evandhoffman

I’ll judge them on two axes:

Quality: the Opus-high review’s findings by severity, whether the full UI suite passes on iPhone and iPad, whether the tests were truly written first, and how sound the new package API is. Speed: wall time from start to report, plus tokens used.

Both builders are still running. I’ll post the scorecard on #35 and give you the verdict here.

11 background commands completed

Build A (Opus medium) is in. I’m starting its review and its UI run now, so the lane isn’t idle while B finishes. B gets the same review prompt and the same suite.

evandhoffman

Prompt: Regenerate AGENTS.md and README.md

Analyze one project and create or regenerate its documentation for AI coding agents and humans in one coordinated pass:

• AGENTS.md: concise, authoritative, tool-neutral entry point for agent guidance.
• README.md (or the existing README in another format): concise, authoritative entry point for humans.
• Supporting documentation: the home for detailed policies, workflows, reference material, rationale, incident history, and anything moved out of either entry point.

"Regenerate" means reconcile existing documentation against project evidence and fill useful gaps. Preserve existing knowledge and intentional policies. Where documentation is missing or skeletal, write a concise starting point from known purpose, approved intent, and available artifacts. Never replace useful content with a generic template.

evandhoffman

Analyze this project and create or regenerate its documentation for both AI coding agents and humans in one coordinated pass:

- `AGENTS.md`: concise, authoritative entry point for tool-neutral agent guidance.
- `README.md`: concise, authoritative entry point for human-facing project documentation.
- Supporting documentation: the appropriate home for detailed policies, workflows, reference material, rationale, incident history, and information moved out of either entry point.

“Regenerate” means reconcile existing documentation against project evidence and fill useful gaps. Preserve its knowledge and intentional policies. When documentation is missing or skeletal, create a concise starting point from known purpose, approved intent, and available artifacts. Do not replace useful content with a generic template.

The task is complete only when both entry points exist and fit the project’s current state, necessary supporting documentation is written, links and symlinks are verified, and the applicable preservat

evandhoffman

Getting session info (cwd, git branch) into the Windows Terminal tab title under WSL

Symptom: the tab always reads Ubuntu-24.04 (the profile name). It never reflects your working directory, and TUI apps that set their own title (Claude Code, vim, ssh) don't show up either.

There are two independent causes, and you have to fix both. Diagnose them separately or you will chase your tail.

---

evandhoffman

Analyze this repository and create or update its README.md. The README is primarily for humans. Agent-specific guidance lives in AGENTS.md — do not duplicate it; link to it once.

Priorities, in order (structure the README this way):

1. What this is — 2–4 sentences: purpose, product surface (CLI/API/library/ app/infra), runtime model.
2. Usage — how to use the software. This is the main help page. First identify the product type(s) from evidence, then adapt:

• CLI tool: commands, flags, examples, exit codes if evident.

evandhoffman

Analyze this repository and create or update its AGENTS.md files. Each AGENTS.md is symlinked to CLAUDE.md and GEMINI.md, so all guidance must be tool-neutral and apply to any AI coding agent.

Delivery mode

Pick one before making changes:

• pr — create a working branch, commit, push, open a pull request.
• direct — commit and push straight to the default branch, no branch, no PR.

evandhoffman

#!/usr/bin/env python3
"""
Manages quality definitions and profile assignments in Radarr and Sonarr.

Usage:
    python3 set-quality-limits.py                          # set size limits
    python3 set-quality-limits.py --dry-run                # preview size limit changes
    python3 set-quality-limits.py --assign-profile Any     # assign profile to all content
    python3 set-quality-limits.py --check-scores Any       # verify custom format scores in a profile
    python3 set-quality-limits.py --refresh                # trigger Refresh & Scan for all content

evandhoffman

import xml.etree.ElementTree as ET
import logging
import re
import json
import csv
from dateutil import parser as date_parser
from datetime import datetime

def extract_body_weight_records(xml_path):
    weights = {}

evandhoffman

// Lifted partially from https://gist.github.com/orion-v/95cb48fa73808cdc5c589fe415cc65f1
// and https://github.com/vegeta897/snow-stamp/blob/main/src/convert.js#L2

const DISCORD_EPOCH = 1420070400000

function dateToPostId(date) {
	return (date - DISCORD_EPOCH) * 4194304
	//return new Date(snowflake / 4194304 + epoch)
}

evandhoffman

# Jimb - Havoc - 2020-04-16 13:01 - US/Doomhammer
# SimC Addon 1.12.5
# Requires SimulationCraft 820-01 or newer

demonhunter="Jimb"
level=120
race=night_elf
region=us
server=doomhammer
role=attack