🧠 Digital Stoic Praxis
Praxis (πρᾶξις) = practice. Knowledge enacted, not just known.
⚠️ Live experiment. My cognitive toolkit — fork it, adapt it to your brain.
🎯 In One Sentence
A cognitive discipline for human-AI collaboration built on mutual sharpening — the human sets intent and directs, the AI challenges and reveals blind spots, and both learn from the loop.
💡 Why This Exists
AI tools are powerful but chaotic. Most people either micromanage every prompt or let AI run wild and pray. Neither scales to real work.
This toolkit treats AI collaboration as cognitive discipline — a set of thinking modes you activate depending on the situation, where the AI also pushes back on your assumptions. The goal is not to make AI do more. It's to think better together — and that includes letting AI challenge the human.
Deeper why → PHILOSOPHY.md
🧭 The Flow
flowchart LR
F["🧭 Frame"] --> T["🧠 Think"]
T --> B["⚙️ Build"]
B --> D["🔧 Debug"]
D --> L["🪞 Learn"]
L -.->|"compounding loop"| F
classDef frame fill:#E8EAF6,stroke:#3F51B5,color:#000
classDef think fill:#E1BEE7,stroke:#7B1FA2,color:#000
classDef build fill:#C8E6C9,stroke:#388E3C,color:#000
classDef debug fill:#FFE0B2,stroke:#F57C00,color:#000
classDef learn fill:#BBDEFB,stroke:#1976D2,color:#000
class F frame
class T think
class B build
class D debug
class L learn
| Mode | What | Hero Skills |
|---|
| 🧭 Frame | Classify the problem → route to the right skill chain | /frame-problem (Cynefin), /pick-model |
| 🧠 Think | Divergent ideation, deep analysis, adversarial review | /brainstorm (SCAMPER), /investigate, /probe, /challenge |
| ⚙️ Build | Plan → develop → gate → test → sync | /openspec-* suite (9 skills, human-gated sections) |
| 🔧 Debug | Search-first troubleshooting with learnings DB | /troubleshoot (Wolf Fence, 5 Whys, OODA), /experiment |
| 🪞 Learn | Extract patterns, persist sessions | /retrospect-*, /save-context, /load-context |
Plus: tool creation (/edit-tool), conversions (PDF, EPUB, Google Docs), and domain plugins (GTD, coaching, business analysis, philosopher personas).
🤝 Human-AI Blend
Not human-drives-AI. Not AI-drives-human. Mutual sharpening:
- Human → AI: Sets intent, chooses cognitive mode, directs execution, verifies at gates
- AI → Human: Challenges assumptions, surfaces blind spots, reveals patterns the human can't self-observe
- Together: The human thinks more clearly because the AI pushes back. The AI produces better work because the human sets precise intent.
Key: Posture before technique — but posture includes the willingness to be challenged.
Full autonomy spectrum + orchestrated agency → PRACTICE.md
💰 Cognitive ROI (Return on Tokens)
Not "how fast" — how deep:
| Tier | What | Value/Token |
|---|
| ⚙️ Automation | Rote tasks (convert, deploy, format) | Low |
| 🤝 Assisted Thinking | AI structures human thought | Medium |
| 🧠 Amplified Judgment | AI challenges/deepens reasoning | High |
Maturity = shifting tokens from ⚙️ toward 🧠.
Multiplied by context efficiency (don't waste tokens re-explaining) and compounding (learnings reduce future spend). Full model → PRACTICE.md
📊 By the Numbers
- 49 skills across 5 cognitive modes + utilities
- 6 plugins: core (dstoic), GTD, coaching, business analysis, philosopher personas, cowork
- 2 agents: devil's advocate (debiasing), context summarizer
- 4 hooks: notifications, session capture, debug dumps, daily sync
- 3 execution modes: garage (default), scale, maintenance
- 🪥 Toothbrush principle: This is one practitioner's discipline. Don't copy — adapt. Why?
🏪 Plugins
| Plugin | Description | Status |
|---|
| dstoic | Core cognitive toolkit: 47 skills, 0 commands, 4 hooks | ✅ v0.24.0 |
| gtd | GTD workflow automation for Obsidian vaults | ✅ v0.3.1 |
| coach | Personal coaching: CLEAR + GROW protocols | ✅ v0.3.0 |
| biz | Business analysis toolkit: competitive analysis, UX strategy, UX wireframes, UX evaluation, UX brand identity | ✅ v0.7.1 |
| philosopher | Philosopher personas: historically-grounded dialogue, source attribution, AI meta-cognition | ✅ v0.1.0 |
| cowork | Multi-project context management: switch projects, save/load sessions. Non-CLI friendly | ✅ v0.2.0 |
📦 Install
/install-plugin https://github.com/digital-stoic-org/agent-skills
To install a specific plugin only, add it to .claude/settings.json:
{"plugins": ["digital-stoic-org/agent-skills/dstoic"]}
