4x founding hire at early-stage startups. I build operational infrastructure from scratch, increasingly with AI tools.
Now: Building AI product at Zero Gravity. Scaled ops 0-1 at Flash Pack (pre-seed to Series A), co-founded MealsForTheNHS (Β£1.8m raised, 303k meals), built regulated workflows at Farewill (SRA/FCA).
Recent: Just Now Possible with Teresa Torres β building AI products that augment human relationships, not replace them.
Background: Languages BA (Birmingham/Fudan) β French & English (native), Spanish (fluent), Chinese (intermediate). BlueDot Impact AI Governance & Alignment.
Tools for the AI-assisted development workflow. I use Claude Code daily to ship production code β these came from scratching my own itches.
| Project | What it does | Why it exists |
|---|---|---|
| π§ͺ Claude-Skill-Potions | Curated Claude Code skills for ops and product workflows | The skills directory is 40K+ deep. These are the ones that actually work. 51 stars |
| π zeste | macOS menubar app β search, install, and manage Claude Code skills | Finding and installing skills shouldn't require digging through GitHub |
| π claudemd-lint | Linter for CLAUDE.md files | Catches vague rules, bloated configs, and instructions that should be hooks |
| πͺ hooksmith | Browse and install pre-built Claude Code hooks with one command | 12 hooks, zero config. The missing package manager for CC hooks |
Domain expertise baked into tools that any AI assistant can use.
| Project | What it does | Why it exists |
|---|---|---|
| π conveyancing-mcp-server | UK homebuying assistant β stamp duty, title registers, searches, surveys, leasehold checks | Buying a house involves 15 weeks of opaque legal process. 6 tools, 95 tests, covers England, Scotland & Wales |
| π‘ hiresignal | Open spec + MCP server for AI-queryable professional profiles | Recruiting agents need structured candidate data, not scraped LinkedIn |
| ποΈ vox | Open-source Voice of Customer research agent | 8 days of PM research in 8 minutes. JTBD, personas, opportunity mapping from Gong/Granola/Jiminy data |
| Project | What it does | Why it exists |
|---|---|---|
| 𧬠claude-eval-toolkit | Evaluation framework for Claude-powered apps β evals, guardrails, deployment patterns | Test your AI before it reaches users. 69 test cases, LLM-as-judge grading, UK education safeguarding (KCSIE/Prevent) |
| Project | What it does |
|---|---|
| ε’¨ mo-hanzi | menubar SRS for learning Chinese characters (HSK 1-3) |
| π plod | A calm running app that cares about your health, not your PBs. PWA with Strava sync |
| π§ spotifyunwrapped | Your Spotify data, visualised properly. Privacy-first analytics, runs entirely in your browser |
- What I Learned Spending A Week With 100+ AI Leaders
- What I Learned Shipping AI to Users Who Can't Afford Bad Advice
- Amsterdam Built the 'Perfect' Ethical AI System. It Still Failed.
- The Trust Gap: Why Your AI Product Will Fail Without This
- Claude Keeps Making the Same Mistakes. So I Started Writing Down the Fixes.
