CtrlK
BlogDocsLog inGet started
Tessl Logo

outlook-automation

Automate Outlook tasks via Rube MCP (Composio): emails, calendar, contacts, folders, attachments. Always search tools first for current schemas.

59

Quality

69%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills-claude/skills/outlook-automation/SKILL.md

The canonical home for this skill is outlook-automation in administrakt0r/AI-Agents-Safe-Coding-Skills

SKILL.md
Quality
Evals
Security

Quality

Content

68%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 body is a well-structured, mostly lean reference with concrete parameters and clear per-workflow tool sequences. Its chief gap is missing verification/feedback loops for create operations, which caps workflow clarity.

Suggestions

Add validation/verification steps after write operations (e.g. after CREATE_CONTACT, fetch or list the contact to confirm it was created).

Remove or replace the boilerplate 'When to Use' line with a concrete trigger summary tied to user intents.

Consider moving the KQL/OData syntax reference and full pitfalls into a separate reference file to sharpen the main overview.

DimensionReasoningScore

Conciseness

The body is lean reference material — tool sequences, key parameters, and pitfalls that mostly earn their tokens — with only minor redundancy such as the Quick Reference table restating tool slugs and the filler 'When to Use' line; mostly efficient with minor instances of over-explanation that could be trimmed.

4 / 5

Actionability

Concrete tool names, real parameter examples (KQL `from:user@example.com`, OData `isRead eq false and importance eq 'high'`), and a task→tool→params table give executable guidance for an MCP-tool skill; it stops short of full copy-paste tool-call payloads, so not a 5.

4 / 5

Workflow Clarity

Each workflow has a numbered, tagged ([Required]/[Optional]/[Prerequisite]) tool sequence and setup includes a status check, but write operations (CREATE_CONTACT, CREATE_MAIL_FOLDER, CREATE_CONTACT_FOLDER) lack verification feedback loops, so workflow clarity is capped at 3 per the destructive/write-operations rule.

3 / 5

Progressive Disclosure

Content is well organized into clearly headed sections with a Quick Reference summary and no nested references; it is self-contained (no bundle files exist) and appropriately placed, with only minor room to split the KQL/OData syntax reference into its own file.

4 / 5

Total

15

/

20

Passed

Description

70%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 and distinct, naming a clear Outlook-via-Composio niche with good natural trigger terms. Its main weakness is the absence of an explicit 'Use when...' trigger clause, which caps completeness.

Suggestions

Add an explicit 'when' clause, e.g. 'Use when the user wants to automate Outlook emails, calendar, contacts, or folders via Composio/Rube MCP.'

Convert the capability list from nouns to discrete actions (e.g. 'search and send emails, schedule events, manage contacts') to lift specificity.

Include common synonyms users say ('mail', 'meetings', 'appointments') to round out trigger-term coverage.

DimensionReasoningScore

Specificity

Lists several concrete Outlook capability areas — "emails, calendar, contacts, folders, attachments" — alongside the action "Automate Outlook tasks"; gaps remain because the areas are nouns rather than discrete actions and tooling caveats are not surfaced.

4 / 5

Completeness

The 'what' is clearly stated ("Automate Outlook tasks via Rube MCP (Composio): emails, calendar, contacts, folders, attachments") but there is no 'Use when...' trigger clause — "Always search tools first for current schemas" is an instruction, not a when, so completeness is capped at 3.

3 / 5

Trigger Term Quality

Natural user-facing terms ("Outlook", "emails", "calendar", "contacts", "folders", "attachments") are present with good coverage; a few common synonyms ("mail", "meetings", "appointments") are missing, keeping it below a 5.

4 / 5

Distinctiveness Conflict Risk

The niche is sharply defined by "Outlook" plus the specific integration "Rube MCP (Composio)", giving clear, distinct triggers with minimal risk of firing for an unrelated skill.

5 / 5

Total

16

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
administrakt0r/AI-Agents-Safe-Coding-Skills
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.