CtrlK
BlogDocsLog inGet started
Tessl Logo

cal-com-automation

Automate Cal.com tasks via Rube MCP (Composio): manage bookings, check availability, configure webhooks, and handle teams. Always search tools first for current schemas.

52

Quality

57%

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/skills/cal-com-automation/SKILL.md

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

SKILL.md
Quality
Evals
Security

Quality

Content

56%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This skill provides a solid structural overview of Cal.com automation via Rube MCP with clear tool sequences and useful parameter documentation. Its main weaknesses are redundancy (pitfalls repeated in multiple places), lack of concrete executable examples showing actual MCP tool call syntax, and a monolithic structure that could benefit from splitting detailed reference material into separate files. The workflow clarity is good but could be improved with explicit error handling steps.

Suggestions

Consolidate the per-workflow 'Pitfalls' sections into the single 'Known Pitfalls' section to eliminate redundancy and reduce token count by ~30%.

Add at least one concrete, executable MCP tool call example showing the actual invocation syntax (e.g., a complete RUBE_SEARCH_TOOLS call followed by a CAL_FETCH_ALL_BOOKINGS call with real parameters).

Move the Quick Reference table and detailed parameter lists into a separate REFERENCE.md file, keeping only the most essential parameters inline.

Add explicit error handling steps to workflows — e.g., 'If booking creation returns an error, check that the slot is still available and retry' — especially for the booking creation flow.

DimensionReasoningScore

Conciseness

The skill is moderately verbose. There's significant repetition between sections (pitfalls are repeated across individual workflows and the 'Known Pitfalls' section), and some information Claude would already know (e.g., explaining what ISO 8601 is, what IANA timezone strings are). The quick reference table duplicates information already covered in each workflow section. However, the parameter listings and tool sequences add genuine value.

3 / 5

Actionability

The skill provides tool names and parameter lists, which is useful, but the 'Common Patterns' section uses pseudocode-style numbered lists rather than actual executable examples showing MCP tool calls with concrete parameters. The guidance is specific enough to follow but lacks copy-paste ready examples with actual tool invocation syntax. The instruction to 'always call RUBE_SEARCH_TOOLS first' is good but the skill never shows what that call looks like.

3 / 5

Workflow Clarity

Workflows are clearly sequenced with labeled steps and tool ordering. The Booking Creation Flow includes a validation-like pattern (check availability before booking). However, there are no explicit error handling or feedback loops for failures — e.g., what happens if booking creation fails, or if a webhook doesn't fire on the test. The setup section has a good validation checkpoint (confirm ACTIVE status before proceeding).

4 / 5

Progressive Disclosure

The content is entirely monolithic with no bundle files or references to external documents. At ~180 lines with detailed parameter lists, pitfalls sections, and a reference table, some of this content (like the full parameter documentation or the quick reference table) could be split into separate files. The structure within the single file is reasonable with clear headers, but the lack of any content splitting is a missed opportunity.

3 / 5

Total

13

/

20

Passed

Description

58%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 does a reasonable job listing specific Cal.com capabilities and naming the integration platform (Rube MCP/Composio), making it fairly distinctive. However, it lacks an explicit 'Use when...' clause and misses common natural language trigger terms users would say like 'schedule', 'calendar', or 'appointment'. Adding these would significantly improve skill selection accuracy.

Suggestions

Add an explicit 'Use when...' clause, e.g., 'Use when the user asks about Cal.com scheduling, booking meetings, checking calendar availability, or managing Cal.com webhooks and teams.'

Include natural language synonyms and trigger terms users would say, such as 'schedule', 'calendar', 'appointments', 'book a call', 'meeting availability'.

DimensionReasoningScore

Specificity

Lists several specific actions: manage bookings, check availability, configure webhooks, handle teams. These are concrete capabilities, though 'manage bookings' and 'handle teams' are somewhat broad. Also includes a procedural note about searching tools first.

4 / 5

Completeness

The 'what' is clearly stated (automate Cal.com tasks with specific capabilities listed), but there is no explicit 'when' clause. The description lacks a 'Use when...' trigger guidance, which caps this dimension at 3 per the rubric.

3 / 5

Trigger Term Quality

Includes relevant keywords like 'Cal.com', 'bookings', 'availability', 'webhooks', 'teams', and 'Composio'. However, it misses natural user phrases like 'schedule a meeting', 'calendar', 'appointments', 'scheduling', or 'book a call' that users would commonly say.

3 / 5

Distinctiveness Conflict Risk

Specifying 'Cal.com' and 'Rube MCP (Composio)' makes this fairly distinct from generic calendar or scheduling skills. Minor overlap risk with other calendar/scheduling tools, but the platform-specific naming reduces conflict significantly.

4 / 5

Total

14

/

20

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.

Validation10 / 11 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

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

Warning

Total

10

/

11

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.