aba-precision-protocol

Featured

FOUNDATIONAL BEHAVIORAL PROTOCOL — ABA-based precision execution rules. Every prompt processed must follow these rules. Mistakes caught late create intermittent reinforcement of wrong patterns. Stop-fix-verify before proceeding.

AI & Automation 157 stars 23 forks Updated today Apache-2.0

Install

View on GitHub

Quality Score: 87/100

Stars 20%
73
Recency 20%
100
Frontmatter 20%
70
Documentation 15%
100
Issue Health 10%
80
License 10%
100
Description 5%
100

Skill Content

# ABA Precision Execution Protocol > **This is the foundation of agent behavior. Every prompt processed must follow these rules.** ## Rule 1: Observable, Measurable Goals Before starting ANY task: 1. **Identify the specific goal** — it must be **observable**, not vague 2. Look at the goal 2-3 times to confirm you understand it the same way each time 3. **Inter-observer agreement must be ≥80%** — if you described the goal to 5 people, at least 4 should describe the same outcome 4. If the goal is ambiguous, clarify BEFORE starting work ### Anti-Pattern ``` Goal: "Fix the bug" ← NOT observable Goal: "Make it work better" ← NOT measurable ``` ### Correct Pattern ``` Goal: "The AI should respond 'Yes, I have git_tool' when asked 'do you have GitHub access?'" ← Observable, testable Goal: "prism load output should NOT contain '⚠️ SPLIT-BRAIN' when Supabase is primary" ← Observable, testable ``` --- ## Rule 2: Teach Slow and Precise Execute each step **exactly as the final result should look**. Not approximately. Not "close enough." Exactly. 1. **Do one step at a time** 2. **Each step must be exactly right** before moving to the next 3. **If you see a mistake — STOP immediately** 4. Fix the mistake FIRST 5. Verify the fix is correct 6. ONLY THEN move forward 7. **Never batch multiple changes hoping they'll all work** ### The Chain ``` Step → Verify → Pass? → Next Step ↓ Fail? → STOP → Fix → V...

Details

Author
dcostenco
Repository
dcostenco/prism-coder
Created
7 months ago
Last Updated
today
Language
TypeScript
License
Apache-2.0

Integrates with

Similar Skills

Semantically similar based on skill content — not just same category