بنقرة واحدة
daily-brief
Generate personalized news intelligence with verified sources (7-day freshness requirement)
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
القائمة
Generate personalized news intelligence with verified sources (7-day freshness requirement)
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
استنادا إلى تصنيف SOC المهني
Autonomous content pipeline - scout announcements in your field, triage by trend momentum and personal angle, produce posts/blogs/videos in your voice with ledger-based dedup, hard volume caps, and screenshot-verified publishing
Periodic trust sweep of persistent memory and durable knowledge notes - re-verifies environment-dependent claims against the live environment, stamps last_verified + confidence, and proposes archiving drifted entries
Build frameworks from scattered insights across all braindumps and notes
Shared loop-engineering reference for COG skills - the agent loop, deterministic verifiers, termination conditions, in-loop context management, and named patterns. Invoke when designing or debugging a skill that iterates (search-verify-retry, scan-until-dry, fetch-retry-gate).
Quick capture URLs with automatic content extraction, insights, and categorization into knowledge booklets
Cross-domain pattern analysis and strategic reflection for weekly review
| name | daily-brief |
| description | Generate personalized news intelligence with verified sources (7-day freshness requirement) |
| roles | ["all"] |
| integrations | ["web-search"] |
Find verified, relevant news for personalized daily briefings with strict verification standards and strategic relevance analysis tailored to user's specific interests and projects.
Check agent_mode in 00-inbox/MY-PROFILE.md frontmatter:
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.agent_mode: solo (default) — handle all research and synthesis directly in the conversation. No delegation.Before executing, check for user profile:
00-inbox/MY-PROFILE.md and 00-inbox/MY-INTERESTS.md in the vaultWelcome 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?
MY-INTERESTS.md to get topics for news curationMY-PROFILE.md to get user's name and active projects03-professional/COMPETITIVE-WATCHLIST.md if exists for competitive trackingGet current timestamp (REQUIRED before generating any files):
date '+%Y-%m-%d %H:%M' using Bash to get the actual current date and timecreated: frontmatter fielddate commandCollect the information needed for personalized curation:
Read 00-inbox/MY-PROFILE.md for:
Read 00-inbox/MY-INTERESTS.md for:
Read 03-professional/COMPETITIVE-WATCHLIST.md (if exists) for:
Read up to 3 most recent daily briefs from 01-daily/briefs/ (most recent first):
dedup_urls from their frontmatter (if present)Matching rules (in priority order):
dedup_urls, it's a known storyDuring news research (Step 2), apply dedup rules:
Apply comprehensive news research methodology:
Date Verification:
Source Credibility Assessment:
Fact Cross-Reference:
Assess impact on user:
Direct Impact (High Priority):
Strategic Impact (Medium Priority):
Contextual Impact (Lower Priority):
Opportunities:
Threats:
Create structured briefing document:
---
type: "daily-brief"
domain: "shared"
date: "YYYY-MM-DD"
created: "YYYY-MM-DD HH:MM"
sources_verified: true
news_age_verified: true
confidence: "high"
tags: ["#daily-brief", "#news", "#strategic-intelligence"]
interests: ["interest1", "interest2"]
projects_referenced: ["project1"]
items_count: [number]
dedup_urls: ["https://primary-source-url-for-each-story-covered"]
---
# Daily Brief - [Date]
**Good [morning/afternoon], [Name]!**
## Executive Summary
[2-3 sentences highlighting the most important developments across all your interest areas]
---
## High Impact News
### [News Item 1 - Direct Impact]
**Relevance:** [Why this matters to you specifically]
[Detailed summary of the news]
**Impact Assessment:**
- **Projects Affected:** [Which of your projects this impacts]
- **Potential Effects:** [Specific implications]
- **Action Suggested:** [Recommended response or follow-up]
**Sources:**
- [Source Name 1] (Tier [1/2/3]) - [Publication Date] - [Link]
- [Source Name 2] (Tier [1/2/3]) - [Publication Date] - [Link]
**Confidence:** [High/Medium/Low] - [Reasoning]
---
### [News Item 2 - Direct Impact]
[Same structure as above]
---
## Strategic Developments
### [News Item 3 - Strategic Impact]
**Relevance:** [Why this matters strategically]
[Detailed summary]
**Strategic Implications:**
- [Implication 1]
- [Implication 2]
- [Implication 3]
**Sources:**
- [Source listings with credibility tiers and links]
**Confidence:** [High/Medium/Low] - [Reasoning]
---
## Market Intelligence
### [News Item 4 - Market Trends]
**Relevance:** [Why this market trend matters]
[Detailed summary]
**Market Impact:**
- [Impact on target customers]
- [Industry trends]
- [Investment patterns]
**Sources:**
- [Source listings with credibility tiers and links]
**Confidence:** [High/Medium/Low] - [Reasoning]
---
## Technology Watch
### [News Item 5 - Tech Developments]
**Relevance:** [Why this technology matters]
[Detailed summary]
**Technology Implications:**
- [Impact on tech stack]
- [New tools or platforms]
- [Emerging technologies]
**Sources:**
- [Source listings with credibility tiers and links]
**Confidence:** [High/Medium/Low] - [Reasoning]
---
## Competitive Landscape
### [Competitor/Company Name - From Watchlist]
**Recent Activity:**
[Summary of competitive intelligence gathered]
**Competitive Implications:**
- [What this means for your projects]
- [Opportunities or threats]
- [Recommended responses]
**Sources:**
- [Source listings with credibility tiers and links]
**Confidence:** [High/Medium/Low] - [Reasoning]
---
## Opportunities & Recommendations
**Note:** Calculate actual due dates from today's date and append Obsidian Tasks emoji format.
### Immediate Actions (Today/This Week)
- [ ] [Specific action item 1] 📅 [YYYY-MM-DD = today's date]
- [ ] [Specific action item 2] 📅 [YYYY-MM-DD = today's date]
- [ ] [Specific action item 3] 📅 [YYYY-MM-DD = end of this week]
### Research Needed
- [Area 1 requiring deeper investigation]
- [Area 2 to monitor closely]
### People to Inform/Consult
- [Stakeholder 1]: [About what]
- [Stakeholder 2]: [About what]
---
## Risks & Threats
### Active Threats
- **Threat 1:** [Description and mitigation approach]
- **Threat 2:** [Description and mitigation approach]
### Emerging Risks to Monitor
- [Risk 1 to watch]
- [Risk 2 to watch]
---
## Verification Report
### Source Analysis
- **Tier 1 Sources:** [count] - [list main ones]
- **Tier 2 Sources:** [count] - [list main ones]
- **Cross-References Performed:** [number]
### Fact-Checking Results
- **Verified Claims:** [count]
- **Unverified Claims:** [count with explanation if any]
- **Conflicting Information:** [count with resolution approach if any]
### Freshness Verification
- ✅ All news items verified within 7-day window
- Publication date range: [Oldest date] to [Newest date]
### Confidence Assessment
- **Overall Confidence:** [percentage]%
- **High Confidence Items:** [count]
- **Medium Confidence Items:** [count]
- **Low Confidence Items:** [count] - [reasons if any]
---
## Complete Sources
### Strategic News
1. [Full source citation with link]
2. [Full source citation with link]
### Market Intelligence
1. [Full source citation with link]
2. [Full source citation with link]
### Technology Watch
1. [Full source citation with link]
2. [Full source citation with link]
### Competitive Intelligence
1. [Full source citation with link]
2. [Full source citation with link]
---
*Curated by COG News Curator | All news verified within 7-day freshness window | Sources cross-referenced for accuracy*
Save to: 01-daily/briefs/daily-brief-YYYY-MM-DD.md
When No Recent News Found: If no relevant news found in last 7 days for a particular interest area:
### [Interest Area]
**No significant news found in last 7 days**
Last significant development was [date if known] regarding [topic if known].
**Suggestions:**
- Consider expanding search criteria
- Check [alternative sources suggested]
- This area may be experiencing a quiet period
NEVER fabricate or use older news without explicit date disclosure.
When Information Cannot Be Verified:
### [Potential News Item]
**⚠️ Unable to verify from independent sources**
**Original Source:** [source] - Credibility: [assessment]
**What We Know:**
[What can be stated based on single source]
**What's Uncertain:**
[Specific claims that couldn't be verified]
**Recommendation:** Monitor for additional confirmation before acting
**Confidence:** Low - [reasoning]
When Sources Conflict:
### [News Item with Conflicting Reports]
**⚠️ Conflicting information from multiple sources**
**Perspective 1:**
[Summary] - **Source:** [source with credibility tier]
**Perspective 2:**
[Summary] - **Source:** [source with credibility tier]
**Areas of Agreement:**
- [What sources agree on]
**Areas of Disagreement:**
- [Where sources conflict]
**Recommendation:** [Approach for resolution or further research]
**Confidence:** Medium - [reasoning]
Daily brief is a verify-retry loop, not a single search. See .claude/skills/loop-engineering/SKILL.md for the shared vocabulary.
The loop (per interest area): search → fetch a candidate → run the verifier → keep it or discard and re-search with an adjusted query → repeat until enough verified items or a stop condition fires. In agent_mode: team, run one loop per interest cluster as isolated workers (orchestrator-workers), then synthesize.
The verifier (deterministic, runs every candidate):
A candidate that fails any check is discarded, not softened. This is COG's verification-first rule applied inside the loop: never let an item in on the agent's own "this looks recent enough."
Termination conditions (layered):
Patterns: evaluator-optimizer (each item scored against the verifier) + reflect-retry (a failed search informs the next query) + orchestrator-workers (team mode).
In-loop context: write verified items straight into the brief file as they pass; drop raw fetched page text once the summary and sources are extracted.
After daily brief, suggest:
The daily brief skill embodies COG's verification-first approach: