Google Workflow: Today's meetings + open tasks as a standup summary.
66
58%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/gws-workflow-standup-report/SKILL.mdQuality
Discovery
32%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 concise but too terse—it reads more like a label than a skill description. It lacks an explicit 'Use when...' clause, misses important trigger term variations (e.g., 'Google Calendar', 'daily standup', 'morning briefing'), and doesn't enumerate the concrete actions the skill performs.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user asks for a daily standup, morning briefing, or wants a summary of today's calendar and tasks.'
Expand trigger terms to include natural variations like 'Google Calendar', 'Google Tasks', 'daily standup', 'morning update', 'status summary', 'what's on my schedule'.
List specific concrete actions such as 'Fetches today's Google Calendar events, retrieves open Google Tasks, and formats them into a standup-style summary.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Google Workflow) and describes the output (standup summary from today's meetings and open tasks), but doesn't list multiple concrete actions like fetching calendar events, querying task lists, or formatting the summary. | 2 / 3 |
Completeness | Describes what it does (generates a standup summary from meetings and tasks) but has no explicit 'Use when...' clause or trigger guidance, which per the rubric should cap completeness at 2, and the 'what' is also fairly thin, placing this at 1. | 1 / 3 |
Trigger Term Quality | Includes some natural keywords like 'meetings', 'tasks', 'standup summary', and 'Google', but misses common variations users might say such as 'daily standup', 'calendar', 'Google Calendar', 'Google Tasks', 'morning briefing', or 'status update'. | 2 / 3 |
Distinctiveness Conflict Risk | The combination of Google + standup summary is somewhat distinctive, but 'meetings' and 'tasks' are generic enough to potentially overlap with other calendar or task management skills. The lack of specificity about which Google services (Calendar, Tasks, etc.) increases conflict risk. | 2 / 3 |
Total | 7 / 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, concise skill for a simple read-only CLI command. It correctly delegates shared concerns (auth, global flags) to a referenced shared skill and keeps the content focused. The main weakness is the lack of example output, which would help Claude understand the expected format of the standup report.
Suggestions
Add an example of the expected output (e.g., a sample JSON or table showing meetings and tasks) so Claude knows what the standup report looks like.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Very lean and efficient. No unnecessary explanations of what a standup report is or how calendars/tasks work. Every section earns its place. | 3 / 3 |
Actionability | Provides concrete CLI commands and flag documentation, but lacks example output showing what the standup report actually looks like. There's no sample JSON/table output to set expectations for the result format. | 2 / 3 |
Workflow Clarity | This is a simple single-command, read-only skill with no multi-step process or destructive operations. The single action is unambiguous and the read-only nature is explicitly noted. | 3 / 3 |
Progressive Disclosure | Clear, well-organized sections with appropriate one-level-deep references to the shared skill and parent workflow skill. The prerequisite callout is well-signaled. | 3 / 3 |
Total | 11 / 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 |
|---|---|---|
metadata_field | 'metadata' should map string keys to string values | Warning |
Total | 10 / 11 Passed | |
a3768d0
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.