skills.rest
GregoryHo
GregoryHoCOMMUNITY
Explore all skills by this author →
GitHub

arc-reflecting

Analyze AI conversation logs to identify patterns, preferences, and rule violations.

6|Updated Feb 8, 2026
Search Tags:#pattern recognition#reflection#session analysis#ai behavior#instinct generation#rule violation
One-click install
npx skills add https://github.com/GregoryHo/arcforge --skill arc-reflecting
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: arc-reflecting
Source: https://github.com/GregoryHo/arcforge/tree/main/skills/arc-reflecting
Command: npx skills add https://github.com/GregoryHo/arcforge --skill arc-reflecting

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill analyzes your past AI conversation logs (diaries) to identify recurring patterns, preferences, and rule violations, helping you understand and refine your AI's behavior over time.

Core Features & Use Cases

  • Pattern Identification: Detects repeated decisions, techniques, or preferences across multiple sessions (3+ occurrences).
  • Rule Violation Detection: Flags instances where the AI broke established rules defined in your CLAUDE.md.
  • Instinct Generation: Automatically creates new AI "instincts" based on identified patterns for future use.
  • Use Case: After a series of coding sessions, you can use this Skill to discover that you consistently prefer PostgreSQL for database tasks, or that the AI frequently needs to be reminded not to add AI attribution to commits.

Quick Start

Run the reflect skill to analyze your recent diary entries for patterns and violations.

Frequently Asked Questions about arc-reflecting

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

FAQPage Schema
How do I analyze AI conversation logs to identify recurring patterns?▼

You can analyze AI conversation logs by running a reflection process on your session diaries to detect recurring patterns, preferences, and rule violations. It identifies repeated decisions or techniques that occur 3 or more times across multiple sessions.

How do I detect rule violations in my AI session history?▼

To detect rule violations in your AI session history, you analyze your conversation diaries against the established rules defined in your CLAUDE.md file. This process flags specific instances where the AI broke those predefined rules.

Do I need Node.js to generate AI instincts from session analysis?▼

Yes, you need Node.js and specific session utility libraries to process your logs and write the generated instincts. These dependencies are required to execute the analysis scripts and output the new AI behavior rules.

Can I automatically create new AI instincts based on past preferences?▼

Yes, you can automatically create new AI instincts based on past preferences by analyzing historical session data. The instinct generation feature extracts insights from identified patterns to refine future AI behavior.

What is the minimum number of occurrences needed to identify a pattern in session diaries?▼

The minimum number of occurrences needed to identify a pattern in session diaries is 3. Pattern identification detects repeated decisions, techniques, or preferences that appear 3 or more times across your analyzed logs.

Related Skills

Explore More Software Engineering Skills→
adiomasadiomas

work-type-classifier

Classify user requests into predefined work types and output .claude/auto-context.yaml.

Community
Advanced
sQVesQVe

conform

Compare changed code against CLAUDE.md and local rule files to report violations.

Community
Intermediate
riftzen-bitriftzen-bit

ck

Manages per-project session state and generates context briefings via CLI.

Community
Advanced
WrongStackWrongStack
224

audit-log

Parse WrongStack session JSONL logs and generate structured markdown audit reports.

Official
Advanced