tool creates a clear niche unlikely to conflict with other skills. | 3 / 3 |
Total | 10 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a comprehensive and highly actionable Gmail automation skill with excellent workflow clarity, specific tool sequences, and thorough pitfall documentation. Its main weakness is length and repetition — the same warnings about ID formats and label operations appear multiple times across sections, and the entire reference could benefit from splitting detailed content into separate files. Despite the verbosity, the content is genuinely useful and provides concrete, executable guidance throughout.
Suggestions
Deduplicate repeated pitfalls (ID formats, label ID resolution, attachment mimetype) by consolidating them in the 'Known Pitfalls' section and referencing it from workflows instead of restating.
Extract the Gmail Query Syntax section and Quick Reference table into separate reference files (e.g., GMAIL_QUERY_SYNTAX.md, GMAIL_TOOLS_REFERENCE.md) to reduce the main file size and improve progressive disclosure.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is quite long (~250 lines) with some repetition across sections — pitfalls are repeated in both workflow-specific sections and the 'Known Pitfalls' summary. Some information (like ID format warnings) appears 3+ times. However, most content is genuinely useful reference material rather than explaining concepts Claude already knows. | 2 / 3 |
Actionability | Provides specific tool names, exact parameter names, concrete examples of valid/invalid values (e.g., hex string formats, 'Label_123'), Gmail query syntax with examples, and clear tool sequences for each workflow. The guidance is highly specific and directly executable via MCP tool calls. | 3 / 3 |
Workflow Clarity | Each workflow has a clear numbered tool sequence with prerequisite/required/optional annotations, explicit pitfalls per step, and the setup section includes a verification flow. Batch operations note the 1000-message limit with chunking guidance. The pagination pattern includes a clear termination condition (nextPageToken absent). | 3 / 3 |
Progressive Disclosure | The content is well-structured with clear sections and a quick reference table, but it's monolithic — all content is inline in a single file. The detailed pitfalls, query syntax reference, and common patterns could be split into separate reference files. The toolkit docs link is provided but no internal file references exist for deeper content. | 2 / 3 |
Total | 10 / 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
7cc63f3
- 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.