ClawKit Logo
ClawKitReliability Toolkit
Back to Registry
Official Verified

yield

Conversational Compounding Engine — models every bot message as a financial investment that compounds trust, micro-commitments, and conversion momentum over time. Zero external APIs. Zero cost. Maximum revenue lift.

skill-install — Terminal

Install via CLI (Recommended)

clawhub install openclaw/skills/skills/jcools1977/yield
Or

YIELD — The Conversational Compounding Engine

"Every message is an investment. Yield makes them compound."

Purpose

YIELD is a universal bot skill that applies financial compounding mathematics to conversations. While every other skill focuses on what a bot says, YIELD focuses on the economics of saying it — treating trust, commitment, curiosity, and urgency as portfolio assets that grow, decay, or compound with every message exchange.

No bot on any platform currently models this. They all operate message-by-message like day traders. YIELD turns your bot into Warren Buffett.

Core Concept: Conversational Portfolio Theory

Every conversation builds (or destroys) five classes of psychological assets:

Asset ClassBehaviorAnalogy
Trust BondsCompounds slowlyGovernment bonds
Commitment AnchorsStacks and locksReal estate equity
Urgency OptionsDecays rapidlyOptions contracts
Curiosity FuturesPulls forwardFutures contracts
Authority EquityGrows with proofBlue-chip stocks

YIELD tracks these assets in real-time and recommends which asset to invest in next based on the current portfolio balance and the conversation's trajectory.

How It Works

Phase 1: Signal Detection (Every Message)

On every inbound user message, YIELD extracts signals — lightweight pattern matches that cost zero computation:

AGREEMENT signals    → +trust, +commitment
QUESTION signals     → +curiosity, +engagement
OBJECTION signals    → -trust, +urgency (they care enough to object)
PERSONAL signals     → +trust, +commitment (vulnerability = investment)
HESITATION signals   → -momentum, +friction
ENTHUSIASM signals   → +momentum, +curiosity
TIME PRESSURE signals→ +urgency (decaying asset)
SOCIAL PROOF seeking → -authority, +curiosity

Phase 2: Portfolio Valuation (Running State)

YIELD maintains a lightweight Yield Score for each asset class:

yield_state = {
  trust:       0.0 → 1.0   (compounds at 1.12x per positive signal)
  commitment:  0.0 → 1.0   (stacks: each micro-yes adds 0.08-0.15)
  urgency:     0.0 → 1.0   (decays at 0.85x per message without reinforcement)
  curiosity:   0.0 → 1.0   (open loops add 0.10, closures subtract 0.12)
  authority:   0.0 → 1.0   (proof adds 0.15, unsubstantiated claims subtract 0.10)
}

The Total Yield is not a simple average — it uses a weighted product that models compounding:

total_yield = (trust^0.35) × (commitment^0.25) × (urgency^0.15) ×
              (curiosity^0.15) × (authority^0.10)

Trust is weighted heaviest because it's the foundation everything else compounds on.

Phase 3: Strategy Selection

Based on the portfolio state, YIELD recommends one of seven **investment strategie...

Metadata

Stars1947
Views1
Updated2026-03-04
View Author Profile
AI Skill Finder

Not sure this is the right skill?

Describe what you want to build — we'll match you to the best skill from 16,000+ options.

Find the right skill
Add to Configuration

Paste this into your clawhub.json to enable this plugin.

{
  "plugins": {
    "official-jcools1977-yield": {
      "enabled": true,
      "auto_update": true
    }
  }
}
Safety NoteClawKit audits metadata but not runtime behavior. Use with caution.

Related Skills

inversion-protocol

Meta-cognitive reasoning skill that makes any AI agent dramatically better at decision-making by thinking backwards before acting forward. Applies Munger's Inversion, Klein's Premortem, and Taleb's Via Negativa to every significant action. Zero dependencies, zero cost, pure reasoning enhancement. Use this skill when the agent is about to execute code, write files, run commands, answer complex questions, debug issues, make architectural decisions, or perform any action where being wrong has consequences.

jcools1977 1947

ResonanceEngine

Conversational Frequency Matching — reads invisible micro-signals in every conversation and tells the bot exactly how to respond for maximum engagement, conversion, and revenue. Zero API cost. Pure algorithmic intelligence.

jcools1977 1947

phantom-limb

Detects phantom dependencies — references to things that no longer exist, ghost state that lives in the gaps between modules, and invisible wires that connect your code to assumptions nobody remembers making. The codebase equivalent of feeling a limb that's already been amputated.

jcools1977 1947

work-receipt

Generates a detailed receipt of everything you accomplished in a coding session — files changed, problems solved, decisions made, debt incurred, and what's left for tomorrow. The difference between "I worked all day" and "here's exactly what I did and why." Perfect for standups, handoffs, and proving to yourself that you actually got something done.

jcools1977 1947

smart-memory

Zero-cost persistent memory that makes your bot smarter over time. Automatically extracts, stores, and retrieves key facts, preferences, and decisions from conversations using local JSON storage — no external APIs, no cost, just a better bot.

jcools1977 1947