Build and maintain an AI Personal OS: onboard new users via conversational interview, journal daily with structured logs, atomize content into a Zettelkasten vault, research topics and publish LinkedIn posts, audit PowerPoint decks for design and accessibility issues, and scan your Claude setup for improvements.
Atomize any content into your Zettelkasten vault. Accepts text, file paths, or URLs. Extracts atomic ideas, finds connections to existing notes, and saves to your vault.
Chief of Staff Review — diagnose, build, and grow your personal AI operating system. Three modes: setup (first run), review (bi-weekly check-in), status (quick health check).
Daily 5-minute energy-mood-focus journal. Creates structured daily logs in notes/ folder. Run this every day to build your personal data foundation for Week 2's Knowledge OS.
Research a topic across multiple platforms and publish a LinkedIn post in your voice. Uses AnySite MCP for research, sub-agents for parallel investigation, /council for review, and Unipile MCP for publishing. Triggers: 'linkedin post', 'research and post', 'write a linkedin post about', 'publish to linkedin'.
Personalized onboarding for the AI Personal OS course. Runs a conversational interview to understand who you are, how you work, and what you want from the course — then creates your personal AI environment (CLAUDE.md, user-profile.md, course-goals.md, SOUL.md, achievements.md). Takes about 10-15 minutes. Use at the start of the course to set up your workspace.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Reusable Claude Code skills for building your AI Personal OS. Installable as a Claude Code plugin marketplace.
/onboarding - Personal AI OnboardingSet up your AI workspace in 10-15 minutes through a conversational interview.
What it does:
CLAUDE.md - your AI's memory of who you areuser-profile.md - structured profile for AI contextcourse-goals.md - what you want to achieveSOUL.md - your AI's personality and communication style/daily-log - Daily Energy-Mood-Focus Journal5-minute daily check-in that builds your personal data foundation.
What it does:
notes/daily-log-YYYY-MM-DD.mdExample:
/daily-log
/atomize - Zettelkasten Note ExtractorExtract atomic ideas from any text into structured Zettelkasten-style notes.
What it does:
[[wikilink]] connections to existing notesnotes/ folder with descriptive filenamesExample:
/atomize [paste an article, book notes, meeting transcript, or any text]
/cos-review - Chief of Staff System ReviewDiagnose, build, and grow your personal AI operating system. Three modes for different needs.
What it does:
/cos-review setup — First-time system scan: checks all 5 layers (identity, sources, procedures, initiative, results), analyzes your conversation history for usage patterns, scores your system 0-25, guides you through fixing the biggest gaps/cos-review — Bi-weekly review: smart diagnostic that remembers your previous score, tests all MCPs and plugins, detects manual repetitions (skill candidates), suggests ONE highest-leverage action/cos-review status — 30-second health check: tests every MCP/plugin connection, checks scheduled tasks, reports with ✅/⚠️ iconsCross-platform: Works on Mac, Windows, and Linux. Detects your OS and adapts (LaunchAgents vs schtasks vs cron).
Example:
/cos-review setup # First run — full scan + guided fixes
/cos-review # Every 2 weeks — track your growth
/cos-review status # Quick health check
/slide-inspector - PowerPoint QASystematic quality audit for PowerPoint decks. Catches layout bugs, design inconsistencies, and structural anti-patterns that make slides look unpolished.
What it does:
Usage:
/slide-inspector presentation.pptx
Or invoked automatically as a QA step after generating a deck with the pptx skill.
/linkedin-research-post - Research-to-LinkedIn PipelineResearch a topic across platforms and publish a LinkedIn post in your voice.
What it does:
/council for multi-perspective reviewRequires:
Example:
/linkedin-research-post AI productivity tools for product managers
In Claude Code, add the marketplace and install:
/plugin marketplace add BayramAnnakov/ai-personal-os-skills
/plugin install onboarding@ai-personal-os-skills
/plugin install daily-log@ai-personal-os-skills
/plugin install atomize@ai-personal-os-skills
/plugin install cos-review@ai-personal-os-skills
/plugin install slide-inspector@ai-personal-os-skills
/plugin install linkedin-research-post@ai-personal-os-skills
/reload-plugins
# Clone the repo
git clone https://github.com/BayramAnnakov/ai-personal-os-skills.git
# Copy all skills at once
cp -r ai-personal-os-skills/skills/* ~/.claude/skills/
npx claudepluginhub bayramannakov/ai-personal-os-skills --plugin slide-inspectorSelf-learning system for Claude Code that captures corrections and updates CLAUDE.md automatically
Multi-agent deliberation for AI coding assistants
Skills for AI-native product teams: team autonomy assessment (/team-assess), multi-perspective AI council (/council), autonomous prototype builder (/prototype), generalized autoresearch loop (/autoresearch) with autonomous claude -p driver, and 90-day team transformation roadmap coach (/transformation-roadmap).
Find where your Claude Code tokens are leaking. Local-only audit, nine detectors ranked by impact, cites Anthropic's Claude Code team.
Knowledge work superpowers that compound over time. Research, execute, review, and capture learnings to make each task easier than the last.
PM 코치 - 업무 소통 최적화. 요청/수신/보고 세 가지 모드로 명확한 소통 지원. 두서없는 지시를 구조화된 업무 정의서로 변환.
PM Weekly Review: a 20-minute structured ritual covering metrics movement, shipping progress, customer insights, and next week's top 3 priorities in a shareable update.
Entrepreneur OS core: AUDHD executive function, voice enforcement, and research mode
個人知識管理系統
Compile humans into AI agents through deep interviews. Conducts comprehensive behavioral interviews, analyzes work artifacts via MCP tools, and generates installable Claude Code plugins that embody a person's decision-making, communication style, and expertise.