CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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.

64

Quality

80%

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

65%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 content is a detailed, highly concrete Notion design spec with good internal organization, and the do/don't table is genuinely useful. Its main weaknesses are the absence of any validation checkpoint in the three-step protocol and the fact that the canonical example.html the whole workflow depends on is missing from the bundle, leaving the source-of-truth step unexecutable and the required page-link script unspecified.

Suggestions

Ship the referenced example.html (or move its spec fully inline) — the entire Step 1/Step 2 'mirror it 1:1' protocol is unexecutable without it, and include the page-link → notion.so injection <script> contents in the body since they are a required output block.

Add an explicit validation step to the protocol (e.g., 'Step 4: before finishing, verify your output has exactly the 11 sections in order, only the two required callouts, and no blocks not present in example.html').

Deduplicate the avatar, callout-bg, and tag-pill specs between the section descriptions and the do/don't table to trim tokens without losing information.

DimensionReasoningScore

Conciseness

The body is a dense, non-obvious design spec — exact hex tokens, px sizes, section order, real-shaped copy — with almost nothing Claude would already know. It loses a point to duplication: avatar styling ("18px circles with letter + Notion-style soft pastel bg") and callout bg (#F1F1EF) are each specified in both the section specs and the do/don't table, and the token list overlaps the per-section color specs. Not 3 because the padding is minor relative to the volume of load-bearing detail.

4 / 5

Actionability

Mostly executable: exact color hexes, type stack, px dimensions, ordered section list with literal copy strings, database columns ("Name | Status | Updated by | Updated"), and a paired do/don't table. Two gaps hold it below 5: the declared canonical source "shipped example.html" is not present in the skill folder, and the required trailing "<script> block at the end (page-link → notion.so injection)" is mandated by reference only, with its contents never provided.

4 / 5

Workflow Clarity

A clear three-step protocol exists (read example.html → mirror its structure 1:1 → refresh mock values without inventing blocks), with an identity guard for person names. But there is no validation checkpoint — no step instructing the model to compare its output against the example section-by-section or verify the do/don't constraints before finishing. The sequence is present while checkpoints are missing, matching anchor 3; not 4 because the sole verification mechanism is an unenforced imperative ("reproduce it, not reinterpret it").

3 / 5

Progressive Disclosure

The body itself is well organized into clearly headed sections (protocol, policy, tokens, section order, formatting rules, do/don't table). However, the entire skill hinges on one bundle file — example.html — which does not exist in the folder (no references/, scripts/, or assets/ directories, and no example.html anywhere in the skill directory), so the single reference is broken and the preview entry index.html from frontmatter is likewise absent. Well-structured content with a broken primary reference lands between anchors 2 and 4; not 4 because the load-bearing reference cannot be resolved.

3 / 5

Total

14

/

20

Passed

Description

88%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.

A strong description: concrete actions, explicit and specific trigger conditions, third-person voice, and a well-defined single-connector niche. The only gaps are a few missing natural synonyms and the slightly over-broad "doc digest" trigger term.

DimensionReasoningScore

Specificity

The description lists multiple concrete actions with comprehensive coverage for its niche: "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)". It stays in third person ("Pulls", "renders"), so no voice penalty applies.

5 / 5

Completeness

Both "what" and "when" are answered explicitly: what — pulls 24 hours of Notion edits/comments/mentions/database changes and renders them as a native Notion page; when — "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", plus "invoked by Orbit's daily-digest scheduler". The trigger conditions are concrete and specific, matching the 5 anchor rather than the softer 4 anchor.

5 / 5

Trigger Term Quality

Good natural keyword coverage within the description ("Notion", "briefing", "daily digest", "document edits", "comments", "mentions", "database row changes"), supplemented by an explicit bilingual frontmatter triggers list ("notion briefing", "notion digest", "doc digest", "notion 简报", "文档摘要"). Not 5 because a few natural synonyms a user might say (e.g. "summary", "recap") are absent; not 3 because the terms present are natural phrases users would actually say rather than jargon.

4 / 5

Distinctiveness Conflict Risk

A clear single-connector niche ("Notion is the user's only connected connector") with an explicit selection rule makes it mostly distinct from sibling connector-briefing skills. Minor overlap risk remains: the generic "doc digest" trigger could match non-Notion digest requests, keeping it below the 5 anchor's "minimal conflict risk".

4 / 5

Total

18

/

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

nexu-io/open-design

Path

design-templates/orbit-notion/SKILL.md

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.