CtrlK
BlogDocsLog inGet started
Tessl Logo

notion-automation

Automate Notion tasks via Rube MCP (Composio): pages, databases, blocks, comments, users. Always search tools first for current schemas.

77

2.08x
Quality

72%

Does it follow best practices?

Impact

98%

2.08x

Average score across 3 eval scenarios

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./plugins/all-skills/skills/notion-automation/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

67%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is a strong, actionable reference: every workflow names exact tools, parameters, and failure modes with concrete JSON examples and pagination handling, and it assumes Claude's competence rather than teaching Notion basics. Its main weaknesses are redundancy between the workflows, the Known Pitfalls section, and the Quick Reference table, plus missing example payloads for block and comment content.

Suggestions

Consolidate the duplicated pitfalls: keep the per-workflow Pitfalls lists and cut the overlapping "Known Pitfalls" entries (case-sensitive property names, read-only formula/rollup fields, pagination) that already appear above, or vice versa.

Add a short example payload for `content_blocks` (one heading + one paragraph block object) and for `rich_text` in comments, since those are the two parameters whose structure is not inferable from the skill.

Drop the redundant Quick Reference rows that restate tools and parameters already covered in the workflows, or replace the table with only the tools not mentioned in any workflow section (e.g. NOTION_DUPLICATE_PAGE).

DimensionReasoningScore

Conciseness

The body is dense and assumes Claude already knows Notion API concepts, but it is noticeably duplicated: the Quick Reference table restates tool slugs and parameters already given in the five workflows, and the "Known Pitfalls" section repeats pitfalls stated earlier (case-sensitive property names, read-only formula fields, pagination). It could be tightened to a 4 by consolidating these.

3 / 5

Actionability

Guidance is concrete and executable for an MCP-driven skill: exact tool names in sequenced order, exact parameter names with the critical gotcha ("Use `content_blocks` parameter, NOT `child_blocks`"), copy-ready JSON filter syntax, and pagination mechanics. Minor gaps keep it from a 5 — no example payload for `content_blocks` block objects or the `rich_text` array.

4 / 5

Workflow Clarity

Each workflow has a numbered tool sequence with [Prerequisite] markers, the setup includes explicit verification ("Confirm connection status shows ACTIVE before running any workflows"), and pitfalls provide error-recovery feedback (404 → wrong database_id, 400 → schema mismatch, unarchive via UPDATE_PAGE). It is not a 5 because destructive operations (ARCHIVE_NOTION_PAGE, DELETE_BLOCK, REPLACE_PAGE_CONTENT) lack an explicit verify-before-acting checkpoint, though their reversibility is clearly flagged.

4 / 5

Progressive Disclosure

The skill is a single well-organized file with clear section headers, per-task subsections, and a clearly signaled external docs link — no nested or buried references. It is not a 5 because the ~220-line body carries reference material (the 21-row Quick Reference table) that overlaps the workflow sections and could be consolidated or split, and the skill exceeds the under-50-line simple-skill threshold.

4 / 5

Total

15

/

20

Passed

Description

65%Weight 40%Scale 1-5

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 clearly identifies a distinct Notion-automation niche with good natural keywords, but it is missing any explicit "when to use" trigger clause and uses only a generic action verb ("Automate") instead of naming the concrete operations it supports. These two gaps hold it to a mid-range score despite strong distinctiveness.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user wants to create, search, update, or archive Notion pages, query or edit Notion databases, or manage comments."

Replace the generic verb "Automate Notion tasks" with concrete actions such as "Create and update pages, query and insert database rows, append and replace page blocks, and add comments".

Trim the operational instruction "Always search tools first for current schemas" from the description — it belongs in the body's workflow steps, not the trigger text.

DimensionReasoningScore

Specificity

Names the domain ("Automate Notion tasks") and enumerates five concrete object areas ("pages, databases, blocks, comments, users"), but the only action verb is the generic "Automate" — no specific actions like create, query, or update are stated, so it falls between the domain-only (2) and several-specific-actions (4) anchors.

3 / 5

Completeness

The "what" is clear (automating Notion pages, databases, blocks, comments, users via Rube MCP), but there is no "Use when…" clause or any explicit trigger guidance, which caps completeness at 3 per the rubric guidelines; the second sentence ("Always search tools first") is operational instruction, not a when-to-use trigger.

3 / 5

Trigger Term Quality

"Notion", "pages", "databases", "blocks", "comments", "users" are natural terms users would say when needing this skill, giving good keyword coverage; a few natural phrasings (e.g. "search Notion", "update a Notion page") are missing, so it is not the comprehensive synonym coverage of a 5.

4 / 5

Distinctiveness Conflict Risk

"Notion" combined with "Rube MCP (Composio)" carves out a clear niche with distinct triggers and minimal conflict risk — it would only compete with other Notion-specific skills, and none of the terms are generic.

5 / 5

Total

15

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
davepoon/buildwithclaude
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.