How is freshness enforced?

All sources must be within 7 days and every claim must be backed by at least one source.

What happens if claims lack a verifiable source?

The claim is flagged for re-check or omitted until a verifiable source is found.

How is confidence determined?

Confidence levels are based on corroboration: high for 3+ sources, medium for 2, and low for 1.

cog-daily-intelligence

npx machina-cli add skill a5c-ai/babysitter/daily-intelligence --openclaw

Files (1)

SKILL.md

1.6 KB

COG Daily Intelligence Skill

Generate personalized daily intelligence briefs using verified sources with strict freshness and accuracy requirements.

Capabilities

Gather intelligence sources filtered by role and interests
Enforce 7-day freshness requirement on all sources
Apply verification-first methodology: every claim needs a source
Target 95%+ source accuracy
Assign confidence levels to all intelligence items
Cross-reference with existing vault knowledge in 05-knowledge
Quality-gated brief generation with iterative refinement

Tool Use Instructions

Use file-read to load user profile and interests from 00-inbox
Use web-search to gather relevant intelligence sources
Use web-fetch to verify and extract content from sources
Cross-verify claims across multiple sources
Use file-read to check existing knowledge in 05-knowledge for context
Use file-write to create daily brief in 01-daily
Use git-commit to commit the brief

Quality Standards

All sources must be within 7 days
Every claim must have at least one verifiable source
Confidence levels: high (3+ corroborating sources), medium (2 sources), low (1 source)
Target overall accuracy: 95%+

Examples

{
  "vaultPath": "./cog-vault",
  "mode": "daily-brief",
  "userName": "Alex",
  "rolePack": "engineer",
  "targetQuality": 80
}

Source

git clone https://github.com/a5c-ai/babysitter/blob/main/plugins/babysitter/skills/babysit/process/methodologies/cog-second-brain/skills/daily-intelligence/SKILL.md

View on GitHub

Overview

Cog Daily Intelligence generates daily briefs tailored to user role and interests, using sources within 7 days and a verification-first approach. Every claim is sourced, confidence-rated, and cross-checked against vault knowledge in 05-knowledge to target 95%+ accuracy.

How This Skill Works

It loads the user profile from 00-inbox, runs web-search to gather relevant sources, and uses web-fetch to verify and extract verified content. It cross-checks claims across sources and against 05-knowledge, then writes the final brief to 01-daily and commits with git-commit.

When to Use It

Daily briefing for role-specific news and interests
Pre-meeting prep with high-confidence briefings
Monitoring evolving topics with 7-day freshness
Competitor or market updates requiring source-backed claims
Regulatory or policy updates needing verifiable sources

Quick Start

Step 1: Load user profile from 00-inbox using file-read
Step 2: Gather and verify sources with web-search and web-fetch
Step 3: Write the brief to 01-daily and commit with git-commit

Best Practices

Keep user profiles current with roles and interests in 00-inbox
Ensure every claim has at least one verifiable source
Cross-verify claims across multiple sources before acceptance
Refer to 05-knowledge to contextualize and validate claims
Tag and monitor confidence levels (high/medium/low) before distribution

Example Use Cases

A daily cybersecurity briefing for an IT lead with 7-day freshness and high confidence
A product team daily digest on competitor moves with verified sources
An executive brief on regulatory developments with source-backed claims
R&D update on AI safety news with cross-source verification
Finance desk daily digest of market-moving headlines with high accuracy

Frequently Asked Questions

Add this skill to your agents