knowledge-consolidation
The knowledge-consolidation skill transforms scattered notes and braindumps into coherent frameworks by scanning personal, professional, and project-specific documents, identifying recurring themes, and synthesizing insights into unified knowledge documents. Use it during periodic maintenance cycles or when you need to extract patterns from accumulated insights before making major decisions that would benefit from structured frameworks.
git clone --depth 1 https://github.com/huytieu/COG-second-brain /tmp/knowledge-consolidation && cp -r /tmp/knowledge-consolidation/.claude/skills/knowledge-consolidation ~/.claude/skills/knowledge-consolidationSKILL.md
# COG Knowledge Consolidation Skill ## Purpose Transform scattered insights from braindumps, daily briefs, and check-ins into coherent frameworks and "single source of truth" knowledge documents through pattern recognition and systematic synthesis. ## When to Invoke - User wants to consolidate their insights - User says "consolidate knowledge", "build frameworks", "synthesize insights" - Time for periodic knowledge base maintenance (weekly, monthly, quarterly) - User wants to extract patterns from accumulated braindumps - Before major decisions that could benefit from framework consultation ## Agent Mode Awareness **Check `agent_mode` in `00-inbox/MY-PROFILE.md` frontmatter:** - If `agent_mode: team` — delegate scanning and pattern extraction to parallel sub-agents (e.g., one per domain: personal braindumps, professional braindumps, project-specific content, daily briefs). Each agent identifies themes and patterns, then a synthesis agent combines findings into frameworks. - If `agent_mode: solo` (default) — handle all scanning, pattern recognition, and framework building directly. No delegation. ## Pre-Flight Check **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. Data Gathering **Scan vault for unprocessed or partially processed content:** - All braindumps since last consolidation: - `02-personal/braindumps/` - `03-professional/braindumps/` - `04-projects/*/braindumps/` - `00-inbox/braindump-*.md` (mixed domain) - Daily briefs and check-ins: - `01-daily/briefs/` - `01-daily/checkins/` - Any meeting transcripts or project documents in: - `04-projects/*/planning/` - `04-projects/*/resources/` **Determine scope:** - Ask user: "What time period should I analyze? (last week, last month, last quarter, all time, or custom range?)" - Identify unprocessed content (check for `status: "captured"` or missing consolidation metadata) **Gather statistics:** - Total documents to analyze - Breakdown by domain and type - Date range coverage ### 2. Pattern Recognition Apply systematic pattern detection across all content: #### Frequency Analysis **What comes up repeatedly?** - Identify themes mentioned across multiple documents - Track topic frequency and clustering - Recognize persistent questions or concerns - Spot recurring action items or decisions #### Temporal Clustering **What insights emerged together?** - Group related insights by time period - Identify how thinking evolved over time - Recognize inflection points where thinking shifted - Map catalysts that triggered changes #### Domain Correlation **What patterns cross domains?** - Personal insights affecting professional thinking - Professional learnings applied to projects - Project experiences informing personal growth - Strategic themes spanning all domains #### Contradiction Analysis **Where does thinking conflict?** - Identify contradictory thoughts or approaches - Recognize evolution vs. inconsistency - Understand resolution or ongoing tension - Track perspective shifts over time #### Cross-Cutting Patterns **Meta-patterns across all dimensions:** - Decision-making approaches - Problem-solving strategies - Learning patterns - Emotional/energy patterns - Relationship patterns - Creative processes ### 3. Framework Development Synthesize patterns into actionable frameworks: #### Identify Core Principles **From scattered insights to fundamental truths:** - What patterns reveal deeper principles? - What rules or heuristics emerge? - What mental models are forming? - What strategies are proving effective? #### Test Against Evidence **Validate frameworks with source material:** - Do source insights support these principles? - Are there counter-examples or exceptions? - How confident can we be in this framework? - What are the boundary conditions? #### Define Boundaries **When does framework apply/not apply?** - What contexts does this framework serve? - What are its limitations? - When should it NOT be used? - What assumptions does it rely on? #### Create Applications **How to use this framework:** - Specific use cases - Decision-making applications - Problem-solving templates - Practical implementation steps ### 4. Knowledge Integration Update and create knowledge base documents: #### Update Existing Frameworks For each framework that needs updating: ```markdown --- type: "consolidated-knowledge" domain: "[primary-domain]" framework: "[framework-name]" created: "[original-date]" last_updated: "YYYY-MM-DD" consolidation_id: "[consolidation-session-id]" source_documents: [count] status: "stable|working|emerging" tags: ["#framework", "#consolidated", "#[topic]"] --- # [Framework Name] ## Framework Overview [Clear description of what this framework is and what it helps with] **Status:** [Stable | Working | Emerging] **Last Updated:** [Date] **Source Insights:** [count] documents analyzed --- ## Core Principles ### Principle 1: [Name] **Statement:** [Clear, concise principle statement] **Evidence:** - [[braindump-YYYY-MM-DD]] - [supporting insight] - [[daily-brief-YYYY-MM-DD]] - [supporting evidence] - [[checkin-YYYY-MM-DD]] - [pattern observation] **Evolution:** [How this principle has developed or been refined] **Confidence:** [High|Medium|Low] - [reasoning] ### Principle 2: [Name] [Same structure as Principle 1] ### Principle 3: [Name] [Same structure as Principle 1] --- ## Applications & Use Cases ### Use Case 1: [Scenario] **When to Apply:** [Specific situation] **How to Apply:** 1. [Step 1] 2. [Step 2] 3. [Step 3] **Expected Outcomes:** [What to expect] **Example:** [Real example from user's experience] ### Use Case 2: [Scenario] [Same structure as Use Case 1] --- ## Boundaries & Limitations **This
Update people profiles in 05-knowledge/people/ with new information from brief data, meetings, or Slack
Collect data from GitHub, Slack, Jira, Linear, or file system. Structured extraction only — no synthesis.
Execute pre-approved mutations — Jira transitions, Linear updates, API calls, build commands.
Read, write, and organize vault files. Metadata updates, file moves, profile updates.
Execute publishing operations — Slack, Confluence, Notion, webhooks. Receives final content and posts it.
Web research agent. Searches, fetches URLs, extracts facts and evidence. No synthesis — just structured findings.
Deep strategic research engine — decomposes questions into parallel research threads, spawns multiple agents, and synthesizes into actionable strategic analysis
Quick capture of raw thoughts with intelligent domain classification and competitive intelligence extraction