Agent skill

Knowledge Consolidation

by huytieu in huytieu/COG-second-brain

Build frameworks from scattered insights across all braindumps and notes

MITAuto-check passedKnowledge Management

Install Knowledge Consolidation

skills CLI
$ npx skills add huytieu/COG-second-brain --skill knowledge-consolidation -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install huytieu/COG-second-brain knowledge-consolidation --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/huytieu/COG-second-brain.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/knowledge-consolidation .claude/skills/knowledge-consolidation && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
knowledge-consolidation
GitHub stars
1.3k
Token cost
~2.9k tokens
SKILL.md length
1,321 words
Files
2 (incl. references)
Skills in repo
37
Repo updated
First seen
Licence
MIT

At a glance

Build frameworks from scattered insights across all braindumps and notes

  • Works in 7 steps: Data Gathering → Pattern Recognition → Framework Development → …
  • Knowledge Management work in your project
  • SKILL.md covers Purpose, When to Invoke, Agent Mode Awareness and Pre-Flight Check, plus 7 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Knowledge Consolidation is an agent skill from huytieu/COG-second-brain. Build frameworks from scattered insights across all braindumps and notes

Its SKILL.md is about 2.9k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including reference files (for example `references/templates.md`).

It sits in Knowledge Management. The repository describes itself as: Self-evolving second brain with 35 AI skills, 10 agents, and people CRM. Closed-loop harness: a V-model verification lifecycle where the worker never grades its own homework… The licence is MIT.

When your agent uses it

  • Knowledge Management work in your project

Example prompts

  • “/knowledge-consolidation”

Workflow steps

7 steps, taken from the step headings in SKILL.md.

  1. Data Gathering
  2. Pattern Recognition
  3. Framework Development
  4. Knowledge Integration
  5. Generate Consolidation Report
  6. Cleanup and Archival
  7. Confirm Completion

What it can do on your machine

Read from SKILL.md and the folder at commit 36ac9d7. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are yaml).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Knowledge Consolidation loads about 2.9k tokens when it runs, and up to ~5.9k if it reads all its reference files. Until then it costs about 24 tokens; SKILL.md has 1,321 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~24
When it runs · the whole SKILL.md, loaded when a task matches
~2.9k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~5.9k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from huytieu/COG-second-brain at commit 36ac9d7, republished under its MIT licence (© huytieu). 1,321 words, ~2,910 tokens.

Download SKILL.mdSave it as .claude/skills/knowledge-consolidation/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
knowledge-consolidation
description
Build frameworks from scattered insights across all braindumps and notes
roles
all

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, use the consolidated-knowledge template in references/templates.md.

Save to: 05-knowledge/consolidated/[framework-name]-framework.md

Create New Frameworks

For newly identified frameworks, use the new-framework template in references/templates.md.

Save to: 05-knowledge/consolidated/[framework-name]-framework.md

Update Pattern Documentation

Document the pattern using the pattern template in references/templates.md.

Save to: 05-knowledge/patterns/pattern-[name].md

Create Timeline Entries

Build the timeline entry using the thinking-evolution template in references/templates.md.

Save to: 05-knowledge/timeline/[topic]-evolution-YYYY-MM.md

5. Generate Consolidation Report

Create the master consolidation document using the report template in references/templates.md.

Save to: 05-knowledge/consolidated/consolidation-YYYY-MM-DD.md

6. Cleanup and Archival

Mark processed braindumps: Update frontmatter in processed braindumps:

yaml
status: "consolidated"
consolidated_in: "[[consolidation-YYYY-MM-DD]]"
consolidated_date: "YYYY-MM-DD"

Archive outdated content: Move superseded frameworks or insights to: 00-inbox/archive/[filename]-archived-YYYY-MM-DD.md

Add note explaining why archived and what supersedes it.

Maintain clean knowledge base:

  • Remove redundancy while preserving important context
  • Update cross-references
  • Fix broken links
  • Ensure consistent tagging
7. Confirm Completion

After consolidation:

  • Show user: "Knowledge consolidation complete! Processed [X] documents"
  • Highlight: "[X] frameworks updated, [X] new frameworks created"
  • Show: "Consolidation report saved to [file path]"
  • Suggest reviewing key frameworks created/updated
  • Offer to explain any specific framework in detail
Show full SKILL.md (617 more words)Show less

Loop Engineering

Consolidation is a loop-until-dry extraction with a completeness critic, not a single scan. See .claude/skills/loop-engineering/SKILL.md for the shared vocabulary.

The loop: scan a batch of in-scope documents → extract themes, patterns, and candidate framework principles → run the completeness critic ("any in-scope doc not yet read? any theme recurring across N+ docs that no framework captures yet?") → if the critic surfaces something new, run another extraction pass → stop when 2 passes in a row surface nothing new (dry). In agent_mode: team, the first scan fans out as one worker per domain (personal / professional / per-project / briefs); each returns its conclusions only, and a synthesis pass merges them.

The verifier (deterministic where it can be):

  • Traceability: every framework principle links at least one source document. A principle with no [[source]] is dropped, not published. This is mechanical and is COG's verification-first rule for consolidation.
  • Coverage: every in-scope document ends marked status: "consolidated" with a consolidated_in backlink.
  • Dedup: before creating a framework, check 05-knowledge/consolidated/ so an existing framework is updated, not duplicated.
  • The completeness critic ("did we miss a theme?") is the one judgment-based check; keep it explicit and evidence-linked.

Termination conditions (layered):

  • Dry: K=2 consecutive passes find no new theme or document.
  • Coverage complete: all in-scope documents marked consolidated.
  • Hard cap: a max number of extraction passes, so a noisy corpus cannot loop forever.

Patterns: loop-until-dry (the spine) + plan-execute-verify (each pass) + orchestrator-workers (team-mode domain scans) + completeness critic.

In-loop context: write the consolidation report incrementally and dedup new themes against the running set, not against the conversation. Externalizing to the report file is what keeps a large corpus from overflowing the window.

Consolidation Guidelines

Quality Over Quantity
  • Don't force insights that aren't mature enough
  • Let patterns emerge naturally from evidence
  • Be patient with incomplete thinking
  • Quality frameworks require time and evidence
  • Mark frameworks as "emerging" vs "working" vs "stable"
Preserve Nuance
  • Don't over-simplify complex insights
  • Maintain important context and conditions
  • Note when frameworks have limitations
  • Preserve contradictions that haven't resolved yet
  • Acknowledge uncertainty explicitly
Maintain Traceability
  • Always link back to source documents
  • Show evidence trail for frameworks
  • Document evolution of thinking
  • Enable future validation or revision
  • Make it easy to audit framework claims
Living Documents
  • Frameworks should evolve with new insights
  • Regular updates better than perfect first draft
  • Clear status indicators (emerging/working/stable)
  • Encourage iteration and refinement
  • Version history through Git

Analysis Techniques Reference

Pattern Detection Methods
  1. Frequency Analysis: Count mentions, cluster topics
  2. Temporal Clustering: Group by time, track evolution
  3. Domain Correlation: Cross-domain connections
  4. Contradiction Analysis: Identify conflicts, track resolution
  5. Energy Pattern Detection: Emotional and practical patterns
Framework Synthesis Process
  1. Identify Core Principles: Extract fundamental truths
  2. Test Against Evidence: Validate with sources
  3. Define Boundaries: Establish applicability
  4. Create Applications: Develop use cases
  5. Document Evolution: Track development over time
Timeline Construction Method
  1. Mark Inflection Points: When thinking shifted
  2. Identify Catalysts: What triggered changes
  3. Document Evolution: How understanding developed
  4. Extract Learnings: What evolution teaches

Success Metrics

  • Completeness: All relevant insights processed
  • Coherence: Frameworks logically consistent
  • Traceability: Clear links to source material
  • Actionability: Frameworks applicable to decisions
  • Evolution: Documented thinking progression
  • User Value: Frameworks actually used in practice

Common Use Cases

  • Weekly Consolidation: Process week's insights into patterns
  • Monthly Framework Development: Build strategic frameworks
  • Quarterly Strategic Synthesis: Big-picture consolidation
  • Annual Knowledge Base Cleanup: Maintain quality and relevance
  • Pre-Decision Framework Consultation: Apply frameworks to major decisions
  • Project Retrospective: Extract learnings for frameworks

Philosophy

The knowledge consolidation skill embodies COG's self-evolving intelligence:

  • Transforms scattered thoughts into strategic frameworks
  • Honors the evolution of thinking over time
  • Builds "single source of truth" living documents
  • Maintains traceability and evidence-based reasoning
  • Creates actionable knowledge for better decision-making
  • Respects nuance while seeking patterns
  • Values iteration and continuous refinement

© huytieu, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file (references) in skills/knowledge-consolidation of huytieu/COG-second-brain.

  • SKILL.md
  • references/templates.md

Open the folder on GitHubat commit 36ac9d7

Compare with similar skills

Knowledge Consolidation next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Knowledge Consolidation compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Knowledge Consolidation this skillhuytieu/COG-second-brain1.3k—~2.9kAutomated safety check: PassMIT
Ontology1mancompany/OneManCompany4412 repos~1.5kAutomated safety check: PassApache-2.0
Open Knowledge Write Skillinkeep/open-knowledge4.4k—~3.7kAutomated safety check: PassGPL-3.0
Auditpricklywiggles/niamos192—~1.4kAutomated safety check: PassNone
Joplinalondmnt/joplin-mcp173—~897Automated safety check: PassMIT
Guideline Writingalfadur7/llm-wiki-newsroom172—~2.4kAutomated safety check: PassMIT

Similar skills

  • Ontology

    1mancompany/OneManCompany

    Typed knowledge graph for structured agent memory and composable skills.

    441 GitHub starsUsed in 2 repos~1.5k tokens
    Knowledge ManagementAuto-check passed
  • Open Knowledge Write Skill

    inkeep/open-knowledge

    A skill your agent uses when the user wants to create, author, write, or design a new Agent Skill (a SKILL.md) — for OpenKnowledge or for their editors — including requests like 'help me write a…

    4.4k GitHub stars~3.7k tokensUpdated today
    Knowledge ManagementAuto-check passed
  • Audit

    pricklywiggles/niamos

    Scan this Obsidian vault for content that's drifted from the conventions in CLAUDE.md (status↔folder drift, missing required fields, naming violations, stale active items, frontmatter health issues…

    192 GitHub stars~1.4k tokensUpdated 3 mo ago
    Knowledge ManagementAuto-check passed
  • Joplin

    alondmnt/joplin-mcp

    Orchestration guidance for Joplin note, notebook, and tag management tools

    173 GitHub stars~897 tokensUpdated 27 days ago
    Knowledge ManagementAuto-check passed
  • Guideline Writing

    alfadur7/llm-wiki-newsroom

    Guideline-authoring craft for instruction SoTs (.claude/ guides, CLAUDE.md, plan files) — operative rules vs recital, MUST/SHOULD/MAY force tiers, pruning, bloat control, blind review protocol…

    172 GitHub stars~2.4k tokensUpdated 4 days ago
    Knowledge ManagementAuto-check passed
  • Brief

    Fergana-Labs/stash

    Brief the user on what they saved in a period — the thread running through it, not a list.

    335 GitHub stars~524 tokensUpdated today
    Knowledge ManagementAuto-check passed

More from huytieu/COG-second-brain

All 37 skills in this repo
  • Voice Baseline

    huytieu/COG-second-brain

    Measure your own writing corpus for the words and sentence shapes you over-use, so an agent writing in your voice stops amplifying your tics into a style.

    1.3k GitHub stars~957 tokensUpdated 7 days ago
    Auto-check passed
  • Daily Journal

    huytieu/COG-second-brain

    A passive daily work journal that Claude keeps FOR you so you never have to write it yourself.

    1.3k GitHub stars~1.3k tokensUpdated 7 days ago
    Auto-check passed
  • Editorial Illustrations

    huytieu/COG-second-brain

    Generate meaning-carrying editorial data-illustrations in the monotykamary / Linear aesthetic (near-black grayscale, Inter display + mono labels, hairline framed figures) with a single coral accent.

    1.3k GitHub stars~2.4k tokensUpdated 7 days ago
    Auto-check passed
  • Loop Engineering

    huytieu/COG-second-brain

    Shared loop-engineering reference for COG skills - the agent loop, deterministic verifiers, termination conditions, in-loop context management, and named patterns.

    1.3k GitHub stars~1.5k tokensUpdated 7 days ago
    Auto-check passed
  • Release Video

    huytieu/COG-second-brain

    Turn a product release (the list of shipped items plus real screen recordings) into a motion recap video and one explained demo per feature, with sound effects tied to on-screen motion and a…

    1.3k GitHub stars~1.7k tokensUpdated 7 days ago
    Auto-check passed
  • Onboarding

    huytieu/COG-second-brain

    Personalize COG for your workflow - creates profile, interests, and watchlist files with guided setup (run this first!)

    1.3k GitHub starsUsed in 1 repo~3.1k tokens
    Auto-check passed

Questions about Knowledge Consolidation

What does Knowledge Consolidation do?

Build frameworks from scattered insights across all braindumps and notes. Knowledge Consolidation is an agent skill from huytieu/COG-second-brain.

When should I use Knowledge Consolidation?

Knowledge Consolidation fits situations like: knowledge Management work in your project.

How do I install Knowledge Consolidation in Claude Code?

Run `npx skills add huytieu/COG-second-brain --skill knowledge-consolidation -a claude-code`. Or copy the skill folder (skills/knowledge-consolidation in huytieu/COG-second-brain) into .claude/skills/knowledge-consolidation in your project. Claude Code loads it when a task matches its description.

How do I install Knowledge Consolidation in Codex?

Run `npx skills add huytieu/COG-second-brain --skill knowledge-consolidation -a codex`. Or copy the skill folder (skills/knowledge-consolidation in huytieu/COG-second-brain) into .agents/skills/knowledge-consolidation in your project. Codex loads it when a task matches its description.

Can I use Knowledge Consolidation in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add huytieu/COG-second-brain --skill knowledge-consolidation -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/knowledge-consolidation, .gemini/skills/knowledge-consolidation, .github/skills/knowledge-consolidation and .opencode/skills/knowledge-consolidation in your project.

What does Knowledge Consolidation need to run?

SKILL.md names no scripts, command-line tools or credentials: Knowledge Consolidation is instructions for the agent only.

Does Knowledge Consolidation access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Knowledge Consolidation safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Knowledge Consolidation use?

Knowledge Consolidation is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Knowledge Consolidation use?

About 2.9k tokens (SKILL.md is roughly 12k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 3k tokens, read only when the agent opens those files.

What are the alternatives to Knowledge Consolidation?

Skills that share tags, products or a category with Knowledge Consolidation: Ontology (1mancompany/OneManCompany, 441 stars), Open Knowledge Write Skill (inkeep/open-knowledge, 4.4k stars), Audit (pricklywiggles/niamos, 192 stars) and Joplin (alondmnt/joplin-mcp, 173 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Knowledge Consolidation?

huytieu (a GitHub user) maintains it in huytieu/COG-second-brain, which has 1,267 GitHub stars. The repository holds 37 skills in this directory. The repository was last updated on October 2, 2026.

Source: huytieu/COG-second-brain on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.