个人作者

Jefferson J Hunt

所在地 · Missouri, USA更新于 2026-10-22

Skills
11
仓库
1
职业覆盖
1
场景覆盖
2
Stars
★ 1

Jefferson J Hunt 的 Skills 11

jeffersonjhunt
jeffersonjhunt/code-monkeys

spark-build

Build the cuda-* primate images (cuda-llama-cpp, cuda-comfy, cuda-vllm — the shared base for g.deceiver's six vLLM services) on a Blackwell GB10, freeing that box's unified memory first by stopping whatever it runs, then restarting it. NOTE the standalone coding cluster (qwen3-coder-next) was RETIRED 2026-09-05, so a "drain" is no longer a coding outage — it's a g.deceiver-service outage (hutch = memory stack; starsky = the live 27B brain, never build there mid-stream). Checks memory BEFORE stopping anything; --allow-outage / --skip-drain control the trade.

★ 1
jeffersonjhunt
jeffersonjhunt/code-monkeys

spark-bench

Run LLM evaluation harnesses (AIME 25, GPQA, LiveCodeBench v6, tau2-bench, SWE-Bench Verified via SWE-agent) against the spark-cluster from a dedicated x86 bench host (intel-nuc.tworivers). The harness runs in the spark-bench primate; only the OpenAI-compatible endpoint URL needs to change between baseline (cluster LB) and test (ad-hoc model server) runs.

★ 1
jeffersonjhunt
jeffersonjhunt/code-monkeys

secret-ops

Decrypt/encrypt this project's SOPS+age secrets and manage the private hemlighet repo. Use whenever a task reads or changes a secret — sops, age, vault, hemlighet, a *.sops file, personal/* dotfiles. Crypto runs on the configured secret host over ssh, NOT inside a primate. Host/identity come from env or ~/.config/secret-ops.conf (never hardcoded here).

★ 1
jeffersonjhunt
jeffersonjhunt/code-monkeys

sdlc

The default software development lifecycle every agent follows — intake, plan, isolate, implement, verify, review, land, deploy, observe, release. Use at the start of any coding task, and whenever deciding whether work is ready to deploy or ready to merge.

★ 1
jeffersonjhunt
jeffersonjhunt/code-monkeys

review-adversarial

Adversarial code review with structured findings and a review loop. Use when asked to critically review code, diffs, or design docs with an adversarial mindset.

代码审查
★ 1
jeffersonjhunt
jeffersonjhunt/code-monkeys

math-fibonacci

Create a fibonacci sequence, as a list, as ascii art to display the divine proportions, etc...

★ 1
jeffersonjhunt
jeffersonjhunt/code-monkeys

img-sixel

Display images as SIXEL graphics in the terminal or convert SIXEL files to PNG. Use when asked to show an image inline, render graphics in a terminal, or convert between SIXEL and PNG formats.

★ 1
jeffersonjhunt
jeffersonjhunt/code-monkeys

docs-issues

Manage markdown-based issues (bugs, features, debt, questions) in docs/reviews/ and export to GitHub, GitLab, or a todo.md index. Use when asked to track, list, create, or push issues from a docs/reviews tree.

★ 1
jeffersonjhunt
jeffersonjhunt/code-monkeys

apple-xcodebuild

Scaffold, build, test, run and screenshot iOS, iPadOS and macOS apps from a Linux container by driving xcodebuild on a macOS host over SSH. Handles single-platform and cross-platform (one multiplatform target) XcodeGen projects. Use for any Apple-platform app work where the Xcode IDE is not available — new projects, CI-style builds, running on a simulator or the Mac, or diagnosing why the Mac cannot build.

★ 1
jeffersonjhunt
jeffersonjhunt/code-monkeys

althingi

Orchestrate roundtable discussions with multiple agent voices. Use when asked to discuss, debate, or get multiple perspectives on a topic. Spawns real subagents by default; use --solo to roleplay all voices directly.

Skill与智能体开发
★ 1
jeffersonjhunt
jeffersonjhunt/code-monkeys

agent-team

Orchestrate a multi-agent development team (PM, Architect, Developer, Designer, Tester, Reviewer) through structured phases with human-in-the-loop checkpoints. Use when asked to run a project with a team, coordinate multiple agents, or build something end-to-end with role separation.

开发工程师Skill与智能体开发
★ 1