Siqi Chen

humanizer. Claude Code skill that removes signs of AI-generated writing from text

Claudeception. A Claude Code skill for autonomous skill extraction and continuous learning. Have Claude Code get smarter as it works.

napkin. A Claude Code skill that gives the agent persistent memory of its mistakes via a per-repo markdown scratchpad.

taskmaster. Stop hook for Claude Code that keeps the agent working until all plans and user requests are 100% complete

schematic. Claude Code / Codex skill: reverse engineer a product & technical spec from a git branch

theorist. A Codex/Claude skill that maintains per-repo operating theory documents.

arbitrage. A Claude Code skill for token arbitrage: keep premium model tokens for judgment, dispatch all code-writing to codex.

MiraViewer. MRI viewer application

razor. Minimize your branch diff against merge base with structured, explicit tradeoffs. A skill for Claude Code and Codex.

cto-review. Public Codex skill: cto-review

adversarial-execution. Adversarial Execution — an execution-time review gate: two independent strong models must both prove your work actually works before it's marked done. A Claude Code / Codex skill.

baton. Baton — clean session handoffs: pass in-progress work to the next agent with a single verified markdown file. A Claude Code / Codex skill.

Project-Euler. siqi's project euler solutions

first-responder. An AI agent skill that acts as the first responder for your oncall Slack channel: investigates incidents, posts evidence-backed findings, and drives validated fix PRs

ream. Ream: A sparse text format for LLM spreadsheet comprehension

warp-autocontinue. Auto-send 'Please continue' when Warp agents pause with incomplete output (local sqlite/AppleScript hook).

clean-pr. Public Codex skill: clean-pr

cartographer. Public Codex skill: cartographer

turborazor. Public Codex skill: turborazor