cog-second-brain
Self-evolving second brain with 43 AI agent skills, 10 agents, and people CRM. Closed-loop harness release: a V-model verification lifecycle (spec to evidence, criterion-traced checkpoints), read-only verifier agents that observe artifacts instead of trusting worker summaries, risk lanes, multi-session ultragoals with a north-star acceptance gate, plus craft skills for writing, visual work, and a paired anti-slop design system for marketing and product UI. Inspired by Garry Tan's gstack specialist sessions, gbrain knowledge patterns, and dwarves-kit closed-loop execution. Works with Claude Code, Antigravity, Cursor, Kiro, Gemini CLI, Codex, and any markdown-reading agent.
Safety scan
A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.
Badge for your README
Markdown
[](/listings/huytieu-cog-second-brain)HTML
<a href="/listings/huytieu-cog-second-brain"><img src="/api/listings/huytieu-cog-second-brain/badge.svg" alt="findsafeskills safety rating" /></a>Install
Install instructions from the README
As written by the repo's author. findsafeskills has not verified these steps.
**1. Clone & enter the repo:**
git clone https://github.com/huytieu/COG-second-brain.git cd COG-second-brain
**2. Run onboarding in your agent:**
| Agent | Command | How it finds skills | |---|---|---| | Claude Code | `code .` → "Run onboarding" | `.claude/skills/` | | Antigravity | Open folder → "Run onboarding" | `.agents/skills/` + `.agents/rules/cog.md` | | Cursor | Open folder → "Run onboarding" | `.cursor-plugin/` + `.cursorrules` | | Kiro | Open folder → "setup COG" | `.kiro/powers/` | | Gemini CLI | `gemini` → `/onboarding` | `GEMINI.md` + `.gemini/commands/` | | OpenAI Codex | `codex` → "Run onboarding" | `AGENTS.md` | | Other agents | Point at `AGENTS.md` → "Run onboarding" | `AGENTS.md` |
**Or install via [skills.sh](https://skills.sh):**
npx skills add huytieu/COG-second-brain
Done — COG is personalized and ready in ~2 minutes. See [SETUP.md](SETUP.md) for optional config (Git sync, iCloud, Obsidian Tasks, etc.).
What was scanned
The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.
.claude-plugin/plugin.json · Manifest · 367 lines
View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)
- {
- "name": "cog-second-brain",
- "version": "3.16.0",
- "description": "Self-evolving second brain with 43 AI agent skills, 10 agents, and people CRM. Closed-loop harness release: a V-model verification lifecycle (spec to evidence, criterion-traced checkpoints), read-only verifier agents that observe artifacts instead of trusting worker summaries, risk lanes, multi-session ultragoals with a north-star acceptance gate, plus craft skills for writing, visual work, and a paired anti-slop design system for marketing and product UI. Inspired by Garry Tan's gstack specialist sessions, gbrain knowledge patterns, and dwarves-kit closed-loop execution. Works with Claude Code, Antigravity, Cursor, Kiro, Gemini CLI, Codex, and any markdown-reading agent.",
- "author": {
- "name": "Huy Tieu",
- "url": "https://github.com/huytieu"
- },
- "homepage": "https://github.com/huytieu/COG-second-brain",
- "repository": {
- "type": "git",
- "url": "https://github.com/huytieu/COG-second-brain"
- },
- "license": "MIT",
- "keywords": [
- "second-brain",
- "knowledge-management",
- "obsidian",
- "ai-agents",
- "productivity",
- "garry-tan",
- "gstack",
- "gbrain",
- "worker-agents",
- "people-crm",
- "braindump",
- "daily-brief",
- "team-intelligence",
- "claude-code",
- "antigravity",
- "cursor",
- "kiro",
- "gemini-cli",
- "codex",
- "agentic",
- "self-evolving",
- "personal-intelligence",
- "note-taking",
- "specialist-sessions",
- "loop-engineering",
- "agent-loop",
- "memory-hygiene",
- "runtime-trust",
- "content-factory",
- "verification",
- "skill-distillation",
- "v-model",
- "closed-loop",
- "verification-harness",
- "evidence-ledger",
- "ultragoal",
- "risk-lanes",
- "verifier-agents",
- "retrospective",
- "no-ai-slop",
- "data-viz",
- "design-systems",
- "ui-ux",
- "anti-slop",
- "product-design"
- ],
- "category": "productivity",
- "tags": [
- "knowledge-management",
- "obsidian",
- "second-brain",
- "ai-agents",
- "productivity",
- "garry-tan",
- "gstack",
- "gbrain",
- "worker-agents",
- "people-crm",
- "claude-code",
- "cursor",
- "specialist-sessions"
- ],
- "skills": [
- {
- "name": "onboarding",
- "path": ".claude/skills/onboarding/SKILL.md",
- "description": "Personalize COG for your workflow - creates profile, interests, and watchlist files (run this first!)"
- },
- {
- "name": "braindump",
- "path": ".claude/skills/braindump/SKILL.md",
- "description": "Quick capture of raw thoughts with intelligent domain classification and competitive intelligence extraction"
- },
- {
- "name": "daily-brief",
- "path": ".claude/skills/daily-brief/SKILL.md",
- "description": "Generate personalized news intelligence with verified sources (7-day freshness requirement)"
- },
- {
- "name": "weekly-checkin",
- "path": ".claude/skills/weekly-checkin/SKILL.md",
- "description": "Cross-domain pattern analysis and strategic reflection for weekly review"
- },
- {
- "name": "knowledge-consolidation",
- "path": ".claude/skills/knowledge-consolidation/SKILL.md",
- "description": "Build frameworks from scattered insights across all braindumps and notes"
- },
- {
- "name": "url-dump",
- "path": ".claude/skills/url-dump/SKILL.md",
- "description": "Quick capture URLs with automatic content extraction, insights, and categorization into knowledge booklets"
- },
- {
- "name": "loop-engineering",
- "path": ".claude/skills/loop-engineering/SKILL.md",
- "description": "Shared loop-engineering reference for iterative skills - the agent loop, deterministic verifiers, termination conditions, in-loop context management, and named patterns"
- },
- {
- "name": "team-brief",
- "path": ".claude/skills/team-brief/SKILL.md",
- "description": "Cross-reference GitHub, Linear, Slack, PostHog, meetings, and braindumps into a daily team intelligence brief with Linear sync-back"
- },
- {
- "name": "meeting-transcript",
- "path": ".claude/skills/meeting-transcript/SKILL.md",
- "description": "Process meeting recordings into structured decisions, action items, and team dynamics"
- },
- {
- "name": "comprehensive-analysis",
- "path": ".claude/skills/comprehensive-analysis/SKILL.md",
- "description": "Deep 7-day analysis for weekly reviews, board prep, or strategic planning"
- },
- {
- "name": "scout",
- "path": ".claude/skills/scout/SKILL.md",
- "description": "Triage a URL or tool (verify, classify, and check fit) before deciding whether to save it"
- },
- {
- "name": "update-cog",
- "path": ".claude/skills/update-cog/SKILL.md",
- "description": "Check for and apply upstream COG framework updates without touching personal content"
- },
- {
- "name": "memory-hygiene",
- "path": ".claude/skills/memory-hygiene/SKILL.md",
- "description": "Periodic trust sweep of persistent memory - re-verify environment-dependent claims, stamp last_verified + confidence, propose archiving drifted entries"
- },
- {
- "name": "content-factory",
- "path": ".claude/skills/content-factory/SKILL.md",
- "description": "Autonomous content pipeline - scout announcements, triage by trend momentum and personal angle, produce and publish with ledger dedup, volume caps, and post-condition verification"
- },
- {
- "name": "auto-research",
- "path": ".claude/skills/auto-research/SKILL.md",
- "description": "Deep strategic research engine with parallel research threads and actionable analysis"
- },
- {
- "name": "create-user-story",
- "path": ".claude/skills/create-user-story/SKILL.md",
- "description": "Create user stories with duplicate checking across Linear, GitHub Issues, or Jira"
- },
- {
- "name": "generate-prd",
- "path": ".claude/skills/generate-prd/SKILL.md",
- "description": "Draft PRDs with approval gate before publishing to Confluence or Notion"
- },
- {
- "name": "generate-release-notes",
- "path": ".claude/skills/generate-release-notes/SKILL.md",
- "description": "Generate release notes from GitHub milestones, Linear cycles, or manual input"
- },
- {
- "name": "export-open-issues",
- "path": ".claude/skills/export-open-issues/SKILL.md",
- "description": "Audit and export open issues from any project tracker"
- },
- {
- "name": "publish-to-confluence",
- "path": ".claude/skills/publish-to-confluence/SKILL.md",
- "description": "Publish vault markdown files to Confluence"
- },
- {
- "name": "update-knowledge-base",
- "path": ".claude/skills/update-knowledge-base/SKILL.md",
- "description": "Maintain product knowledge base from releases and feature updates"
- },
- {
- "name": "closed-loop",
- "path": ".claude/skills/closed-loop/SKILL.md",
- "description": "V-model execute pipeline - plan, build, component verify, integration verify, acceptance; the worker never grades its own homework and every evidence row traces to an AC-n criterion"
- },
- {
- "name": "ultragoal",
- "path": ".claude/skills/ultragoal/SKILL.md",
- "description": "Run a goal too big for one session as a chain of phases, each its own full closed-loop run, with cross-session state and a final north-star acceptance gate"
- },
- {
- "name": "harvest",
- "path": ".claude/skills/harvest/SKILL.md",
- "description": "Capture durable session learnings, stage them for human promotion into knowledge, and propose skill/CLAUDE.md patches - never writes durable knowledge unapproved"
- },
- {
- "name": "retro",
- "path": ".claude/skills/retro/SKILL.md",
- "description": "CP-7 retrospective - audit checkpoints, evidence quality, and action items; closes the V-model cycle and feeds the next run"
- },
- {
- "name": "review-cockpit",
- "path": ".claude/skills/review-cockpit/SKILL.md",
- "description": "One living review document per multi-item session - cockpit header plus per-item cards you approve or request changes on directly in the doc"
- },
- {
- "name": "no-ai-slop",
- "path": ".claude/skills/no-ai-slop/SKILL.md",
- "description": "Edit drafts into sharper, more human writing while preserving personal voice, or detect AI-slop patterns without rewriting"
- },
- {
- "name": "editorial-illustrations",
- "path": ".claude/skills/editorial-illustrations/SKILL.md",
- "description": "Generative guide for meaning-carrying editorial data-illustrations - teaches the claim-to-geometry method, renders self-contained theme-aware HTML/SVG figures"
- },
- {
- "name": "data-forms",
- "path": ".claude/skills/data-forms/SKILL.md",
- "description": "Pick the right form for a dataset so the finding lands in three seconds - 20+ chart and diagram forms with when-to-use, failure modes, and encoding discipline"
- },
- {
- "name": "museum-art",
- "path": ".claude/skills/museum-art/SKILL.md",
- "description": "Source authentic high-res public-domain artwork from museum open-access APIs instead of AI-generated or generic-stock imagery"
- },
- {
- "name": "daily-journal",
- "path": ".claude/skills/daily-journal/SKILL.md",
- "description": "A passive daily work journal the agent keeps for you - appends entries after meaningful work, runs a guided reflection on request"
- },
- {
- "name": "taste-skill",
- "path": ".claude/skills/taste-skill/SKILL.md",
- "description": "Anti-slop frontend skill for landing pages, portfolios, and redesigns - reads the brief, states a design read, and ships interfaces that do not look templated"
- },
- {
- "name": "product-ui-taste",
- "path": ".claude/skills/product-ui-taste/SKILL.md",
- "description": "Anti-slop skill for dense product surfaces (dashboards, tables, forms, wizards, admin consoles) - frame-first, correct at every edge case real data produces"
- },
- {
- "name": "slop-gate",
- "description": "Refuse AI-slop tells in anything about to be written, published, or sent; runs in CI or as a hook",
- "path": ".claude/skills/slop-gate/SKILL.md"
- },
- {
- "name": "voice-baseline",
- "description": "Measure the words and sentence shapes you over-use so an agent stops amplifying your tics",
- "path": ".claude/skills/voice-baseline/SKILL.md"
- },
- {
- "name": "release-video",
- "path": ".claude/skills/release-video/SKILL.md",
- "description": "Turn a product release into a motion recap video and explained per-feature demos: deterministic HTML scenes, sound effects tied to motion, music composed to the timeline"
- },
- {
- "name": "blog-publish",
- "path": ".claude/skills/blog-publish/SKILL.md",
- "description": "Write and publish a post to your own static blog: TL;DR, ASCII art, markdown twin for agents, deploy, and social distribution"
- },
- {
- "name": "feature-doc",
- "path": ".claude/skills/feature-doc/SKILL.md",
- "description": "Document a shipped feature from the live app: real screenshots and a screen recording, a docs article with how-to and use cases, verified before publish"
- },
- {
- "name": "release-comms",
- "path": ".claude/skills/release-comms/SKILL.md",
- "description": "Turn a deployment runsheet and a GitHub milestone into a customer release note with real media, docs updates, and a Slack announcement draft"
- },
- {
- "name": "social-media-kit",
- "path": ".claude/skills/social-media-kit/SKILL.md",
- "description": "Attach native media (teaser video, GIF, card images) to every social post, with per-platform upload steps"
- },
- {
- "name": "terminal-replica",
- "path": ".claude/skills/terminal-replica/SKILL.md",
- "description": "Reproduce your real terminal and CLI agents (Claude Code, Codex, Gemini CLI) faithfully in graphics and video frames"
- },
- {
- "name": "vector-cover",
- "path": ".claude/skills/vector-cover/SKILL.md",
- "description": "Flat vector editorial cover illustrations in HTML and SVG, rendered to a 2400x960 PNG with headless Chrome"
- },
- {
- "name": "youtube-video-kit",
- "path": ".claude/skills/youtube-video-kit/SKILL.md",
- "description": "YouTube packaging: thumbnail, animated opening title, ElevenLabs music bed, and the upload metadata bundle"
- }
- ],
- "metadata": {
- "pluginRoot": ".",
- "architecture": "multi-agent-skill-pack",
- "features": [
- "Self-evolving intelligence with pattern recognition",
- "Self-healing system with auto-updating cross-references",
- "Verification-first approach (no AI hallucinations)",
- "Privacy-first architecture with strict domain separation",
- "Plain text markdown files (no database, no vendor lock-in)",
- "Multi-device sync via iCloud (iPhone, iPad, Mac)",
- "Git version control for tracking thinking evolution",
- "Agent-surface validator for manifest/docs consistency",
- "Worker agent architecture with model routing (Sonnet workers, Opus lead)",
- "People CRM with tiered enrichment and evidence-based profiles",
- "Runtime trust: memory-hygiene sweeps with last_verified + confidence stamps",
- "Skill post-condition checks - observe the mutated artifact before reporting success",
- "Skill distillation pattern: explore once with a strong model, execute cheap with a small one",
- "V-model closed loop: decompose to falsifiable criteria, verify with evidence traced back to each one",
- "Read-only verifier agents (task-verifier, integration-verifier) that observe artifacts, not worker summaries",
- "Risk lanes: ceremony scales with blast radius instead of applying uniformly",
- "Ultragoals: multi-session goals with per-phase verification and a final north-star acceptance gate",
- "Cross-model flagship gate - a different model family catches a different error class",
- "Paired anti-slop design skills: taste-skill owns marketing surfaces, product-ui-taste owns dense product UI"
- ],
- "requirements": {
- "obsidian": "Recommended for markdown file management",
- "git": "Optional but recommended for version control and safe updates",
- "claudeCode": "Recommended for the full 33-skill native experience",
- "kiro": "Optional - ships 7 native core powers",
- "geminiCli": "Optional - ships 7 native core commands",
- "agentsMd": "Universal fallback surface for Codex and other markdown-reading agents"
- },
- "installation": {
- "quickStart": "Clone the repo, cd into COG-second-brain, then run onboarding in your agent of choice",
- "setupTime": "2-5 minutes",
- "onboardingTime": "2 minutes",
- "validation": "Run ./scripts/validate-agent-surface.sh before publishing or after framework updates"
- },
- "directoryStructure": {
- ".claude/skills": "33 Claude Code skills (full surface)",
- ".claude/agents": "10 agent definitions - 6 workers plus 4 read-only verifiers",
- ".claude/roles": "7 role packs for personalized skill and integration recommendations",
- ".kiro/powers": "7 Kiro powers (core workflows)",
- ".gemini/commands": "7 Gemini CLI commands (core workflows)",
- ".gemini/skills": "Detailed Gemini command playbooks",
- "AGENTS.md": "Universal command surface for Codex and other agents",
- "00-inbox": "Temporary processing area with profile and interests files",
- "01-daily": "Daily briefs and check-ins",
- "02-personal": "Personal domain (strict privacy)",
- "03-professional": "Professional domain with competitive watchlist",
- "04-projects": "Project-specific tracking",
- "05-knowledge": "Consolidated insights and patterns",
- ".claude/lib": "Harness shell helpers (checkpoint recorder, risk-lane classifier)",
- "WORKFLOW.md": "The V-model lifecycle: checkpoints, gate classes, evidence contract"
- },
- "skillArchitecture": {
- "type": "agent-skills",
- "skills": 33,
- "workerAgents": 10,
- "rolePacks": 7,
- "invocation": "model-invoked",
- "progressiveDisclosure": true,
- "nativeSurfaces": {
- "claudeCode": 33,
- "antigravity": 33,
- "kiro": 7,
- "geminiCli": 7,
- "agentsMd": 33
- },
- "description": "Self-contained skills with worker delegation and a read-only verification layer, full Claude Code and Antigravity surfaces, core native Kiro/Gemini surfaces, and AGENTS.md as the universal fallback"
- }
- }
- }
README.md · README · 341 lines
View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)
- # COG: The Agentic Second Brain That Actually Self-Evolves
- **Cognition + Obsidian + Git** — A self-evolving second brain powered by AI agents, markdown files, and version control. No database, no vendor lock-in — just `.md` files that think.
- [Quick Start](#quick-start) | [Skills](#skills) | [Features](#features-at-a-glance) | [FAQ](#faq) | [SETUP.md](SETUP.md)
- > Works with [Claude Code](https://claude.ai/download) • Antigravity • [Cursor](https://cursor.com/) • [Kiro](https://kiro.dev/) • [Gemini CLI](https://github.com/google-gemini/gemini-cli) • [OpenAI Codex](https://github.com/openai/codex) • any AI that reads markdown
- >
- > Inspired by [Garry Tan's gstack](https://github.com/garrytan/gstack) and [gbrain](https://github.com/garrytan/gbrain)
- ```mermaid
- graph LR
- A[You] -- natural language --> B[AI Agent]
- B -- runs --> C[43 Skills]
- C -- delegates to --> W[6 Workers]
- C -- verified by --> V[4 Read-Only Verifiers]
- C -- reads & writes --> D[.md Files]
- W -- reads & writes --> D
- V -- observes --> D
- C -- syncs with --> G[GitHub / Linear / Slack / PostHog]
- D --> E[Git]
- D --> F[iCloud]
- ```
- ## Quick Start
- **1. Clone & enter the repo:**
- ```bash
- git clone https://github.com/huytieu/COG-second-brain.git
- cd COG-second-brain
- ```
- **2. Run onboarding in your agent:**
- | Agent | Command | How it finds skills |
- |---|---|---|
- | Claude Code | `code .` → "Run onboarding" | `.claude/skills/` |
- | Antigravity | Open folder → "Run onboarding" | `.agents/skills/` + `.agents/rules/cog.md` |
- | Cursor | Open folder → "Run onboarding" | `.cursor-plugin/` + `.cursorrules` |
- | Kiro | Open folder → "setup COG" | `.kiro/powers/` |
- | Gemini CLI | `gemini` → `/onboarding` | `GEMINI.md` + `.gemini/commands/` |
- | OpenAI Codex | `codex` → "Run onboarding" | `AGENTS.md` |
- | Other agents | Point at `AGENTS.md` → "Run onboarding" | `AGENTS.md` |
- **Or install via [skills.sh](https://skills.sh):**
- ```bash
- npx skills add huytieu/COG-second-brain
- ```
- Done — COG is personalized and ready in ~2 minutes. See [SETUP.md](SETUP.md) for optional config (Git sync, iCloud, Obsidian Tasks, etc.).
- ## Agent Support Matrix
- COG ships a **full Claude Code surface**, a **full Antigravity surface**, plus **core native surfaces** for Kiro and Gemini CLI, with `AGENTS.md` as the universal fallback for Codex and other markdown-reading agents.
- | Surface | Current support | Notes |
- |---|---|---|
- | Claude Code | 33 native skills + 10 agents (6 workers + 4 verifiers) | Full first-class surface |
- | Antigravity | 43 skills + 10 agents (pointer-stub format) | Full surface — thin stubs in `.agents/` delegate to the `.claude/` playbooks, which stay authoritative |
- | [Agent Plugins](https://agent-plugins.org) standard | Root `plugin.json` + `skills/` (43 skills) | Spec 1.0.0 conformant; any standard-aware client loads COG as a plugin |
- | Cursor | Plugin manifest + rules | `.cursor-plugin/plugin.json` + `.cursorrules` |
- | Kiro | 7 native powers | Core workflows today |
- | Gemini CLI | 7 native commands | Core workflows today |
- | `AGENTS.md` | 33 documented commands | Universal fallback for Codex and other agents |
- Before publishing or updating framework files, run `./scripts/validate-agent-surface.sh` to catch drift between manifests, docs, and shipped files. See [docs/AGENT-SUPPORT.md](docs/AGENT-SUPPORT.md) for the detailed support matrix and contributor rules.
- ## Skills
- ### Core Skills (Personal Knowledge)
- | Skill | What it does | Try saying... |
- |---|---|---|
- | **onboarding** | Personalize COG for your workflow (run first!) | "Run onboarding" |
- | **braindump** | Capture raw thoughts with intelligent classification | "I need to braindump" |
- | **daily-brief** | Verified news intelligence (7-day freshness) | "Give me my daily brief" |
- | **url-dump** | Save URLs with auto-extracted insights | "Save this URL" |
- | **weekly-checkin** | Cross-domain pattern analysis | "Weekly review" |
- | **knowledge-consolidation** | Build frameworks from scattered notes | "Consolidate my knowledge" |
- | **update-cog** | Update framework files without touching your content | "Update COG" |
- | **memory-hygiene** | Trust sweep of persistent memory — re-verify claims against the live environment, stamp `last_verified` + confidence | "Audit my memories" |
- ### Team Intelligence Skills (for Product & Engineering Leads)
- | Skill | What it does | Try saying... |
- |---|---|---|
- | **team-brief** | Cross-reference GitHub + Linear + Slack + PostHog into a daily team intelligence brief with two-way Linear sync-back | "Team brief" / "What did we ship?" |
- | **meeting-transcript** | Process meeting recordings into structured decisions, action items, and team dynamics | "Process this meeting" |
- | **comprehensive-analysis** | Deep 7-day analysis for weekly reviews, board prep, or strategic planning (~8-12 min) | "Weekly analysis" / "Board prep" |
- ### PM Workflow Skills (for Product Managers)
- | Skill | What it does | Try saying... |
- |---|---|---|
- | **create-user-story** | Create user stories with duplicate checking across Linear, GitHub Issues, or Jira | "Create a user story for..." |
- | **generate-prd** | Draft PRDs with approval gate before publishing to Confluence/Notion | "Generate a PRD for..." |
- | **generate-release-notes** | Generate release notes from GitHub milestones, Linear cycles, or manual input | "Generate release notes for v2.1" |
- | **export-open-issues** | Audit and export open issues from any tracker into a structured vault summary | "Export open issues" |
- | **publish-to-confluence** | Publish any vault markdown file to Confluence | "Publish this to Confluence" |
- | **update-knowledge-base** | Maintain product knowledge base from releases, features, and project changes | "Update the knowledge base with v2.1 changes" |
- | **release-comms** | Turn a runsheet and a milestone into a release note with real media, docs updates, and a Slack draft | "Cover today's release" |
- | **feature-doc** | Drive the live app, capture screenshots and a recording, and write the docs article | "Write the doc for issue #123" |
- > **PM Workflow:** These skills form a complete product management lifecycle: **Research** (`/auto-research`) → **PRD** (`/generate-prd`) → **Stories** (`/create-user-story`) → Development → **Release Notes** (`/generate-release-notes`) → **Knowledge Base** (`/update-knowledge-base`). Use `/export-open-issues` for audits and `/publish-to-confluence` to share externally.
- ### Strategic Research
- | Skill | What it does | Try saying... |
- |---|---|---|
- | **auto-research** | Deep strategic research engine — decomposes questions into parallel research threads with multiple agents | "Research the future of AI testing tools" |
- ### Content Creation
- | Skill | What it does | Try saying... |
- |---|---|---|
- | **content-factory** | Autonomous content pipeline — scout announcements, triage by trend momentum + your unique angle, publish with ledger dedup, hard volume caps, and screenshot-verified posting | "Run the content factory" |
- | **blog-publish** | Write and publish a post to your own blog, with a markdown twin and social distribution | "Publish this to my blog" |
- | **social-media-kit** | Teaser video, GIF, and card images for every social post | "Make the social kit for this post" |
- | **youtube-video-kit** | Thumbnail, opening title, music bed, and upload metadata | "Make a thumbnail and intro for this video" |
- ### Verification Harness
- Opt-in. Ask for one of these and work walks a **V**: decompose left into falsifiable criteria, build at the apex, verify right with evidence traced back to each criterion. Say nothing and none of it runs: ordinary work carries no checkpoints and no evidence ledger. Turn it on per request, or by default for build tasks with `verification_harness: on` in `00-inbox/MY-PROFILE.md`. Full lifecycle in [WORKFLOW.md](WORKFLOW.md).
- | Skill | What it does | Try saying... |
- |---|---|---|
- | **closed-loop** | Plan → build → component verify → integration verify → acceptance. The worker never grades its own homework; verifiers observe the artifact, not the worker's summary | "Run this through the closed loop" |
- | **ultragoal** | A goal too big for one session, run as a chain of phases with cross-session state and a north-star acceptance gate | "Track this as an ultragoal" |
- | **harvest** | Capture session learnings, stage them for approval, propose skill patches. Never writes durable knowledge unapproved | "Harvest what we learned" |
- | **retro** | Audit the run's checkpoints and *evidence quality*. A run can pass every gate on weak observations | "Retro this run" |
- | **review-cockpit** | One living doc per multi-item session: progress, per-item cards, and an approval slot you edit in place | "Set up a review cockpit" |
- ### Craft Skills (Writing & Visuals)
- | Skill | What it does | Try saying... |
- |---|---|---|
- | **no-ai-slop** | Sharpen a draft without flattening its voice, or just detect AI-slop patterns | "Make this less AI-sounding" |
- | **slop-gate** | Refuse slop tells in anything about to be written, published, or sent; runs in CI or as a hook | "Scan this before I publish" |
- | **voice-baseline** | Measure the words and shapes you over-use so an agent stops amplifying your tics | "Why do my drafts all sound the same?" |
- | **release-video** | Turn a release into a motion recap and explained per-feature demos, with sound tied to motion | "Make a video for this release" |
- | **terminal-replica** | Draw your real terminal and CLI agents in graphics and video frames | "Draw a Claude Code terminal for this post" |
- | **vector-cover** | Flat vector cover illustrations rendered to PNG | "Make a cover image for this article" |
- | **editorial-illustrations** | Claim → geometry: derive the *right* figure from what the text argues, render it as self-contained theme-aware HTML/SVG | "Make a diagram for this argument" |
- | **data-forms** | 20+ chart and diagram forms with when-to-use, failure modes, and the encoding discipline that makes any of them readable | "The bar chart is burying the point" |
- | **museum-art** | Real public-domain artwork from museum open-access APIs instead of AI-generated or stock imagery | "Find a hero image for this post" |
- | **daily-journal** | A passive work journal the agent keeps for you, plus a guided reflection on request | "Reflect on today" |
- ### Design Skills (Anti-Slop UI)
- A paired set. `taste-skill` owns first-impression surfaces, `product-ui-taste` owns surfaces people use every day. Never run both on the same component.
- | Skill | Owns | Try saying... |
- |---|---|---|
- | **taste-skill** | Landing pages, portfolios, marketing, editorial. States a "Design Read" before writing code so it stops defaulting to one house aesthetic | "Build a landing page for this" |
- | **product-ui-taste** | Dashboards, data tables, forms, wizards, settings, admin consoles. Budgets the frame in px first, then survives real data: overflow, long labels, empty/error/permission-denied states | "Build the admin table for this" |
- ### Agents (Specialist Sessions)
- COG uses a worker agent architecture inspired by [garrytan/gstack](https://github.com/garrytan/gstack) specialist sessions and [garrytan/gbrain](https://github.com/garrytan/gbrain) knowledge patterns. Workers handle data-heavy tasks cheaply (Sonnet) while the lead session does reasoning (Opus).
- | Agent | What it does | Model |
- |---|---|---|
- | **worker-data-collector** | Structured extraction from GitHub, Slack, Jira, Linear | Sonnet |
- | **worker-researcher** | Web research with source citations | Sonnet |
- | **worker-file-ops** | Vault file operations, metadata, profiles | Sonnet |
- | **worker-executor** | Pre-approved mutations (Jira, Linear, APIs) | Sonnet |
- | **worker-publisher** | Publishing to Slack, Confluence, Notion | Sonnet |
- | **brief-people-updater** | Batch-update people profiles from meetings/briefs | Sonnet |
- **Read-only verifiers** (they cannot edit files or mutate external state):
- | Agent | What it does | Checkpoint |
- |---|---|---|
- | **task-verifier** | Checks output against acceptance criteria by observing the artifact | CP-3v |
- | **integration-verifier** | Cross-task wiring and global acceptance | CP-4 |
- | **fix-agent** | Targeted fixes after a `FAIL:fixable` verdict; max 2 attempts | CP-3v retry |
- | **harvest-curator** | Shapes session learnings into adoption notes; propose-only | CP-7 |
- > Workers write results to `/tmp/` files and return only a status + path. The lead reads the file for synthesis. This eliminates slow token generation in agent output.
- >
- > Verifiers receive **paths only**, never a worker's output. Pasted context induces narrativisation: the verifier classifies the framing instead of independently reading the source.
- ### People CRM (Knowledge-Based Team Profiles)
- Track the people you work with using progressive, evidence-based profiles in `05-knowledge/people/`. Profiles auto-escalate via tiered enrichment:
- - **Tier 3 (Stub)** — 1 mention: name, role, one-line context
- - **Tier 2 (Moderate)** — 3+ mentions: executive snapshot, working style, strengths
- - **Tier 1 (Full)** — 8+ mentions or direct meeting: complete profile with all sections
- Every observation includes a source citation with confidence level. See `05-knowledge/people/README.md` for details.
- ### Role Packs (Personalized Recommendations)
- COG matches your role during onboarding to a **role pack** that prioritizes the most relevant skills and integrations for you. Available role packs: Product Manager, Engineering Lead, Engineer, Designer, Founder, Marketer — or create your own from the template.
- > **New to team skills?** These require GitHub CLI (`gh`) and work best with Linear, Slack, and PostHog MCP integrations. They degrade gracefully — start with just GitHub and add integrations over time. See [SETUP.md](SETUP.md) for configuration.
- ## The Evolution Cycle
- ```mermaid
- graph TD
- A[Daily: Braindump thoughts] --> B[Daily: News intelligence]
- A --> T[Daily: Team intelligence brief]
- M[Meetings: Process transcripts] --> T
- T -- syncs back to --> L[Linear / GitHub]
- B --> C[Weekly: Pattern analysis]
- T --> CA[Weekly: Comprehensive analysis]
- C --> D[Monthly: Knowledge consolidation]
- CA --> D
- D -- COG learns your patterns --> A
- R[Strategic: Auto-research] --> P[PM: Generate PRD]
- P --> S[PM: Create user stories]
- S -- after development --> RN[PM: Release notes]
- RN --> KB[PM: Update knowledge base]
- ```
- - **Daily capture** — braindump raw thoughts; COG classifies by domain and extracts action items
- - **Daily intelligence** — personalized news briefings with verified, sourced news
- - **Daily team brief** — cross-reference GitHub, Linear, Slack, PostHog, meetings into one brief with two-way sync
- - **Meeting processing** — extract decisions, action items, and team dynamics from transcripts
- - **Weekly reflection** — pattern analysis across all domains surfaces insights you'd miss
- - **Weekly deep dive** — comprehensive analysis for board prep, retros, and strategic planning
- - **Monthly synthesis** — scattered notes become consolidated frameworks and a knowledge base
- - **Strategic research** — deep multi-agent investigation of strategic questions with real sources
- - **PM workflow** — full product lifecycle from PRD to release notes to knowledge base updates
- ## Features at a Glance
- | | | |
- |---|---|---|
- | **Self-Evolving** — Learns your patterns, auto-organizes content, builds frameworks | **Self-Healing** — Rename files or restructure; cross-references update automatically | **Verification-First** — Sources required, 7-day freshness, confidence levels on all analysis |
- | **Privacy-First** — Local `.md` files, strict domain separation, no external servers | **Multi-Device** — iCloud sync to iPhone/iPad/Mac; Git for version history | **Obsidian Tasks** — `📅 YYYY-MM-DD` emoji format works with Tasks plugin dashboards |
- | **Garry Tan Inspired** — gstack specialist sessions + gbrain knowledge patterns | **Multi-Platform** — Listed on [skills.sh](https://skills.sh), [agentskill.sh](https://agentskill.sh), [cursor.directory](https://cursor.directory) | **Worker Agents** — Sonnet handles I/O, Opus handles thinking |
- | **Runtime Trust** — memory hygiene sweeps re-verify stored facts against the live environment | **Post-Condition Checks** — mutating skills observe the artifact before reporting success | **Skill Distillation** — [explore once, execute cheap](docs/SKILL-DISTILLATION.md) with small models |
- | **V-Model Closed Loop** — every criterion has a task on the left and an evidence row on the right | **Risk Lanes** — ceremony scales with blast radius | **Cross-Model Gate** — a different model family catches a different error class |
- ## Your Vault
- ```
- COG-second-brain/
- ├── .claude/skills/ # Claude Code skills (33)
- ├── .claude/agents/ # Worker agent definitions (6)
- ├── .claude/roles/ # Role packs (7) — personalized recommendations
- ├── .agents/ # Antigravity (agy CLI + IDE) — pointer stubs to .claude/
- ├── .kiro/powers/ # Kiro powers
- ├── .gemini/commands/ # Gemini CLI commands
- ├── AGENTS.md # Universal agent docs
- ├── CLAUDE.md # Framework instructions
- ├── 00-inbox/ # Profiles, interests, integrations
- ├── 01-daily/ # Briefs & check-ins
- ├── 02-personal/ # Personal braindumps (private)
- ├── 03-professional/ # Professional braindumps & strategy
- ├── 04-projects/ # Per-project tracking
- ├── 05-knowledge/ # Consolidated insights & patterns
- │ └── people/ # People CRM profiles
- └── 06-templates/ # Document templates
- ```
- > **Real-world results:** 120+ braindumps processed, daily briefs with 95%+ source accuracy, 5 major strategic insights discovered — zero maintenance required.
- ## Keeping COG Updated
- COG separates **framework files** (skills, docs, scripts) from **your content** (braindumps, profiles, notes). Updates never touch your personal data.
- | Method | Command |
- |---|---|
- | AI Agent (any) | "Update COG" or `/update-cog` |
- | Shell script | `./cog-update.sh` (interactive) • `--check` • `--dry-run` • `--force` |
- | Manual Git | `git fetch cog-upstream main` then checkout specific files |
- Check your version: `cat COG-VERSION`
- Validate packaged surfaces: `./scripts/validate-agent-surface.sh`
- ## FAQ
- <details><summary><strong>Why not just use Notion / Roam / Obsidian alone?</strong></summary>
- COG adds self-evolving intelligence on top. It doesn't just store — it learns, analyzes, and synthesizes insights automatically.
- </details>
- <details><summary><strong>How much does it cost?</strong></summary>
- COG is free and open-source (MIT). You only pay for your AI agent's API usage.
- </details>
- <details><summary><strong>Is my data private?</strong></summary>
- Yes. Everything is local markdown files. The AI agent's API is only called when you invoke a skill. No data stored on external servers.
- </details>
- <details><summary><strong>Can I customize or add skills?</strong></summary>
- Yes — edit any `SKILL.md` / `POWER.md` / `AGENTS.md` file. See [SETUP.md](SETUP.md) for details on creating new skills.
- </details>
- <details><summary><strong>Will updating overwrite my customizations?</strong></summary>
- No. The update process detects customized files and lets you choose per-file: keep yours, use upstream, or backup + update. Nothing is overwritten without approval.
- </details>
- <details><summary><strong>What if I don't use Git?</strong></summary>
- Git is optional but recommended for version history. COG works fine with just iCloud sync.
- </details>
- ## Roadmap
- - [x] ~~Gemini CLI + OpenAI Codex support~~ (shipped in v3.1)
- - [x] ~~Upstream update system~~ (shipped in v3.2)
- - [x] ~~Role packs & integration discovery~~ (shipped in v3.3)
- - [x] ~~PM workflow skills & auto-research~~ (shipped in v3.4)
- - [x] ~~Worker agents, people CRM & specialist sessions~~ (shipped in v3.5)
- - [x] ~~Loop engineering for iterative skills~~ (shipped in v3.6)
- - [x] ~~Runtime trust: memory hygiene, post-condition checks, verifier pass, content factory~~ (shipped in v3.7)
- - [ ] Web interface for knowledge graph visualization
- - [ ] Mobile-first commands (optimized for Obsidian mobile)
- - [ ] Team collaboration features (with privacy preservation)
- - [ ] Integration with calendar/task management tools
- ## Contributing & Support
- | | | |
- |---|---|---|
- | [Contribute](CONTRIBUTING.md) | [Report bugs](https://github.com/huytieu/COG-second-brain/issues) | [Discussions](https://github.com/huytieu/COG-second-brain/discussions) |
- | [Sponsor on GitHub](https://github.com/sponsors/huytieu) | [Buy me a coffee](https://buymeacoffee.com/0xlight) | [MIT License](LICENSE) |
- ## Acknowledgments & Inspiration
- Built with [Claude Code](https://claude.ai/code), [Cursor](https://cursor.com/), [Kiro](https://kiro.dev/), [Gemini CLI](https://github.com/google-gemini/gemini-cli), [OpenAI Codex](https://github.com/openai/codex), and [Obsidian](https://obsidian.md/).
- **Key inspirations:**
- - [**Garry Tan's gstack**](https://github.com/garrytan/gstack) — specialist sessions, clear operating gears, repo-local skill distribution. COG's worker agent architecture and model routing borrow directly from gstack's explicit mode separation.
- - [**Garry Tan's gbrain**](https://github.com/garrytan/gbrain) — Compiled Truth + Timeline pattern, tiered enrichment for people profiles, brain-first lookup protocol. COG's people CRM and knowledge-first approach are adapted from gbrain's design.
- - **Zettelkasten** — atomic, interlinked notes as the foundation of knowledge
- - **Building a Second Brain (Tiago Forte)** — PARA organization, progressive summarization
- - **GTD (David Allen)** — capture everything, process systematically
- ---
- **TL;DR:** Clone, run onboarding, braindump daily. COG evolves with you — just `.md` files, any AI agent, zero maintenance.
Version history
v3.16.010/23/2026
Ratings and comments
Sign in to rate this skill.
Sign inFree to use. If it’s helped, pass it on.