One-click install
npx skills add https://github.com/shahdanish/vibepos --skill instinct-system-shahdanish
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: instinct-system
Source: https://github.com/shahdanish/vibepos/tree/main/skills/instinct-system
Command: npx skills add https://github.com/shahdanish/vibepos --skill instinct-system-shahdanish

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It helps you reliably detect recurring project conventions by treating early observations as hypotheses, scoring confidence as evidence accumulates, and only promoting confirmed insights into permanent guidance.

Core Features & Use Cases

  • Confidence-scored hypothesis lifecycle: Start instincts at 0.3, adjust confidence through confirm/disconfirm evidence, and promote only when confidence reaches 0.9.
  • Project-scoped memory: Keep instincts per-project in .claude/instincts.md and promote them into MEMORY.md once confirmed to avoid cross-project contamination.
  • Observe–Hypothesize–Confirm workflow: Actively seek evidence in 2–3 related areas, track seen counts and last-updated dates, and discard stale or contradicted patterns.
  • Confidence-based behavior control: Ignore low-confidence items, mention or follow at higher confidence, and request user approval before permanence.
  • Import/export discipline: Export at 0.7+ and import with decay so local verification remains required.

Quick Start

Load this skill at the start of a session to read .claude/instincts.md and apply any 0.7+ instincts, then when you notice a recurring pattern form a new instinct at 0.3 and check 2–3 related files to confirm or disconfirm it.

Frequently Asked Questions about instinct-system

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

FAQPage Schema
How do I systematically detect and learn recurring software patterns in a codebase?

To detect recurring software patterns, observe conventions, hypothesize likely rules, and actively confirm evidence across related files. You track confidence scores for each hypothesis, promoting confirmed patterns into permanent guidance once confidence reaches 0.9.

What is the best way to manage project conventions without cross-project contamination?

Manage project conventions safely by keeping scoped instincts in a local `.claude/instincts.md` file. You promote confirmed patterns into `MEMORY.md` only after reaching high confidence, ensuring local verification remains strictly required.

How do I build confidence-scored hypotheses for architecture guidelines?

Build confidence-scored hypotheses by starting instincts at 0.3, checking 2–3 related files for evidence, and adjusting scores based on seen counts and last-updated metadata. You promote items to permanent memory only when confidence hits 0.9.

When should I avoid applying low-confidence project conventions?

You should ignore low-confidence instincts below 0.7 to prevent applying unverified patterns. The system specifically controls behavior by only mentioning or following conventions at higher confidence levels, discarding stale or contradicted patterns.

Can I import and export observed developer workflow patterns across different projects?

Yes, you can export instincts at 0.7+ confidence and import them with decay applied. This import discipline requires local verification, ensuring you must confirm evidence before treating imported patterns as reliable guidance.

Does the instinct-system workflow require specific dependencies or components?

No specific dependencies or components are required. The workflow operates by storing and updating hypotheses with confidence, seen, and last metadata in `.claude/instincts.md`, and promoting confirmed items to `MEMORY.md`.