outlook-automation
Automate Outlook tasks via Rube MCP (Composio): emails, calendar, contacts, folders, attachments. Always search tools first for current schemas.
73
60%
Does it follow best practices?
Impact
97%
1.53xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/all-skills/skills/outlook-automation/SKILL.mdQuality
Discovery
57%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 (Outlook automation via Rube MCP/Composio) and lists the major categories of functionality, making it distinctive. However, it lacks specific concrete actions within each category and is missing an explicit 'Use when...' clause, which limits its effectiveness for skill selection. The trigger terms cover the basics but miss common user phrasings.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user asks to send emails, schedule meetings, manage contacts, or perform any Outlook-related task.'
Replace category nouns with specific actions, e.g., 'send/read/search emails, schedule/cancel meetings, create contacts, manage folders, download attachments'
Include additional natural trigger terms like 'inbox', 'schedule meeting', 'appointment', 'Microsoft Outlook', 'mail' to improve matching
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | It names the domain (Outlook) and lists categories of actions (emails, calendar, contacts, folders, attachments) but doesn't describe specific concrete actions like 'send emails, schedule meetings, create contacts'. The categories are somewhat vague. | 2 / 3 |
Completeness | It answers 'what' (automate Outlook tasks) and includes an operational instruction ('always search tools first'), but lacks an explicit 'Use when...' clause specifying when Claude should select this skill. The when is only implied by the domain mention. | 2 / 3 |
Trigger Term Quality | Includes 'Outlook', 'emails', 'calendar', 'contacts', 'folders', 'attachments' which are natural terms users might say. However, it's missing common variations like 'schedule meeting', 'send email', 'inbox', 'appointment', 'Microsoft Outlook', or '.msg' that users would naturally use. | 2 / 3 |
Distinctiveness Conflict Risk | The description is clearly scoped to Outlook via Rube MCP (Composio), which is a very specific niche. The mention of the specific MCP tool and Outlook makes it unlikely to conflict with other skills. | 3 / 3 |
Total | 9 / 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 solid reference skill for Outlook automation via Rube MCP with well-organized workflows, clear tool sequencing, and useful pitfall documentation. Its main weaknesses are the lack of concrete executable examples (actual MCP call payloads) and some content redundancy across sections. The monolithic structure could benefit from splitting reference material into separate files.
Suggestions
Add at least one concrete, copy-paste-ready MCP tool call example per major workflow (e.g., an actual RUBE_SEARCH_TOOLS call with input JSON and expected response structure) to improve actionability.
Extract the KQL/OData syntax references and the quick reference table into separate bundle files (e.g., SYNTAX_REFERENCE.md, QUICK_REFERENCE.md) and link to them from the main skill to improve progressive disclosure.
Remove duplicate pitfall information—consolidate account type limitations and field confusion warnings into the 'Known Pitfalls' section only, referencing it from individual workflows rather than repeating.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably efficient but includes some redundancy—pitfalls are repeated across sections (e.g., account type limitations mentioned in both workflow #1 and the 'Known Pitfalls' section), and the quick reference table largely duplicates information already covered in the workflow sections. Some sections like Contacts and Mail Folders are thin enough to consolidate. | 2 / 3 |
Actionability | The skill provides specific tool names, parameter names, and query syntax examples, which is good. However, there are no executable code snippets or concrete MCP call examples showing exact input/output JSON. The guidance is specific but stops short of copy-paste ready tool invocations with example payloads. | 2 / 3 |
Workflow Clarity | Multi-step workflows are clearly sequenced with numbered steps, labeled as [Required]/[Optional]/[Prerequisite], and include explicit validation checkpoints (e.g., 'Confirm connection status shows ACTIVE before running any workflows', checking pagination flags, verifying folder IDs before operations). The setup flow has a clear verify-then-proceed pattern. | 3 / 3 |
Progressive Disclosure | The content is well-structured with clear sections and a useful quick reference table, but it's a monolithic ~180-line file with no bundle files to offload detailed reference material. The KQL and OData syntax sections, the full quick reference table, and per-workflow pitfalls could be split into separate reference files for better progressive disclosure. | 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
74c7031
- 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.