CtrlK
BlogDocsLog inGet started
Tessl Logo

notion-knowledge-capture

Capture conversations and decisions into structured Notion pages; use when turning chats/notes into wiki entries, how-tos, decisions, or FAQs with proper linking.

68

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

80%Weight 40%Scale 1-3

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

Concise and highly actionable with strong tool-call guardrails, but the workflow lacks an explicit content-validation feedback loop after create/update operations and the progressive-disclosure references point to bundle files that are not present.

Suggestions

Add an explicit validation step after page create/update (e.g., re-fetch the page to confirm properties/content applied correctly) with a fix-and-retry loop, to satisfy the feedback-loop expectation for database/write operations.

Create the referenced 'reference/' and 'examples/' bundle files (team-wiki-database.md, how-to-guide.md, etc.) or remove the dangling references so progressive disclosure points to real content.

Either reference the existing assets (notion.png/notion-small.svg) where useful or clarify that they are optional, since the only present bundle files are currently unreferenced.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence, with no padding or explanations of concepts Claude already knows; every section earns its place.

3 / 3

Actionability

It gives concrete tool names and exact parameter guidance (e.g., 'Notion:notion-update-page' with 'command: "update_content"', 'properties: {}', 'old_str'/'new_str', and 'filters: {}'), making the instruction-only guidance fully actionable.

3 / 3

Workflow Clarity

Steps 0-5 are clearly sequenced with a tool-availability guardrail, but the Notion page create/update flow lacks an explicit validate-then-fix-then-retry content-verification loop; for database/write operations the scoring notes cap workflow_clarity at 2 when such feedback loops are missing.

2 / 3

Progressive Disclosure

The body signals one-level-deep references to 'reference/' and 'examples/' with named files, but those directories are absent from the bundle (only assets/ exists), so the references point to non-existent files rather than a real split of content.

2 / 3

Total

10

/

12

Passed

Description

90%Weight 40%Scale 1-3

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A well-constructed description with explicit trigger guidance and natural user vocabulary, written in proper third person. It is distinguishable and complete; the only mild gap is action breadth, which keeps specificity at 2 rather than 3.

DimensionReasoningScore

Specificity

Quotes concrete actions like 'Capture conversations and decisions into structured Notion pages' and names the target domain, but the action list is not as comprehensive as the score-3 multi-action example; it stops short of enumerating the full range of capture operations.

2 / 3

Completeness

It states what the skill does ('Capture conversations and decisions into structured Notion pages') and provides an explicit 'use when' trigger clause, satisfying both what and when.

3 / 3

Trigger Term Quality

Natural user-facing terms appear ('chats/notes', 'wiki entries', 'how-tos', 'decisions', 'FAQs') giving good coverage of phrasings a user would actually say, matching the score-3 anchor.

3 / 3

Distinctiveness Conflict Risk

It is niched to Notion knowledge capture with distinct triggers (wiki entries, how-tos, decisions, FAQs), making it unlikely to fire for the wrong skill.

3 / 3

Total

11

/

12

Passed

Validation

87%

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

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

referenced_paths_exist

Referenced path issues: 1 missing

Warning

Total

14

/

16

Passed

Repository
openai/plugins
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.