- name
SKILL.md
技能檔案保留在發布者的儲存庫中。
在終端機中貼上複製的指令。它會將這個 SKILL.md 安裝到對應的代理中。
npx skills add Innei/ryugi --skill candidate2 -a cursor -y在終端機中貼上複製的指令。它會將這個 SKILL.md 安裝到對應的代理中。
npx skills add Innei/ryugi --skill candidate2 -a claude-code -y在終端機中貼上複製的指令。它會將這個 SKILL.md 安裝到對應的代理中。
npx skills add Innei/ryugi --skill candidate2 -a codex -y在終端機中貼上複製的指令。它會將這個 SKILL.md 安裝到對應的代理中。
npx skills add Innei/ryugi --skill candidate2 -a grok -y在 Grok Bot 聊天中傳送複製的訊息。Bot 會從 GitHub 取得這個 SKILL.md,並加入你所有 Bot 共用的技能中。
Install this skill: https://github.com/Innei/ryugi/tree/HEAD/docs/ryugi/skill-evals/2026-11-13-verifying-slim/skills/candidate2來自發布者
A claim is proved where it is about, by you, before you make it. Whatever a command can decide, you decide and show. Your human partner is asked only for what needs a person: how something looks, moves, feels, sounds or reads, and whether a trade-off is right.
REQUIRED BACKGROUND: ryugi:artifacts — its verify.md covers verify
reports (claims, output, gaps), and its artboard.md covers verify groups
for screens; both cover from, capturedAt and reading verdicts.
Two things decide it: does a person have to judge something a reply cannot show, and does the proof fit in a reply. Who reported the work does not.
A fix proved by driving a flow end to end (sync between two clients, an import, a deploy and what it serves) is a run of several steps: its log goes in a verify report, where it can be kept and linked, not into the reply. When a small row and the last row still both seem to fit, the small row wins.
Capture the broken state from the running app now, while you reproduce it. After the fix there is no honest "before".
This part always runs, at every size.
No homework. Your final message never ends with a check for your human partner to run. Verify it before you report, or list it under "Not verified" with why you cannot do it and the one thing you need from them.
Never ask permission to verify. Running the checks needs no approval. Destructive and outward-facing actions keep their usual confirmation.
When only they can act — fold a device, unlock it, a passkey, an account you have no access to — first try the tools this environment has. If none can do it, ask once: one numbered list of the exact actions, with what to reply after each. Do everything around those actions yourself.
Ask of each claim: is it judged by looking at a screen, or by reading output and numbers?
Work whose whole question is how a screen looks, moves or feels has only screen claims. What you measured or ran to back them — pixel sizes, sampled frames, the test suite, a typecheck — is your proof of those same claims, not a second kind: put it in the group's sticky or your final message. An output claim is one that would still need proving if nobody looked at a screen: an API result, data, a deploy, a number against a threshold.
Before you write a verify report or a verify page, or add a recording to
one, read pages.md in this directory and follow it.
Each check has one output location. A retry or rerun writes over the
previous result; never create numbered copies (-1, -2, -final) of
the same check. Keep two runs side by side only when the point is comparing
two builds, and name them for the builds. Delete scratch output you created
once the evidence you need is copied to the verify page.
They pass, reject, skip or say ship, in chat or on the page: read
verdicts.md in this directory before you act on it.
Done means: your proof is complete, every gap is gone or waived, and every claim and group that waits on them has passed. Until then your final message carries the link and what is waiting on whom.
Use before telling your human partner that work is done, fixed, live or ready, whatever it touched — UI, an API, a CLI, data, a deploy, performance — and before fixing a bug they can see, to capture i
---name: verifyingdescription: Use before telling your human partner that work is done, fixed, live or ready, whatever it touched — UI, an…---# docs/ryugi/skill-evals/2026-11-13-verifying-slim/skills/candidate2/SKILL.md總覽
Use before telling your human partner that work is done, fixed, live or ready, whatever it touched — UI, an API, a CLI, data, a deploy, performance — and before fixing a bug they can see, to capture it first
常見問題
從發布者下載 docs/ryugi/skill-evals/2026-11-13-verifying-slim/skills/candidate2/SKILL.md,或複製路徑後開啟儲存庫。PlugMCP 只收錄這項技能,不代管檔案。
發布者將它存放在 https://github.com/Innei/ryugi。
Claude、Cursor、Codex 和 Grok Build 可以讀取你從發布者儲存庫加入的 SKILL.md。在聊天中傳送技能的 GitHub 資料夾連結,Grok Bot 就會安裝它。
| "Pending means fine" | Pending means nobody has looked. |