Fix Your Entire Life in 1 Day

Fix your entire life in 1 day. 10 psychological sessions based on Dan Koe's viral article.

Security Scan

The skill's described purpose (guided coaching sessions) matches the files and runtime instructions, but it relies on bundled shell scripts that will be executed with user-provided text and may create scheduled reminders — the actual scripts were not shown, so there is a non-trivial risk of command injection, data exfiltration, or unwanted system changes unless you inspect them first.

Purpose & Capability

Name, description, and declared requirements (bash + jq) align with a local, interactive coaching skill that stores session text in $WORKSPACE. There are no requested environment variables or external credentials that would be disproportionate for the stated purpose.

Instruction Scope

Runtime instructions explicitly tell the agent to execute scripts/handler.sh and export.sh and to write user session files under $WORKSPACE/memory/life-architect/. Those scripts are called with raw user responses (e.g., handler.sh save "USER_RESPONSE"), and the skill can create reminders (handler.sh reminders ... and an explicit question about cron reminders). Because the script contents were not provided for review here, this raises concern: shell scripts that accept arbitrary user text can be vulnerable to command injection or could invoke network tools, edit crontab, or upload data. The SKILL.md itself does not document any external endpoints, but the scripts could add them — review of the actual scripts is required.

Install Mechanism

There is no install spec (no downloads) — the skill ships code in the skill bundle. That reduces supply-chain concerns from remote fetches, but executing included scripts still runs code delivered with the skill. This is lower-risk than a remote download, but it's not as low-risk as instruction-only skills with no code files.

Credentials

The skill requests no environment variables or external credentials and stores data under $WORKSPACE, which is proportionate to a journaling/coaching tool. The only privileged surface is the filesystem and whatever the agent process is allowed to do (scheduling, network, etc.), so those runtime capabilities should be reviewed.

Persistence & Privilege

always:false and user-invocable:true (normal). The skill writes persistent user data into $WORKSPACE/memory/life-architect/ (state.json, session files, final-document.md), which is expected. However the SKILL.md and handler interface reference creating reminders; if the scripts create OS-level scheduled tasks (cron/systemd/at) or modify system configuration, that increases persistence and privilege — confirm whether the scripts only write to the skill workspace or also modify system schedulers.

What to consider before installing

What to do before installing or running this skill: - Inspect the bundled scripts (scripts/handler.sh, scripts/export.sh, scripts/init.sh, scripts/status.sh) before executing anything. Search for network commands (curl, wget, nc, netcat, ssh, scp), remote hosts, base64/openssl decode+exec patterns, and any use of eval, backticks, or unescaped variable expansion that could allow command injection when handling user text. - Pay special attention to how user input is handled. The handler is called like: handler.sh save "USER_RESPONSE" — if the script inserts that text into shell commands without sanitization, a maliciously crafted response could execute arbitrary commands. - Check whether the scripts modify system schedulers (crontab, at, systemctl timers) or edit files outside the skill workspace. If they do, ask the author to justify why and consider running in a restricted environment. - Run the skill in a sandbox first (a throwaway VM or container) and monitor outbound network connections and file writes. Verify reminders behavior (do they only schedule local notifications or attempt to contact external services?). - Ensure the agent process has minimal permissions; avoid running as root. Back up any important data from your normal workspace before first run. - If you are not comfortable auditing shell scripts, decline installation or ask the maintainer for a review that documents: (a) that no external network calls are made, (b) that scheduling is done only via local, user-owned crontab entries (if at all), and (c) that user input is safely escaped/handled. If the scripts are clean and only write session files under $WORKSPACE and schedule reminders via safe, local mechanisms, the skill appears coherent for its coaching purpose. If the scripts contact remote endpoints, modify system-wide config, or use unsafe shell practices, consider the skill untrusted.

10 psychological sessions based on Dan Koe's viral article.

Based on:

• 📝 @thedankoe — "How to fix your entire life in 1 day"
• 🔧 @alex_prompter — 10 AI prompts reverse-engineered from Dan's article
• ⚡ @chip1cr — Clawdbot skill implementation

What It Does

Guides users through 10 structured sessions:

1. The Anti-Vision Architect — Build a visceral image of the life you're drifting toward
2. The Hidden Goal Decoder — Expose what you're actually optimizing for
3. The Identity Construction Tracer — Trace limiting beliefs to their origins
4. The Lifestyle-Outcome Alignment Auditor — Compare required vs actual lifestyle
5. The Dissonance Engine — Move from comfort to productive tension
6. The Cybernetic Debugger — Fix your goal-pursuit feedback loop
7. The Ego Stage Navigator — Assess developmental stage and transition
8. The Game Architecture Engineer — Design life as a game with stakes
9. The Conditioning Excavator — Separate inherited beliefs from chosen ones
10. The One-Day Reset Architect — Generate a complete 1-day transformation protocol

Commands

Command	Action
/life	Start or continue (shows intro for new users)
/life ru	Start in Russian
/life status	Show progress
/life session N	Jump to session N
/life reset	Start over

Usage Flow

When User Says /life

Step 1: Check if intro needed

bash scripts/handler.sh intro en $WORKSPACE

If showIntro: true → Send intro message with image and "🐇 Jump into the rabbit hole" button (life:begin)

If showIntro: false → Run start and show current phase

Step 2: Get current state

bash scripts/handler.sh start en $WORKSPACE

Step 3: Format and show to user:

🧠 **Life Architect** — Session {session}/10
**{title}**
Phase {phase}/{totalPhases}
━━━━━━━━━━━━━━━━━━━━━━━━━━━

{content}

━━━━━━━━━━━━━━━━━━━━━━━━━━━

Step 4: When user responds, save and advance:

bash scripts/handler.sh save "USER_RESPONSE" $WORKSPACE

Handler Commands

handler.sh intro [en|ru]     # Check if should show intro
handler.sh start [en|ru]     # Start/continue session
handler.sh status            # Progress JSON
handler.sh session N         # Jump to session N
handler.sh save "text"       # Save response & advance
handler.sh skip              # Skip current phase
handler.sh reset             # Clear all progress
handler.sh callback <cb>     # Handle button callbacks
handler.sh lang en|ru        # Switch language
handler.sh reminders "07:00" "2026-01-27"  # Create Session 10 reminders
handler.sh insights          # Get accumulated insights

Callbacks

• life:begin / life:begin:ru — Start sessions
• life:prev — Previous phase
• life:skip — Skip phase
• life:save — Save and exit
• life:continue — Continue
• life:lang:en / life:lang:ru — Switch language
• life:session:N — Jump to session N

Files

life-architect/
├── SKILL.md              # This file
├── assets/
│   └── intro.jpg         # Intro image
├── references/
│   ├── sessions.md       # Session overview
│   ├── sources.md        # Original sources
│   └── sessions/
│       ├── en/           # English sessions (1-10)
│       └── ru/           # Russian sessions (1-10)
└── scripts/
    ├── handler.sh        # Main command handler
    └── export.sh         # Export final document

User Data

Stored in $WORKSPACE/memory/life-architect/:

• state.json — Progress tracking
• session-NN.md — User responses
• insights.md — Key insights from completed sessions
• final-document.md — Exported complete document

Languages

• English (default)
• Russian (full translation)

Requirements

• jq (JSON processor)
• bash 4.0+

License

MIT