CtrlK
BlogDocsLog inGet started
Tessl Logo

orbit-notion

Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and renders the digest as a native Notion page (callout / toggle / database table primitives). This skill should not be triggered manually — it is invoked by Orbit's daily-digest scheduler against live Notion data.

55

Quality

62%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./design-templates/orbit-notion/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

57%

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

Highly actionable and concrete in its design tokens and mirroring rules, but it leans on an example.html that is not present in the bundle and lacks an explicit verification step for matching the canonical example.

Suggestions

Ship the referenced example.html in the skill bundle (e.g. under assets/ or the skill root) so the core reference actually resolves; without it the source-of-truth protocol is unactionable.

Add an explicit validation checkpoint (e.g. 'After rendering, diff your DOM hierarchy, section order, and class names against example.html; fix any drift before returning') to lift workflow clarity to 3.

Trim the duplicated canvas-token table and section walkthrough where they merely restate example.html, keeping SKILL.md as a concise overview that points to the example for the full design.

DimensionReasoningScore

Conciseness

The body is mostly efficient and well-structured, but the full token/color table plus a redundant 'Page sections' walkthrough duplicates much of what the canonical example.html already encodes, adding tokens that partly restate the example.

2 / 3

Actionability

It gives copy-paste-ready specifics — exact hex tokens, font stack, px sizes, DOM/class-name mirroring rules, and a paired do/don't table — leaving Claude with concrete, executable guidance.

3 / 3

Workflow Clarity

The numbered Step 1–3 source-of-truth protocol provides a clear sequence, but there is no validation/verification checkpoint confirming the rendered output actually matches example.html, which the rubric caps at 2 for output-generation tasks.

2 / 3

Progressive Disclosure

It repeatedly instructs reading and reproducing an example.html, but no example.html file ships in the skill bundle (references/, scripts/, assets/ are absent), so the central reference is missing and navigation cannot resolve.

1 / 3

Total

8

/

12

Passed

Description

67%

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 concrete, well-scoped description with strong specificity and distinctiveness, but it omits an explicit 'Use when...' trigger clause and leans on the frontmatter triggers list rather than natural-language phrasing inside the description.

Suggestions

Add an explicit 'Use when...' sentence to the description (e.g. 'Use when generating the daily Notion digest or when the user asks for a Notion briefing/digest') to lift completeness to 3.

Weave one or two natural trigger phrases ('Notion briefing', 'Notion digest') into the description body itself so trigger-term quality does not depend solely on the frontmatter triggers list.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'Pulls the past 24 hours of document edits, comments, mentions, and database row changes' and 'renders the digest as a native Notion page (callout / toggle / database table primitives)' — rather than vague language.

3 / 3

Completeness

It clearly states what the skill does, but 'when' guidance is contextual ('when Notion is the user's only connected connector...') rather than an explicit 'Use when...' clause, which the rubric caps at 2.

2 / 3

Trigger Term Quality

The description itself does not embed natural user phrasing; natural trigger terms ('notion briefing', 'notion digest', 'doc digest') live in the separate frontmatter triggers list, and a reader of the description alone sees only 'Notion' and 'daily digest'.

2 / 3

Distinctiveness Conflict Risk

The single-connector Notion scoping and explicit statement that it 'should not be triggered manually — it is invoked by Orbit's daily-digest scheduler' carve out a clear niche unlikely to collide with other skills.

3 / 3

Total

10

/

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

frontmatter_unknown_keys

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

Warning

Total

15

/

16

Passed

Repository
nexu-io/open-design
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.