- name
SKILL.md
File skill tetap berada di repositori penerbit.
Tempel perintah yang disalin di terminal. Perintah itu memasang SKILL.md ini ke agen tersebut.
npx skills add sno-ai/sno-station-skills --skill skill -a cursor -yTempel perintah yang disalin di terminal. Perintah itu memasang SKILL.md ini ke agen tersebut.
npx skills add sno-ai/sno-station-skills --skill skill -a claude-code -yTempel perintah yang disalin di terminal. Perintah itu memasang SKILL.md ini ke agen tersebut.
npx skills add sno-ai/sno-station-skills --skill skill -a codex -yTempel perintah yang disalin di terminal. Perintah itu memasang SKILL.md ini ke agen tersebut.
npx skills add sno-ai/sno-station-skills --skill skill -a grok -yKirim pesan yang disalin di chat Grok Bot. Bot mengambil SKILL.md ini dari GitHub dan menambahkannya ke skill yang dipakai bersama oleh semua Bot Anda.
Install this skill: https://github.com/sno-ai/sno-station-skills/tree/HEAD/skills/J-peer-review-and-audit/agentic-walkthrough/skillDari penerbit
The stance is the whole method. You are not a reviewer standing outside the code with a checklist; you are the thing the source describes — the job, the stage, the handler — and you run it in your head, hop by hop, exactly as it would run, noticing every switch you pass and every place your output goes. Only then do you turn to the real system and make it show you that what you just walked actually happened. The principle: BE the executor, then make the executor prove itself.
Ordinary debugging starts from a failure — an error, a red test, a wrong number. This starts from the opposite and much quieter case: everything reports success and you still do not know whether the work happened.
That case is real and it is not rare. A stage that cannot do its work can still report done. A
job can start, finish, write a trace, and pass its own verification while touching nothing. No
test suite catches this, because no assertion in the suite is false.
Three moves, in order. How far to take each is your judgment — often the first cannot finish without the ones after it.
Put yourself where the code sits and go hop by hop from entry point to effect. You are reading, not executing, which is the whole point: a live run cannot show you the branch it never took.
Three questions at each hop are usually enough:
The last hop is the one everyone skips and it is usually the decisive one: is this output visible to whatever consumes it downstream? A stage that runs perfectly and writes where nothing reads is indistinguishable from a stage that never ran. Check the reader's path, not the writer's — they are frequently not the same file, the same directory, or the same database.
Where to start and how deep to go is judgment. Go where the switches are dense, or where the evidence gets thin.
The walk tells you which hops matter. A probe is how you make one of them prove itself.
Keep each probe narrow: one observable that only the real thing could have produced. A broad health check is worth little here, because everything passes it — that is the whole problem. The walk already told you what this hop is supposed to do; probe exactly that.
These classes come up again and again, and each fails in a way that looks fine from the caller's side. Treat them as places to look, not a checklist to complete.
if (ok) check. Zero calls is the loudest
possible answer and the easiest one to miss.This is the one part worth being strict about, because it is what separates a gate from a reading exercise.
Finish with a number a no-op could not have produced, plus the line where each action happens. N rows changed, M requests sent, and here is where I can see those N rows differ.
Most wrong conclusions here come from a check that could never have said anything else. Prove your check could have produced the other answer — feed it a case you know is positive and watch it fire. Shapes this actually takes:
grep -c against a path that does not exist returns 0, identical to a real file with no
matches. Confirm the path exists before the count means anything.Prove that a reported run caused its intended real effect. Walk the executor path from entry to effect, capture one observable per hop, and report a result a no-op could not produce.
---name: agentic-walkthroughdescription: Prove that a reported run caused its intended real effect. Walk the executor path from entry to effect…---# skills/J-peer-review-and-audit/agentic-walkthrough/skill/SKILL.mdFAQ
Unduh skills/J-peer-review-and-audit/agentic-walkthrough/skill/SKILL.md dari penerbit, atau salin path-nya dan buka repositori. PlugMCP hanya mendaftar skill ini dan tidak meng-host filenya.
Penerbit menyimpannya di https://github.com/sno-ai/sno-station-skills.
Claude, Cursor, Codex, dan Grok Build bisa membaca SKILL.md yang Anda tambahkan dari repositori penerbit. Grok Bot memasangnya saat Anda mengirim tautan folder GitHub skill tersebut di chat.