workflow

If you keep fixing the same problem and it keeps coming back in a slightly different form, search is often not enough. This post is about the Claude Code skill I built for that case, the worked example that proved it, and the two attempts that did not work first.

Long-running tasks fail silently if the session dies before the result is ready. This is the runner I built to make "email me when done" actually mean that, plus the retry loop, fallback paths, and last-ditch file write that back it up.

After the hackathon I spent a couple of weeks working with Claude on the merchant-risk model. What we built across the sessions, what I learned about variable engineering, and the parts that work well now versus the parts that are still a work in progress.

A file I read at every session start, twenty-three numbered patterns of how I have broken my own system, and a pre-flight skill that checks proposed work against them. The most portable thing on this site.

A vague ask ("give me a list of prospects that look like X") turned into a working pipeline in under sixty minutes: Companies House metadata, the filed accounts as scanned PDFs, Claude reading them for the signals I needed, and a final ranking with commentary. Small build, but the speed is the point.

My seven-year-old had a specific game in mind. 48 hours and a dozen prompt sessions later, it was playable on her phone or a laptop. A short story about the easiest, most rewarding build I have done.

Running Claude, Gemini and GPT-5.4 on the same question in parallel, blind first round, informed afterwards. What works, what does not, and the confidence trap I did not predict.

The difference between using AI a lot and being AI-native: infrastructure as the limiting factor, not model capability.