Agent skill · Audited from source

Daily Brief

skill · huytieu/COG-second-brainMIT licenceAudited 14 Oct 2026 · source 6ea1a6ff2160

★ 1,281pushed 11 days ago
✓SAFEGrade B · 89/100 · 14 Oct 2026 · 6ea1a6f
1,281repo stars · whole huytieu/COG-second-brain

Is it safe? Yes — SAFE, grade B (89/100). We read this skill's source at commit 6ea1a6ff2160 and found no filesystem, network or shell access and no hard-coded secrets. What it does: Generate personalized news intelligence with verified sources (7-day freshness requirement)

Ask an AI about this pageGChatGPTCClaudePPerplexityGeGeminiXGrok
More
Cite

Cite this page

ModelsAtlas. “Daily Brief (huytieu/COG-second-brain)”. Retrieved 14 Oct 2026. https://modelsatlas.com/skills/huytieu/daily-brief

Trust audit

Audit 0.4.1 · source read 14 Oct 2026

Trust score89/100✓SAFE B
0 critical0 high0 medium0 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, activityPASS0
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 (0)

No findings at any severity. We re-audit when the source changes.

Audit 0.4.1 · source sha 6ea1a6ff2160 · 14 Oct 2026Report an issue or request a re-scan

Provenance

Who published it, and what the verdict is pinned to

  • Publisherhuytieu GitHub userOwner of the repository this skill is read from
  • Source folderhuytieu/COG-second-brain/.claude/skills/daily-briefThe exact folder we audited
  • LicenceMITAs the repository states it
  • Commit pinned for this verdict6ea1a6ff2160A new audit runs when the source changes
  • Repository statusNot archivedLast push 11 days ago
  • Sandboxed runNot runSkills are read, not executed; layer L4 is skipped

What it tells the agent

Full source on GitHub ↗

Its description: Generate personalized news intelligence with verified sources (7-day freshness requirement)

---
name: daily-brief
description: Generate personalized news intelligence with verified sources (7-day freshness requirement)
roles: [all]
integrations: [web-search]
---

# COG Daily Brief Skill

## Purpose
Find verified, relevant news for personalized daily briefings with strict verification standards and strategic relevance analysis tailored to user's specific interests and projects.

## When to Invoke
- User wants their daily news briefing
- User says "daily brief", "news", "what's happening", "morning brief"
- User wants to stay updated on their interests
- Morning routine or regular check-in time

## Agent Mode Awareness

**Check `agent_mode` in `00-inbox/MY-PROFILE.md` frontmatter:**
- If `agent_mode: team` — delegate news research across different interest areas to parallel sub-agents (e.g., one agent per topic cluster). Each agent searches, verifies sources, and returns findings. Combine and synthesize results into the final brief.
- If `agent_mode: solo` (default) — handle all research and synthesis directly in the conversation. No delegation.

## Pre-Flight Check

**Before executing, check for user profile:**

1. Look for `00-inbox/MY-PROFILE.md` and `00-inbox/MY-INTERESTS.md` in the vault
2. If NOT found:
   ```
   Welcome to COG! Daily briefs work best when personalized.

   Let's quickly set up your profile (takes 2 minutes).

   Would you like to run onboarding first, or should I generate a general brief?
   ```
3. If found:
   - Read `MY-INTERESTS.md` to get topics for news curation
   - Read `MY-PROFILE.md` to get user's name and active projects
   - Read `03-professional/COMPETITIVE-WATCHLIST.md` if exists for competitive tracking
   - Use topics to curate relevant news
   - Connect news to user's active projects when relevant

**Get current timestamp (REQUIRED before generating any files):**

1. Run `date '+%Y-%m-%d %H:%M'` using Bash to get the actual current date and time
2. Store this value and use it for the `created:` frontmatter field
3. NEVER guess or fabricate the time — always use the value returned by the `date` command

## Process Flow

### 1. Gather Context

Collect the information needed for personalized curation:

- Read `00-inbox/MY-PROFILE.md` for:
  - User's name
  - User's role/job
  - Active projects

- Read `00-inbox/MY-INTERESTS.md` for:
  - Topics they're interested in
  - Preferred news sources

- Read `03-professional/COMPETITIVE-WATCHLIST.md` (if exists) for:
  - Companies/people to track

#### Deduplication — Previous Brief Scan

Read up to 3 most recent daily briefs from `01-daily/briefs/` (most recent first):
- Extract `dedup_urls` from their frontmatter (if present)
- Also scan their headlines/story titles as semantic fallback for cross-source matching
- Build a set of **covered stories** to avoid repeating

**Matching rules (in priority order):**
1. **URL match (primary):** If a candidate story's main source URL already appears in `dedup_urls`, it's a known story
2. **Headline match (fallback):** If the URL is different but the headline describes the same event as a previous story, treat as duplicate — this catches the same story reported by different outlets

During news research (Step 2), apply dedup rules:
- **Skip** stories already covered unless there is a **material update** (new data, resolution, escalation, reversal)
- If including an update, prefix with "**Update:** _first covered [date]_"
- Stories older than 3 briefs are eligible for re-inclusion if still developing

### 2. News Research and Curation

Apply comprehensive news research methodology:

#### Interest-Based Research
- Search based on user's current interest profile
- Focus on strategic relevance to user's role and projects
- Identify emerging patterns and developments
- Diversify sources for balanced perspective

#### Verification Standards (MANDATORY)

**Date Verification:**
- ALL news MUST be from last 7 days ONLY
- Verify publication dates with verified timestamps
- NEVER include older news without explicit disclosure

**Source Credibility Assessment:**
- **Tier 1 Sources (Highest Credibility):** Major news organizations (Reuters, AP, Bloomberg, WSJ, NYT), official company announcements, government statements
- **Tier 2 Sources (High Credibility):** Industry publications, credible tech/business blogs, research reports from reputable firms
- **Tier 3 Sources (Moderate - Verify Carefully):** Social media from verified accounts, company blogs, community discussions
- Minimum 2 credible sources for any claim
- Cross-reference key facts and figures

**Fact Cross-Reference:**
- Verify claims across multiple independent sources
- Use WebFetch to verify any statistics before including them
- Identify potential bias and provide balanced perspective

#### Strategic Relevance Analysis

Assess impact on user:

**Direct Impact (High Priority):**
- News directly affecting user's projects or companies
- Regulatory changes affecting user's industry
- Competitive moves by direct competitors
- Technology developments affecting user's tech stack

**Strategic Impact (Medium Priority):**
- Market trends affecting user's target customers
- Investment patterns in user's industry
- Talent market changes affecting hiring
- Partnership opportunities or threats

**Contextual Impact (Lower Priority):**
- Broader economic trends affecting business climate
- Technology trends affecting future planning
- Industry thought leadership and opinion
- Educational content for professional development

#### Opportunity and Threat Identification

**Opportunities:**
- Market Opportunities: New markets or customer segments opening
- Technology Opportunities: New tools or platforms to leverage
- Partnership Opportunities: Potential collaboration partners
- Competitive Opportunities: Competitor weaknesses or market gaps

**Threats:**
- Competitive Threats: New competitors or competitive advantages
- Technology Threats: Disruptive technologies or obsolescence risks
- Market Threats: Market shifts or customer 

Excerpt, first 6,000 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 6ea1a6f

Download folder ↗
git clone https://github.com/huytieu/COG-second-brain
git -C COG-second-brain checkout 6ea1a6ff2160

The author documents no install command, so this uses the repository directly. Our verdict covers commit 6ea1a6ff2160 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 6ea1a6ff2160

README badge

For maintainers · shows the latest audit

ModelsAtlas: SAFE BMODELSATLASSAFE · B
[![ModelsAtlas: SAFE B](https://modelsatlas.com/skills/huytieu/daily-brief/badge.svg)](https://modelsatlas.com/skills/huytieu/daily-brief/)

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

Similar skills

Add this badge to your README

[![ModelsAtlas: SAFE B](https://modelsatlas.com/skills/huytieu/daily-brief/badge.svg)](https://modelsatlas.com/skills/huytieu/daily-brief/)

Questions about Daily Brief

What does the Daily Brief skill do?
Self-evolving second brain with 35 AI skills, 10 agents, and people CRM. Closed-loop harness: a V-model verification lifecycle where the worker never grades its own homework. Plus paired anti-slop design skills for marketing and product UI. Works with Claude Code, Cursor, Kiro, Gemini CLI, Codex.
Is Daily Brief 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 Daily Brief 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 (6ea1a6ff2160), 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.