forge-self

Build a structured persona.json from guided intake and optional material analysis.

107|21|Updated Apr 4, 2026
One-click install
npx skills add https://github.com/YIKUAIBANZI/forge-skill --skill forge-self
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: forge-self
Source: https://github.com/YIKUAIBANZI/forge-skill/tree/main/forge-self
Command: npx skills add https://github.com/YIKUAIBANZI/forge-skill --skill forge-self

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

You lack a reliable way to see your own patterns—how you decide, what you value, and where your blind spots are—so your choices feel cloudy or inconsistent.

Core Features & Use Cases

  • Guided self-distillation: Runs a multi-round intake conversation to capture your identity, decision style, values, and blind spots without judgment or beautifying your reality.
  • Optional cross-source evidence analysis: If you provide materials (e.g., WeChat exports, diary/notes, social content), it parses and cross-validates what you say with what you do, preserving contradictions for your confirmation.
  • A calibrated “persona base” for reflection: Produces a structured persona.md (and persona.json) that you can later use as input for private decision support (via /use-self).
  • Validation + correction loop: Shows a summary, asks what feels “too off” or “too beautified,” records user corrections into a correction layer, and runs an automated validator for structural and evidence coverage.

Quick Start

Tell the user to run /forge-self and follow the four intake phases (conversation first, then optional material import) to generate your persona base.

Frequently Asked Questions about forge-self

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I create a digital persona for self-reflection and decision support?

You build a digital persona for self-reflection by completing a multi-round conversational intake that captures your identity and decision style, ultimately generating a structured persona.json file for private decision support.

What is evidence-based cross-validation in personal decision making?

Evidence-based cross-validation in personal decision making involves parsing your provided materials like WeChat exports or diary notes to compare what you say against what you actually do, preserving any contradictions for your confirmation.

Can I use local-first data ingestion to expose my cognitive blind spots?

Yes, you can use local-first data ingestion to expose cognitive blind spots by optionally importing personal materials like social content and notes, which the system parses to cross-validate your stated values against your actions.

How do I calibrate a personalized persona base after initial generation?

You calibrate a personalized persona base by reviewing a generated summary, identifying what feels too off or beautified, recording your corrections into a correction layer, and running an automated validator for structural coverage.

What is the best way to extract decision patterns from my personal notes and WeChat exports?

The best way to extract decision patterns from personal notes and WeChat exports is using a parser-driven ingestion process that cross-validates your conversational intake with your actual behavioral evidence to distill a clear persona base.