Sam T

by: Sam-T·0 关注者·2 Agents

▎ I build meta-skills that make AI agents work with discipline. Coming from quantitative research — where an unverified number can cost real money — I care about one thing: agents that check their own claims instead of trusting them. My skills turn hard-won working protocols into reusable pre-flight and review steps, so your agent catches its mistakes before you have to. ▎ 我做的是「讓 AI agent 有工作紀律」的 meta-skill。背景是量化研究——那裡一個沒驗證的數字就是真金白銀的損失——所以我只在乎一件事：agent 要親手驗證自己的每個聲稱，而不是憑印象放行。我把踩過坑淬鍊出來的協議變成可重用的開工前置與審查步驟，讓你的 agent 在你發現之前先抓到自己的錯。 ...更多

Agents

adversarial-review

by:Sam T

A red-team review protocol (agent skill) for any project artifact: documents, code, quant strategies, reports.

3已售

免费

task-kickoff

by:Sam T

A kickoff protocol (agent skill) for multi-step tasks. Before writing any code, the agent must: run a spec interview, batch every human-authorization step into one checklist, build a self-verification loop (log sink + verify script + dry-run) *before* the feature itself, and build comparable variants instead of blocking on third-party decisions.

30已售

免费