← ClaudeAtlas

veri-did-it-worklisted

The learning gate: after the work orders ship, the questions a receipt cannot answer. Use it when the shipping is finished and the verdict is not: "did the caching work actually move p95 latency to the target REQ-028 declared?", "we shipped the onboarding rewrite six weeks ago — did it actually help activation?", "all of REQ-035's work orders are done, was the bet right or do we retire it?". It keeps three questions apart — criteria met, constraints still holding, and what the declared metric did against its target — reaches one of four verdicts including inconclusive, and files reality's answer as an outcome source linked to the bet and to the work that shipped, without applying it to the requirement. Not for checking code against its spec before anything ships: "go through the diff on the wo-118 branch against its work order before I mark it done", "WO-124's acceptance criteria are all ticked — check whether we actually did what we said" are veri:review's, because nothing has shipped and there is no outcome
danielyayla/veri · ★ 0 · AI & Automation · score 64
Install: claude install-skill danielyayla/veri
<!-- generated by `veri skills install` — do not edit; edit the method document instead --> This file is a pointer, not the method. The method is the Veri document **MET-008**, at `veri/methods/did-it-work.md`. Before doing anything else, read it: fetch `MET-008` with the `get_document` MCP tool, or open the file. Follow what it says; nothing in this file substitutes for it. This gate cannot run without these MCP tools: `file_source`, `get_document`, `get_neighbors`, `get_receipts`, `run_check`. If any is missing from the connected Veri server, stop and say which one — never interview a user and then have nowhere to file the result. Everything filed here is `draft`/`proposed`. Promotion is the user's act (REQ-008).