Dicklesworthstone

User Query: Based on using the /modes-of-reasoning-project-analysis skill, what did the skill and the swarm that followed it get right? What was wrong? How could those findings be articulated into feedback that could be used to improve the skill so it's more effective?

This is a great question — and honestly, the most valuable output of the whole exercise is this meta-analysis rather than the 600-line report itself. Let me break it down honestly.

What the Skill/Swarm Got Right

1. Convergence as signal genuinely works. When 5-6 modes independently flagged the god-package problem and the global mutable state pattern, that convergence was a real signal. These were the most actionable findings in the report, and they were actionable precisely because multiple lenses validated them.
2. The adversarial mode (H2) found things nothing else would have. The pane input API missing policy checks, the SLB self-approval bypass in local mode, the CORS config mutation vector — these are real code-level

farzaa

name	wiki
description	Compile personal data (journals, notes, messages, whatever) into a personal knowledge wiki. Ingest any data format, absorb entries into wiki articles, query, cleanup, and expand.
argument-hint	ingest | absorb [date-range] | query <question> | cleanup | breakdown | status

Personal Knowledge Wiki

You are a writer compiling a personal knowledge wiki from someone's personal data. Not a filing clerk. A writer. Your job is to read entries, understand what they mean, and write articles that capture understanding. The wiki is a map of a mind.

karpathy

LLM Wiki

A pattern for building personal knowledge bases using LLMs.

This is an idea file, it is designed to be copy pasted to your own LLM Agent (e.g. OpenAI Codex, Claude Code, OpenCode / Pi, or etc.). Its goal is to communicate the high level idea, but your agent will build out the specifics in collaboration with you.

The core idea

Most people's experience with LLMs and documents looks like RAG: you upload a collection of files, the LLM retrieves relevant chunks at query time, and generates an answer. This works, but the LLM is rediscovering knowledge from scratch on every question. There's no accumulation. Ask a subtle question that requires synthesizing five documents, and the LLM has to find and piece together the relevant fragments every time. Nothing is built up. NotebookLM, ChatGPT file uploads, and most RAG systems work this way.

boxabirds

# =============================================================================
# Step 2: Fallback detection (using Claude CLI)
# =============================================================================

# Skip if claude not available
if ! command -v claude &> /dev/null; then
    echo "Warning: claude CLI not found, skipping fallback check"
    exit 0
fi

dollspace-gay

Verified Spec-Driven Development (VSDD)

The Fusion: VDD × TDD × SDD for AI-Native Engineering

Overview

Verified Spec-Driven Development (VSDD) is a unified software engineering methodology that fuses three proven paradigms into a single AI-orchestrated pipeline:

• Spec-Driven Development (SDD): Define the contract before writing a single line of implementation. Specs are the source of truth.
• Test-Driven Development (TDD): Tests are written before code. Red → Green → Refactor. No code exists without a failing test that demanded it.

mberman84

OpenClaw: System Prompt File Templates

Generalized versions of all root .md files used by OpenClaw. These files are loaded into the agent's system prompt on every request (except MEMORY.md which is conditional).

Copy these as starting points and customize for your own setup. Replace <placeholders> with your values.

---

AGENTS.md

minimaxir

Agent Guidelines for Python Code Quality

This document provides guidelines for maintaining high-quality Python code. These rules MUST be followed by all AI coding agents and contributors.

Your Core Principles

All code you write MUST be fully optimized.

"Fully optimized" includes:

minimaxir

Agent Guidelines for Rust Code Quality

This document provides guidelines for maintaining high-quality Rust code. These rules MUST be followed by all AI coding agents and contributors.

Your Core Principles

All code you write MUST be fully optimized.

"Fully optimized" includes:

hansonw

<!doctype html>
<html lang="en">
<head>
  <meta charset="utf-8" />
  <meta name="viewport" content="width=device-width, initial-scale=1" />
  <title>codex_gpt2_codegolf.jsonl - Codex Session</title>
  <style>
    :root {
      --bg: #ffffff;
      --panel: #ffffff;

weshoke

#!/usr/bin/env python3
"""
Codebase analyzer using Recursive Language Models (RLM) via DSPy.

Based on: https://kmad.ai/Recursive-Language-Models-Security-Audit

Usage:
    python analyze-codebase.py --mode security --output report.md
    python analyze-codebase.py --mode documentation --exclude tests,vendor
    python analyze-codebase.py --mode quality --max-iterations 50