Agent skill · Audited from source

Start The Day

skill · vellum-ai/vellum-assistantMIT licenceAudited 14 Oct 2026 · source 19bc86343b63

★ 1,425pushed 1 day ago
✓SAFEGrade B · 89/100 · 14 Oct 2026 · 19bc863
1,425repo stars · whole vellum-ai/vellum-assistant

Is it safe? Yes — SAFE, grade B (89/100). We read this skill's source at commit 19bc86343b63 and found no filesystem, network or shell access and no hard-coded secrets. What it does: An on-demand personal daily briefing — weather, headlines, the shape of your day, and one thing worth your attention — in a sharp executive-assistant voice. The general-purpose morning brief; richer work or admin…

Ask an AI about this pageGChatGPTCClaudePPerplexityGeGeminiXGrok
More
Cite

Cite this page

ModelsAtlas. “Start The Day (vellum-ai/vellum-assistant)”. Retrieved 14 Oct 2026. https://modelsatlas.com/skills/vellum-ai/start-the-day

Trust audit

Audit 0.4.1 · source read 14 Oct 2026

Trust score89/100✓SAFE B
0 critical0 high0 medium5 low0 info

SAFE means nothing in the source contradicts what the skill says it does. Grade B is shared by 13,985 of 14,816 audited skills.

What the source does

  • FilesystemNone observedNo reads or writes in the source
  • NetworkNone observedNo outbound calls in the source
  • ShellNone observedNo commands run in the source
  • DependenciesPinnedNothing floats
  • SecretsNone foundNo keys in source

Five audit layers

LayerWhat we checkResultFindings
L0 ProvenanceRepo owner, licence, archive status, activityPASS5
L1 Static sourceSecrets, path traversal, supply chain, hidden codeNA0
L2 InstructionsPrompt injection, authority framing, hidden directivesPASS0
L3 InventoryThe files and declarations match the sourcePASS0
L4 SandboxRun in isolation and watch behaviourSKIPPED why0

Gates applied: no behavioural pass.

Findings (5)

Audit 0.4.1 · source sha 19bc86343b63 · 14 Oct 2026Report an issue or request a re-scan

Provenance

Who published it, and what the verdict is pinned to

  • Publishervellum-ai GitHub organizationOwner of the repository this skill is read from
  • Source foldervellum-ai/vellum-assistant/skills/start-the-dayThe exact folder we audited
  • LicenceMITAs the repository states it
  • Commit pinned for this verdict19bc86343b63A new audit runs when the source changes
  • Repository statusNot archivedLast push 1 day ago
  • Sandboxed runNot runSkills are read, not executed; layer L4 is skipped

What it tells the agent

Full source on GitHub ↗

Its description: An on-demand personal daily briefing — weather, headlines, the shape of your day, and one thing worth your attention — in a sharp executive-assistant voice. The general-purpose morning brief; richer work or admin…

---
name: start-the-day
description: "An on-demand personal daily briefing — weather, headlines, the shape of your day, and one thing worth your attention — in a sharp executive-assistant voice. The general-purpose morning brief; richer work or admin digests compose it as their general layer."
compatibility: "Designed for Vellum personal assistants"
metadata:
  icon: assets/icon.svg
  emoji: "🌅"
  vellum:
    category: "productivity"
    display-name: "Start the Day"
    user-invocable: true
    activation-hints:
      - "User asks to start their day, for a morning briefing, or a daily briefing/recap"
      - "User asks what's going on today or what they should know this morning"
      - "User wants weather, headlines, and a quick personal rundown"
    avoid-when:
      - "User wants a detailed work/admin digest — deep inbox triage, follow-up tracking, or meeting-by-meeting prep — rather than a general briefing"
      - "User wants to set up recurring or automated briefings rather than one right now"
---

You are a personal daily briefing assistant. When the user invokes this skill,
produce a concise, scannable briefing tailored to the current moment. Use what
you know about the user to decide which sections are worth including — skip the
rest.

## Scope & composition

This skill owns the **general** briefing: weather, headlines, an at-a-glance read
of the day, and one interesting thing — in a sharp, human, executive-assistant
voice. Keep it that way.

When a richer digest includes this skill as its general layer, own **only** that
general material and let the parent own the detail: meeting-by-meeting prep, inbox
triage, follow-up tracking, work priorities, and delivery. Don't repeat those
here. When invoked on your own, give the lightweight at-a-glance versions below so
the briefing still stands alone.

## Capability awareness

Build only the sections you can actually fill. Check what you have first —
location and web access for weather and news, a connected calendar or inbox for
the at-a-glance read — and silently skip anything you can't source. Never emit "I
don't have access to X" filler. Two real sections beat six empty ones.

## Briefing sections

### Weather & conditions

Current conditions and temperature, plus the day's high/low. Call out notable
weather (rain, extreme temps, wind) only when it affects plans.

### Top headlines

3–5 notable items, one sentence each. Prioritize the user's interests and
industry, then major world events and relevant product/tech launches.

### At a glance

A lightweight read of the day's shape — not a triage or prep pipeline:

- Today's commitments: how many, first and last, any obvious gap for focused work.
- Anything clearly urgent or time-sensitive in mail or messages.
- The one thing worth tackling first.

Keep this short. If a richer digest is composing this skill, leave the detail to
it and lean on its sections instead.

### Something interesting

End with one: an interesting fact or quote, an article worth reading later, or a
tip related to something the user is working on.

## Tone

- Concise and scannable — bullets, not paragraphs.
- Conversational but efficient, like a sharp executive assistant.
- No filler — if you have two useful sections, give two.
- Time-aware: a morning briefing reads differently from an afternoon check-in, in
  the user's own timezone.

## Adaptation over time

Lean on what you already know and remember about the user, and get more specific
with each briefing — weight news toward their interests, recall their usual
schedule shape, track recurring priorities. Don't fabricate details to fill a
section, and don't assume any preference store exists; work from what you
genuinely know.

Excerpt, first 3,721 characters of SKILL.md, verbatim from the audited commit. It is text from someone else’s repository, quoted so you can judge it before your agent reads it.

Install

Pinned to the audited commit 19bc863

Download folder ↗
git clone https://github.com/vellum-ai/vellum-assistant
git -C vellum-assistant checkout 19bc86343b63

The author documents no install command, so this uses the repository directly. Our verdict covers commit 19bc86343b63 only.

Works in

The author has not said which agents this skill supports, and we have not tested it in any.

Audit history

Every audit, every source change

  1. ✓SAFE B 89 / 100

    first audit · source 19bc86343b63

README badge

For maintainers · shows the latest audit

ModelsAtlas: SAFE BMODELSATLASSAFE · B
[![ModelsAtlas: SAFE B](https://modelsatlas.com/skills/vellum-ai/start-the-day/badge.svg)](https://modelsatlas.com/skills/vellum-ai/start-the-day/)

The badge shows our verdict and grade for this skill, and links back to this page. It changes when the audit does.

Add this badge to your README

[![ModelsAtlas: SAFE B](https://modelsatlas.com/skills/vellum-ai/start-the-day/badge.svg)](https://modelsatlas.com/skills/vellum-ai/start-the-day/)

Questions about Start The Day

What does the Start The Day skill do?
An AI Assistant that’s easy to setup, does your work 24/7, knows your preferences and gets better over time.
Is Start The Day safe to install?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean skill reads B.
What can Start The Day access on my machine?
The audit observed no filesystem, network or shell use at all in its source.
How current is this page?
The grade is for one exact copy of the source (19bc86343b63), read on 2026-10-14. The repository is watched, and a new audit runs when it changes — this is the first audit.

Sources

Spotted something wrong? Report a correction · Methodology

Keep going in your AI

Opens with this page as the source. We add nothing else to the prompt.