Skip to content

Instantly share code, notes, and snippets.

View trevorh's full-sized avatar

Trevor Hart trevorh

View GitHub Profile
@ericclemmons
ericclemmons / AGENTS.md
Last active August 28, 2026 12:51
/docs/adr/* + .agents/skills/record-architecture-decisions/SKILL.md

Architecture Decision Records

Repository history and durable technical decisions are recorded in docs/adr/.

Before completing any non-trivial implementation thread or merge request, use the repository's record-architecture-decisions skill to evaluate whether the work produced a durable architectural decision.

When a decision is ADR-worthy, add a small record under docs/adr/ in the same merge request. Capture the constraints and evidence available at the time, including failed or rejected approaches that explain why the practical solution differed from the ideal one. If no ADR is needed, say so explicitly in the final handoff.

@aarondfrancis
aarondfrancis / audit-your-codebase.md
Created August 14, 2026 15:20
A read-only, agent-orchestrated codebase audit prompt for data structures, state modeling, algorithms, and ownership.

Audit this entire codebase for materially useful simplifications in its data structures, state representation, control flow, algorithms, and ownership.

This is an audit-only exercise. Do not edit files, run tests, implement recommendations, commit, or push. Read-only inspection commands are allowed.

You are the coordinator. Continue until the complete codebase has been reviewed and the final audit is validated.

  1. Establish the coverage contract

Inspect the repository and inventory every identifiable subsystem.

@dmmulroy
dmmulroy / coding-standards-draft.md
Created June 18, 2026 22:39
coding-standards-draft.md

TypeScript Coding Standards

These standards describe how to design and write TypeScript code in this codebase. They are especially intended for agents: before adding patterns, libraries, adapters, or abstractions, read the existing code and prefer the local convention unless it conflicts with the safety/correctness principles below.

Decision priority

When rules pull in different directions, use this order:

  1. Preserve correctness, safety, and debuggability.
  2. Follow established project architecture and conventions.
@aparente
aparente / SKILL.md
Last active November 9, 2026 23:29
tufte-viz Claude Code skill — Edward Tufte data visualization principles

name: tufte-viz description: | Ideate and critique data visualizations using Edward Tufte's principles from "The Visual Display of Quantitative Information." Use this skill when: (1) Designing new data visualizations or charts (2) Critiquing or improving existing visualizations (3) Reviewing dashboards or reports for graphical integrity (4) Deciding between visualization approaches (5) Reducing chartjunk or improving data-ink ratio (6) Planning small multiples or high-density displays

@jkm-4314
jkm-4314 / README.md
Last active May 10, 2026 01:04
multi-model-review: Claude Code skill that orchestrates iterative spec/code review between Claude and Codex (GPT-5.5) until both models agree the work is production-ready

multi-model-review

📦 Also part of claude-code-skills — a small collection of opinionated Claude Code skills (project bootstrap, persistent session memory, and this multi-model review). Clone the repo for the full set.

A Claude Code skill that orchestrates iterative adversarial review of specs or code between Claude and OpenAI's Codex (GPT-5.5) until both models independently agree the work is production-ready.

Why

Claude and Codex catch different classes of issues. Running them as adversarial reviewers — each given the same artifact and the other's feedback — surfaces problems that either model would miss alone: missed edge cases, security gaps, ambiguous requirements, regressions introduced by remediation. The loop terminates when both models reach GO, or after 5 rounds (Claude's position prevails to avoid blocking work indefinitely).

@mculp
mculp / cc-settings-json-full.md
Last active November 11, 2026 12:20
Claude Code - Complete settings.json Reference (Updated April 13, 2026 - v2.1.104)

Claude Code — Complete settings.json Reference

Compiled from: plugin refs (claude-code-internals v2.5.0), the CC binary bundle (v2.1.105), local settings.json files on this machine, and the official docs at code.claude.com/docs/en/settings. ~125+ keys total.

Attribution & Output

Key Type Description
attribution.commit string Git commit trailer (e.g., "Co-Authored-By: Claude…"). Empty string disables
attribution.pr string PR description attribution. Empty string disables
includeCoAuthoredBy bool Deprecated — use attribution.commit
@gregolsen
gregolsen / SKILL.md
Created March 18, 2026 22:42
Intercom's create-pr skill
name create-pr
description This skill should be used when the user asks to "create a PR", "open a pull request", "make a PR", "submit a PR", "push a PR", or any variation of creating/opening a pull request. The skill focuses on extracting the INTENT behind changes and creating meaningful PR descriptions.
allowed-tools Bash Read Write Grep Glob AskUserQuestion

Pull Request Creation

@karpathy
karpathy / microgpt.py
Last active November 17, 2026 21:32
microgpt
"""
The most atomic way to train and run inference for a GPT in pure, dependency-free Python.
This file is the complete algorithm.
Everything else is just efficiency.
@karpathy
"""
import os # os.path.exists
import math # math.log, math.exp
@stanislaw
stanislaw / Open source requirements management tools.md
Last active October 16, 2026 09:46
Open source requirements management tools

Open source requirements management tools

Almirah is an Application Lifecycle Management framework.

A tool developed to support Software Specification analysis and Testable Requirements definition.