CtrlK
BlogDocsLog inGet started
Tessl Logo

notion-meeting-intelligence

Prepare meeting materials with Notion context and Codex research; use when gathering context, drafting agendas/pre-reads, and tailoring materials to attendees.

91

1.29x
Quality

81%

Does it follow best practices?

Impact

97%

1.29x

Average score across 7 eval scenarios

SecuritybySnyk

Advisory

Suggest reviewing before use

SKILL.md
Quality
Evals
Security

Quality

Content

62%

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

The body is well-structured with concrete tool calls and a clear workflow including an MCP error-recovery checkpoint, but two issues hold it back: the Quick start and Workflow sections duplicate the same phases, and the templates/examples it points to are not bundled. Addressing the missing reference files would most improve actionability and progressive disclosure.

Suggestions

Bundle the referenced files (reference/template-selection-guide.md and the template files, plus the examples/ files) so the template-selection and agenda-building steps are actually actionable, or remove the dangling references and inline the essential template guidance.

Merge the Quick start and Workflow sections into a single sequenced procedure to remove the duplicated five-phase rendering and tighten token usage.

Either reference the bundled assets/notion-small.svg and notion.png from the body or remove them, so the bundle contents and the body's references stay consistent.

DimensionReasoningScore

Conciseness

The body is lean and avoids explaining concepts Claude already knows, but the 'Quick start' and 'Workflow' sections render the same five phases twice with overlapping detail; not a 3 because that duplication could be tightened, not a 1 because there is no padding or concept exposition.

2 / 3

Actionability

Concrete tool calls ('Notion:notion-search', 'Notion:notion-create-pages') and copy-paste setup commands ('codex mcp add notion --url ...') are present, but the template-dependent steps reference files like 'reference/template-selection-guide.md' that do not exist in the bundle; not a 3 because those key details are missing/non-functional, not a 1 because substantial executable guidance is still provided.

2 / 3

Workflow Clarity

Steps 0-5 are clearly sequenced, and Step 0 provides an explicit error-recovery feedback loop ('If any MCP call fails because Notion MCP is not connected, pause and set it up') with concrete remediation; not a 2 because a real validation/recovery checkpoint is present.

3 / 3

Progressive Disclosure

References are clearly signaled and one level deep in a 'References and examples' section, but the referenced template and example files are not present in the bundle (only two unreferenced asset images exist); not a 3 because the disclosure structure is not actually realized, not a 1 because the body itself is well-organized rather than a monolithic wall of text.

2 / 3

Total

9

/

12

Passed

Description

100%

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, specific, and complete: it names concrete actions, includes an explicit 'use when' trigger clause with natural terms, and occupies a clear niche. It is a strong description with no notable weaknesses.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'gathering context, drafting agendas/pre-reads, and tailoring materials to attendees' — matching the 'lists multiple specific concrete actions' anchor; not a 2 because the actions are comprehensive rather than partial.

3 / 3

Completeness

Explicitly states what it does ('Prepare meeting materials with Notion context and Codex research') and when to use it ('use when gathering context, drafting agendas/pre-reads...'); not a 2 because the 'when' is an explicit trigger clause, not merely implied.

3 / 3

Trigger Term Quality

Natural meeting-prep terms appear in the trigger clause ('drafting agendas/pre-reads', 'tailoring materials to attendees') that users would say; not a 2 because coverage spans several common phrasings rather than a single keyword.

3 / 3

Distinctiveness Conflict Risk

Clear niche (meeting prep via Notion + Codex) with distinct triggers unlikely to fire for unrelated skills; not a 2 because the meeting/agenda/pre-read framing is specific rather than broadly overlapping.

3 / 3

Total

12

/

12

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.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

Total

15

/

16

Passed

Repository
openai/skills
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.