recipe-create-task-list
Set up a new Google Tasks list with initial tasks.
67
60%
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/recipe-create-task-list/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 brief and identifies the core domain (Google Tasks) and a basic action (setting up a new list with tasks), but lacks depth in specificity, trigger terms, and completeness. The absence of a 'Use when...' clause and limited keyword coverage make it harder for Claude to reliably select this skill from a large pool.
Suggestions
Add a 'Use when...' clause with explicit triggers, e.g., 'Use when the user wants to create a new Google Tasks list, set up a to-do list in Google Tasks, or initialize tasks for a new project.'
Include natural trigger term variations such as 'to-do list', 'Google task list', 'create tasks', 'new task list', and 'task setup'.
Expand the capability description with more specific actions, e.g., 'Creates a new Google Tasks list, populates it with initial tasks including titles, due dates, and notes.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Google Tasks) and two actions (set up a new list, add initial tasks), but doesn't elaborate on specific capabilities like setting due dates, organizing subtasks, or configuring task properties. | 2 / 3 |
Completeness | Describes what it does (set up a Google Tasks list with initial tasks) but has no 'Use when...' clause or equivalent explicit trigger guidance, which per the rubric caps completeness at 2, and the 'what' is also fairly thin, bringing this to a 1. | 1 / 3 |
Trigger Term Quality | Includes 'Google Tasks' and 'tasks list' which are relevant keywords, but misses common variations like 'to-do list', 'task manager', 'Google task list', or 'create tasks'. | 2 / 3 |
Distinctiveness Conflict Risk | Specifying 'Google Tasks' provides some distinctiveness from generic task or to-do skills, but could overlap with other Google Tasks skills (e.g., editing tasks, managing existing lists) since the scope isn't sharply delineated. | 2 / 3 |
Total | 7 / 12 Passed |
Implementation
87%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a concise, actionable recipe-style skill that provides executable commands for creating a Google Tasks list with initial tasks. Its main weakness is the lack of explicit guidance on capturing the TASKLIST_ID from step 1's response and no validation that operations succeeded, which is a gap in workflow clarity for a multi-step process.
Suggestions
Add an explicit note after step 1 to capture the TASKLIST_ID from the response, e.g., 'Extract the `id` field from the response to use as TASKLIST_ID in subsequent steps.'
Add a brief validation checkpoint, such as verifying the task list was created before adding tasks, or noting expected output format from step 1.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Very lean and efficient. No unnecessary explanations of what Google Tasks is or how APIs work. Every line serves a purpose with concrete commands. | 3 / 3 |
Actionability | Fully concrete, copy-paste ready commands with specific JSON payloads and parameters. Each step is an executable CLI command with realistic example data. | 3 / 3 |
Workflow Clarity | Steps are clearly sequenced and logical, but there's no validation or error handling. The TASKLIST_ID placeholder is used in steps 2-4 without explicitly stating to capture it from step 1's output, which could cause confusion. No feedback loop for verifying task creation succeeded. | 2 / 3 |
Progressive Disclosure | For this simple, single-purpose skill under 50 lines, the structure is appropriate. It has a clear prerequisite reference to the gws-tasks skill and well-organized sequential steps. No need for external file references. | 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 | |
- Repository
- googleworkspace/cli
- Commit
c7c6646
- 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.