Braindump

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

Gates applied: no behavioural pass.

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

• Publisherhuytieu GitHub userOwner of the repository this skill is read from
• Source folderhuytieu/COG-second-brain/.claude/skills/braindumpThe 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

Its description: Quick capture of raw thoughts with intelligent domain classification and competitive intelligence extraction

---
name: braindump
description: Quick capture of raw thoughts with intelligent domain classification and competitive intelligence extraction
roles: [all]
integrations: []
---

# COG Braindump Skill

## Purpose
Transform raw thoughts into strategic intelligence through quick capture, systematic analysis, pattern recognition, and domain-aware insight extraction with minimal user friction.

## When to Invoke
- User wants to capture stream-of-consciousness thoughts
- User says "braindump", "brain dump", "capture thoughts", or "write down ideas"
- User has ideas they want to quickly record
- User mentions wanting to get thoughts out of their head

## Agent Mode Awareness

**Check `agent_mode` in `00-inbox/MY-PROFILE.md` frontmatter:**
- If `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.
- If `agent_mode: solo` (default) — handle everything directly in the conversation. No delegation.

## Pre-Flight Check

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

1. Look for `00-inbox/MY-PROFILE.md` in the vault
2. If NOT found:
   ```
   Welcome 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?
   ```
3. If found:
   - Read the profile to get user's name and active projects
   - If user has active projects listed, offer them as domain options
   - Use user's name for friendly communication
   - Read `03-professional/COMPETITIVE-WATCHLIST.md` if it exists for competitive intelligence detection

**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 ALL timestamp fields (`created:` frontmatter AND filename `HHMM` component)
3. NEVER guess or fabricate the time — always use the value returned by the `date` command

## Process Flow

### 1. User Interaction & Input Collection
- Greet user warmly (use their name from MY-PROFILE.md if available)
- Ask: "What's on your mind?" or "Ready for a brain dump?"
- Collect their stream-of-consciousness input (can be long, rambling, voice-to-text, etc.)
- Accept any format - no judgment, no filtering

### 2. Domain Classification
Ask user to classify or auto-detect based on content:

**If user profile exists with projects:**
- **Personal:** Individual growth, relationships, wellness
- **Professional:** Work, leadership, career development
- **Project-Specific:** Related to specific projects
  - If MY-PROFILE.md lists projects, offer: "Which project? [list project names]"
  - Example: "Which project? (1) SaaS Product, (2) Book Writing, (3) Health App"
- **Mixed/Unclear:** Spans multiple areas

**If no profile:** Use standard personal/professional/mixed classification

### 3. Content Analysis and Processing

Apply the comprehensive analysis framework directly:

#### Phase 1: Content Ingestion
Analyze the input to understand:
- **Content Type:** [voice-transcript|written-notes|mixed]
- **Length:** [word-count]
- **Energy Level:** [high|medium|low]
- **Emotional Tone:** [excited|frustrated|curious|concerned|neutral|mixed]
- **Context:** [situational-background]

#### Phase 2: Structural Analysis
Extract and identify:
- **Main Themes:** [3-5 primary topics]
- **Supporting Ideas:** [related concepts and details]
- **Questions Raised:** [explicit and implicit questions]
- **Decisions Contemplated:** [choices being considered]
- **Action Items:** [tasks and commitments identified]

#### Phase 3: Domain Classification (with confidence)
Determine:
- **Primary Domain:** [personal|professional|project-specific] with confidence level
- **Secondary Domains:** [if content spans multiple areas]
- **Cross-Domain Elements:** [themes that apply across domains]
- **Privacy Considerations:** [sensitive content requiring protection]

#### Phase 4: Strategic Insight Extraction
Identify:
- **Key Insights:** [3-5 most important realizations]
- **Pattern Recognition:** [connections to previous thoughts/decisions]
- **Strategic Implications:** [what this means for goals and priorities]
- **Decision Framework:** [how this informs future choices]

#### Phase 5: Competitive Intelligence Detection
If COMPETITIVE-WATCHLIST.md exists:
- Scan braindump content for mentions of tracked companies/people
- Extract competitive intelligence to separate files
- Create cross-references back to original braindump

### 4. Generate Structured Output

Create braindump file with this structure:

```markdown
---
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 T

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.

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

Works in

1. 2026-10-14
   ✓SAFE B 89 / 100

   first audit · source 6ea1a6ff2160

Questions about Braindump

• github.com/huytieu/COG-second-brain/tree/main/.claude/skills/bra — the audited source at commit 6ea1a6ff2160 and every finding aboveObserved · 14 Oct 2026

Spotted something wrong? Report a correction · Methodology