Deep strategic research engine — decomposes questions into parallel research threads, spawns multiple agents, and synthesizes into actionable strategic analysis
中文简介正在准备中。当前显示原文说明。
Quick capture of raw thoughts with intelligent domain classification and competitive intelligence extraction
中文简介正在准备中。当前显示原文说明。
安装前可以查看交给 AI 代理的指令内容。
Transform raw thoughts into strategic intelligence through quick capture, systematic analysis, pattern recognition, and domain-aware insight extraction with minimal user friction.
Check agent_mode in 00-inbox/MY-PROFILE.md frontmatter:
agent_mode: team — delegate research, analysis, and writing subtasks to specialist sub-agents (e.g., use Task tool to delegate deep analysis, competitive intel extraction, or pattern recognition to separate agents). Combine results before presenting to user.agent_mode: solo (default) — handle everything directly in the conversation. No delegation.Before executing, check for user profile:
00-inbox/MY-PROFILE.md in the vaultWelcome to COG! It looks like this is your first time.
Before we start, let's quickly set up your profile (takes 2 minutes).
Would you like to run onboarding first, or should I proceed with default settings?
03-professional/COMPETITIVE-WATCHLIST.md if it exists for competitive intelligence detectionGet current timestamp (REQUIRED before generating any files):
date '+%Y-%m-%d %H:%M' using Bash to get the actual current date and timecreated: frontmatter AND filename HHMM component)date commandAsk user to classify or auto-detect based on content:
If user profile exists with projects:
If no profile: Use standard personal/professional/mixed classification
Apply the comprehensive analysis framework directly:
Analyze the input to understand:
Extract and identify:
Determine:
Identify:
If COMPETITIVE-WATCHLIST.md exists:
Create braindump file with this structure:
---
type: "braindump"
domain: "[personal|professional|project-specific|mixed]"
project: "[project-name]" # Only if project-specific
date: "YYYY-MM-DD"
created: "YYYY-MM-DD HH:MM"
themes: ["theme1", "theme2", "theme3"]
tags: ["#braindump", "#raw-thoughts", "#domain-tag"]
status: "captured"
energy_level: "[high|medium|low]"
emotional_tone: "[primary-emotion]"
confidence: "[high|medium|low]"
---
# Braindump: [Auto-generated descriptive title]
## Raw Thoughts
[Original user content preserved exactly as provided]
## Content Analysis
### Main Themes
1. **Theme 1:** [description and significance]
2. **Theme 2:** [description and significance]
3. **Theme 3:** [description and significance]
### Supporting Ideas
- [Supporting concept 1]
- [Supporting concept 2]
- [Supporting concept 3]
### Questions Raised
- [Question 1 for deeper exploration]
- [Question 2 requiring consideration]
### Decisions Contemplated
- [Decision 1 being considered with options]
- [Decision 2 under evaluation]
## Strategic Intelligence
### Key Insights
1. **Insight 1:** [description and implications]
2. **Insight 2:** [description and implications]
3. **Insight 3:** [description and implications]
### Pattern Recognition
- **Connection to Previous Thinking:** [links to earlier braindumps or frameworks]
- **Recurring Patterns:** [themes that keep appearing]
- **Evolution:** [how thinking has developed]
### Strategic Implications
- [How this affects goals]
- [Impact on current projects]
- [Decision-making considerations]
## Action Items
**Note:** Calculate actual due dates from today's date and append Obsidian Tasks emoji format.
### Immediate (24-48 hours)
- [ ] [specific action] 📅 [YYYY-MM-DD = tomorrow's date]
### Short-term (1-2 weeks)
- [ ] [specific action] 📅 [YYYY-MM-DD = date +1 week from today]
### Strategic Considerations
- [longer-term implications and considerations]
## Connections
- **Related Braindumps:** [[link1]], [[link2]]
- **Relevant Projects:** [[project1]], [[project2]]
- **Knowledge Base:** [[insight1]], [[framework1]]
## Domain Classification
- **Primary Domain:** [domain] ([confidence]%)
- **Reasoning:** [why this classification]
- **Cross-Domain Elements:** [if applicable]
- **Privacy Level:** [public|private|confidential]
## Processing Notes
### Emotional Context
- **Energy Level:** [assessment]
- **Emotional Tone:** [assessment]
- **Implications:** [what this suggests]
### Confidence Assessment
- **Overall Analysis:** [percentage] - [reasoning]
- **Domain Classification:** [percentage] - [reasoning]
- **Strategic Insights:** [percentage] - [reasoning]
- **Areas Requiring Clarification:** [specific questions if needed]
---
*Processed by COG Brain Dump Analyst*
Save to appropriate location:
02-personal/braindumps/braindump-YYYY-MM-DD-HHMM-<slug>.md03-professional/braindumps/braindump-YYYY-MM-DD-HHMM-<slug>.md04-projects/[project-slug]/braindumps/braindump-YYYY-MM-DD-HHMM-<slug>.md00-inbox/braindump-YYYY-MM-DD-HHMM-<slug>.mdIf competitive intelligence detected (mentions of companies/people from watchlist):
Create/update: 04-projects/[project]/competitive/[company-slug].md
---
type: "competitive-intelligence"
company: "[Company Name]"
project: "[project-name]"
last_updated: "YYYY-MM-DD"
sources: ["braindump"]
tags: ["#competitive", "#intelligence", "#[company-slug]"]
---
# Competitive Intelligence: [Company Name]
## Latest Update - [Date]
**Source:** [[braindump-file-reference]]
[Extracted competitive intelligence from braindump]
## Previous Intelligence
[Historical intel from earlier braindumps]
## Strategic Implications
[Analysis of what this means for the project]
## Action Items
- [ ] [Follow-up actions based on intel] 📅 [YYYY-MM-DD = calculated due date]
---
*Auto-extracted by COG Brain Dump Analyst*
CRITICAL: All YAML frontmatter must use proper Obsidian-compatible formatting:
["item1", "item2", "item3"]true or falseExamples:
# CORRECT
type: "braindump"
themes: ["automation", "testing", "ui-improvements"]
analysis_needed: true
# INCORRECT
type: braindump
themes: [automation, testing, ui-improvements]
analysis_needed: "true"
Always explicitly state confidence levels and reasoning in the processing notes.
After braindump, suggest:
If competitive mentions detected:
还没有评价。欢迎分享你的使用感受。
无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。
还没有评论。来写第一条吧。
Deep strategic research engine — decomposes questions into parallel research threads, spawns multiple agents, and synthesizes into actionable strategic analysis
中文简介正在准备中。当前显示原文说明。
Run one task through the V-model verification loop: CP-2 plan → CP-3 build → CP-3v component verify → CP-4 integration verify (full lane) → CP-5 acceptance. The worker never grades its own homework; evidence rows trace back to AC-n. Opt-in: invoke with /closed-loop or by asking for the closed loop, proper verification, or an evidence trail. Ordinary work does not run this.
中文简介正在准备中。当前显示原文说明。
Deep-dive 7-day analysis across all data sources for weekly reviews, board prep, and strategic planning
中文简介正在准备中。当前显示原文说明。
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
中文简介正在准备中。当前显示原文说明。
Create user stories with duplicate checking across any project tracker (Linear, GitHub Issues, Jira)
中文简介正在准备中。当前显示原文说明。
Generate personalized news intelligence with verified sources (7-day freshness requirement)
中文简介正在准备中。当前显示原文说明。