outlook-calendar-automation
Automate Outlook Calendar tasks via Rube MCP (Composio): create events, manage attendees, find meeting times, and handle invitations. Always search tools first for current schemas.
74
65%
Does it follow best practices?
Impact
90%
1.16xAverage 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-calendar-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 in specificity and distinctiveness, clearly naming the tool ecosystem and concrete calendar operations. Its main weaknesses are the lack of an explicit 'Use when...' trigger clause and incomplete coverage of natural user language variations (e.g., 'schedule a meeting', 'book time'). Adding explicit trigger guidance and more user-facing synonyms would make this description excellent.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user asks to schedule meetings, check calendar availability, send calendar invites, or manage Outlook Calendar events.'
Include more natural user trigger terms such as 'schedule a meeting', 'book time', 'calendar invite', 'reschedule', 'cancel meeting', and 'check availability'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'create events, manage attendees, find meeting times, and handle invitations.' Also specifies the tool chain (Rube MCP, Composio) and includes a procedural note about searching tools first. | 3 / 3 |
Completeness | Clearly answers 'what does this do' with specific actions, but lacks an explicit 'Use when...' clause. The 'when' is only implied by the action descriptions. Per rubric guidelines, a missing 'Use when...' clause caps completeness at 2. | 2 / 3 |
Trigger Term Quality | Includes good terms like 'Outlook Calendar', 'events', 'attendees', 'meeting times', 'invitations', but misses common user variations like 'schedule a meeting', 'book a room', 'calendar invite', '.ics', or 'reschedule'. The technical terms 'Rube MCP' and 'Composio' are not user-facing trigger terms. | 2 / 3 |
Distinctiveness Conflict Risk | Highly distinctive due to the specific combination of 'Outlook Calendar', 'Rube MCP (Composio)', and calendar-specific actions. Unlikely to conflict with other skills given the narrow, well-defined niche. | 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 reference skill covering Outlook Calendar automation with clear workflow sequences, good pitfall documentation, and a useful quick reference table. Its main weaknesses are moderate verbosity with repeated pitfall information across sections, lack of fully executable tool call examples (parameters are listed but not shown in complete invocation format), and all content being in a single file when some sections could be extracted for better progressive disclosure.
Suggestions
Deduplicate pitfalls: consolidate repeated warnings (e.g., attendee replacement, datetime formats) into the 'Known Pitfalls' section only, and reference it from individual workflows instead of restating.
Add at least one fully executable tool call example with complete parameter JSON for a core workflow like event creation, so Claude can see the exact invocation format.
Extract the 'Common Patterns' and 'Known Pitfalls' sections into separate reference files (e.g., PATTERNS.md, PITFALLS.md) and link from the main skill to improve progressive disclosure.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is fairly comprehensive but includes some redundancy—pitfalls are repeated across sections and in the 'Known Pitfalls' summary section. Some parameter descriptions are things Claude would know (e.g., explaining ISO 8601 format). The content could be tightened by ~30% without losing information. | 2 / 3 |
Actionability | Tool sequences are clearly named and parameters are well-documented, but the code examples are pseudocode/numbered lists rather than executable tool invocations with actual parameter JSON. The OData filter examples are concrete and useful, but the workflow steps lack copy-paste-ready tool call examples with full parameter structures. | 2 / 3 |
Workflow Clarity | Multi-step workflows are clearly sequenced with labeled steps (Optional/Required/Prerequisite/Alternative), include validation checkpoints (verify connection is ACTIVE before proceeding, resolve event ID before update/delete), and pitfalls sections serve as error-recovery guidance. The setup flow includes an explicit gate (confirm ACTIVE status). | 3 / 3 |
Progressive Disclosure | The content is a single monolithic file with no bundle files or references to supplementary documents. At ~200+ lines covering 5 workflows plus common patterns, known pitfalls, and a quick reference table, some content (e.g., OData filter syntax, known pitfalls) could be split into separate reference files. The quick reference table at the end is a good navigational aid, but the overall structure would benefit from splitting. | 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.