I build tools that make LLM agents do careful, measurable work. Each one is developed with the first.
| Project | What it is |
|---|---|
| claude-arsenal | A Claude Code plugin marketplace: specs before code, failing tests first, gates with numbers, and a skill-authoring rubric drawn from research. |
| drawspec | Declarative diagram spec → clean, themeable SVG. JSON with no coordinates, so an LLM can write it. |
| integral-job-search | A candidate-centred job search run as a conversation in Claude Code. One dimension model carries from what you need to the interview. |
| literary-critic | Lets an LLM index, analyse and advise on a full novel manuscript like a professional editor, across drafts. The writer writes. |
| doc-control | A deterministic tool for AI agents to edit Word documents. Every change is a tracked change. (In development.) |
The other four are built with claude-arsenal's spec-driven workflow and gated task queue.



