todoist-automation
Automate Todoist task management, projects, sections, filtering, and bulk operations via Rube MCP (Composio). Always search tools first for current schemas.
67
52%
Does it follow best practices?
Impact
94%
1.56xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/all-skills/skills/todoist-automation/SKILL.mdQuality
Discovery
40%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 identifies a clear niche (Todoist via Rube MCP/Composio) which makes it distinctive, but it lacks an explicit 'Use when...' clause and could be more specific about the concrete actions it performs. The trigger terms are adequate but miss common user language variations for task management.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user asks about Todoist tasks, to-do lists, task organization, or managing projects and deadlines in Todoist.'
List more specific concrete actions such as 'create tasks, update due dates, assign labels, move tasks between projects, complete tasks in bulk' instead of broad categories.
Include natural user language variations like 'to-do list', 'tasks', 'due dates', 'reminders', 'labels', and 'priorities' to improve trigger term coverage.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Todoist task management) and lists several actions (projects, sections, filtering, bulk operations), but these are more like categories than concrete specific actions. It doesn't detail what specific operations are performed (e.g., 'create tasks', 'move tasks between projects', 'set due dates'). | 2 / 3 |
Completeness | Describes what it does (automate Todoist task management) but has no explicit 'Use when...' clause or equivalent trigger guidance. The rubric states a missing 'Use when...' clause should cap completeness at 2, and since the 'when' is entirely absent, this scores a 1. | 1 / 3 |
Trigger Term Quality | Includes relevant keywords like 'Todoist', 'task management', 'projects', 'sections', 'filtering', and 'bulk operations', which are natural terms. However, it misses common variations users might say like 'to-do list', 'tasks', 'due dates', 'reminders', 'labels', or 'priorities'. | 2 / 3 |
Distinctiveness Conflict Risk | The description is clearly scoped to Todoist specifically via Rube MCP (Composio), which creates a very distinct niche. It's unlikely to conflict with other skills given the specific tool and integration mentioned. | 3 / 3 |
Total | 8 / 12 Passed |
Implementation
64%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a thorough and highly actionable Todoist automation skill with excellent parameter documentation and practical pitfall warnings. Its main weaknesses are redundancy (pitfalls repeated across sections and in a consolidated section), lack of validation/verification steps in workflows involving destructive operations, and a monolithic structure that could benefit from splitting reference material into separate files.
Suggestions
Consolidate pitfalls into the 'Known Pitfalls' section only, removing duplicates from individual workflow sections (or vice versa) to reduce redundancy and token usage.
Add explicit validation steps to workflows — e.g., after BULK_CREATE_TASKS, verify with GET_ALL_TASKS; after DELETE operations, confirm the entity is gone.
Consider splitting the detailed parameter references and quick reference table into a separate REFERENCE.md file, keeping SKILL.md as a concise overview with workflow sequences.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is quite long (~200+ lines) with some redundancy — pitfalls are repeated across sections (priority inversion mentioned 3 times, ID format issues mentioned multiple times, due date rules repeated). The 'Known Pitfalls' section largely duplicates pitfalls already listed in individual workflows. However, most content is genuinely useful and not explaining things Claude already knows. | 2 / 3 |
Actionability | Provides specific tool names, exact parameter names and formats, concrete filter syntax examples, and precise API conventions. The key parameters sections with exact field names, formats (RFC3339, YYYY-MM-DD), and value ranges (priority 1-4) make this highly actionable and copy-paste ready for MCP tool invocations. | 3 / 3 |
Workflow Clarity | Workflows are clearly sequenced with labeled steps and tagged as [Required]/[Optional]/[Prerequisite]. However, there are no explicit validation checkpoints or feedback loops — for example, after bulk task creation there's no 'verify tasks were created' step, and after delete operations there's no confirmation step. For destructive operations like DELETE_TASK and DELETE_SECTION, this is a notable gap. | 2 / 3 |
Progressive Disclosure | The content is well-structured with clear sections and a useful quick reference table, but it's monolithic — all content is in one file with no references to separate detailed docs. The repeated pitfalls sections and the comprehensive parameter listings could be split into reference files. The single external link (Composio toolkit docs) is helpful but the skill itself could benefit from splitting. | 2 / 3 |
Total | 9 / 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 |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- davepoon/buildwithclaude
- Commit
7cc63f3
- 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.