Automate Notion tasks via Rube MCP (Composio): pages, databases, blocks, comments, users. Always search tools first for current schemas.
67
51%
Does it follow best practices?
Impact
98%
2.08xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/all-skills/skills/notion-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 (Notion automation via Rube MCP) and lists the entity types it works with, giving it good distinctiveness. However, it lacks specific concrete actions beyond 'automate tasks,' and critically missing an explicit 'Use when...' clause that would help Claude know when to select this skill. The operational instruction about searching tools first is useful but doesn't compensate for the missing trigger guidance.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user asks to create, update, or query Notion pages, databases, or blocks, or mentions Notion workspace management.'
Replace the vague 'automate Notion tasks' with specific actions like 'Create and update Notion pages, query databases, manage blocks, post comments, and look up users.'
Include natural trigger terms users would say, such as 'Notion workspace', 'create a page', 'query a database', 'add a comment in Notion'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | It names the domain (Notion) and lists entity types (pages, databases, blocks, comments, users) but doesn't describe specific concrete actions beyond 'automate tasks' and 'search tools.' It lacks detail on what actions are performed (e.g., create pages, query databases, add comments). | 2 / 3 |
Completeness | It partially answers 'what' (automate Notion tasks) but there is no explicit 'Use when...' clause or equivalent trigger guidance. The instruction to 'always search tools first' is operational guidance for Claude, not a trigger condition. Missing 'when' caps this at 2, but the 'what' is also quite vague, bringing it to 1. | 1 / 3 |
Trigger Term Quality | Includes 'Notion', 'pages', 'databases', 'blocks', 'comments', 'users' which are relevant keywords. However, it includes technical jargon like 'Rube MCP (Composio)' that users wouldn't naturally say, and misses common user phrases like 'create a page', 'update database', or 'add a comment in Notion'. | 2 / 3 |
Distinctiveness Conflict Risk | The description is clearly scoped to Notion via a specific MCP integration (Rube/Composio), making it highly distinctive. It's unlikely to conflict with other skills unless there are multiple Notion-related skills. | 3 / 3 |
Total | 8 / 12 Passed |
Implementation
62%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a comprehensive Notion automation skill with strong workflow clarity and good structural organization within a single file. Its main weaknesses are moderate redundancy across sections (pitfalls and tool references repeated in multiple places) and the lack of progressive disclosure through supporting bundle files, which would reduce token consumption. The actionability could be improved with more concrete, executable MCP call examples rather than pseudocode-style tool sequences.
Suggestions
Extract the Quick Reference table and Common Patterns section into separate bundle files (e.g., REFERENCE.md, PATTERNS.md) to reduce the main skill's token footprint and improve progressive disclosure.
Deduplicate pitfalls — consolidate pagination warnings, archive behavior notes, and property name case-sensitivity into the 'Known Pitfalls' section only, removing them from individual workflow sections.
Add at least one fully executable MCP call example (with actual tool invocation syntax and realistic parameters) for a core workflow like creating a page or querying a database, rather than relying on pseudocode-style numbered lists.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is fairly well-organized but is quite long (~180 lines) with some redundancy. Pitfalls are repeated across sections (e.g., pagination warnings appear in multiple workflows and again in Common Patterns). The quick reference table at the end largely duplicates information already presented in the workflow sections. However, it avoids explaining basic concepts Claude already knows. | 2 / 3 |
Actionability | The skill provides concrete tool names, parameter names, and filter syntax examples, which is good. However, the tool sequences are described as ordered lists rather than executable code/commands, and the 'Common Patterns' section uses pseudocode-style descriptions rather than actual MCP call examples with real parameters. The filter syntax JSON examples are a strong point but are the exception rather than the rule. | 2 / 3 |
Workflow Clarity | Multi-step workflows are clearly sequenced with labeled steps, prerequisite/optional annotations, and explicit validation checkpoints (e.g., verify connection is ACTIVE before proceeding, check has_more for pagination, inspect schema before inserts). The setup section includes a clear 4-step verification flow. Pitfalls sections serve as error recovery guidance for each workflow. | 3 / 3 |
Progressive Disclosure | The content is well-structured with clear sections and headers, but it's a monolithic document with no references to supporting files. The detailed pitfalls, common patterns, and quick reference table could be split into separate files. For a skill of this length and complexity, having everything inline makes it harder to navigate and consumes more tokens than necessary. The external link to composio.dev/toolkits/notion is a good touch but doesn't compensate for the lack of bundle file organization. | 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 | |
74c7031
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.