Create, update, and organize Google Calendar events and schedules. Check availability, book time, and manage calendars. Use when asked to schedule a meeting, set up an appointment, book a call, check gcal, or manage calendar events.
Install with Tessl CLI
npx tessl i github:odyssey4me/agent-skills --skill google-calendar95
Does it follow best practices?
Evaluation — 97%
↑ 2.48xAgent success when using this skill
Validation for skill structure
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is an excellent skill description that follows best practices. It uses third person voice, lists specific concrete actions, includes a comprehensive 'Use when...' clause with natural trigger terms users would actually say, and clearly distinguishes itself as a Google Calendar-specific skill.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Create, update, and organize Google Calendar events and schedules. Check availability, book time, and manage calendars.' These are clear, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers both what (create, update, organize events, check availability, book time, manage calendars) AND when with explicit 'Use when...' clause listing specific trigger scenarios. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'schedule a meeting', 'set up an appointment', 'book a call', 'check gcal', 'manage calendar events'. Includes both formal and informal variations (gcal). | 3 / 3 |
Distinctiveness Conflict Risk | Clear niche focused specifically on Google Calendar with distinct triggers like 'gcal', 'calendar events', 'book a call'. Unlikely to conflict with other skills due to specific platform and action focus. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
85%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 skill with excellent actionability and clear workflow guidance. The progressive disclosure is appropriate with external references for detailed setup. Minor verbosity in some sections (Model Guidance, some explanatory text) prevents a perfect conciseness score, but overall the skill is effective and well-organized.
Suggestions
Remove the 'Model Guidance' section as Claude doesn't need to be told what model to use for itself
Condense the 'Setup Verification' section - the bullet list of what it checks is unnecessary detail that Claude can infer
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Generally efficient but includes some unnecessary sections like 'Model Guidance' which Claude doesn't need, and the setup verification section could be more compact. The dependency installation and authentication sections are reasonably concise. | 2 / 3 |
Actionability | Provides fully executable bash commands with concrete examples including real arguments, time formats, and attendee syntax. Commands are copy-paste ready with clear parameter patterns. | 3 / 3 |
Workflow Clarity | Clear setup sequence (install → configure → verify), explicit error handling guidance distinguishing retryable vs non-retryable errors, and specific instructions on when to stop and inform the user vs retry. | 3 / 3 |
Progressive Disclosure | Well-structured with quick start in main file, detailed command reference linked separately, and OAuth/GCP setup guides appropriately externalized. References are one level deep and clearly signaled. | 3 / 3 |
Total | 11 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
Table of Contents
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.