- name
SKILL.md
The skill file stays in the publisher's repository.
Paste the copied command in a terminal. It installs this SKILL.md into that agent.
npx skills add MiniMax-AI/mcode-stack --skill evidence-first-review -a cursor -yPaste the copied command in a terminal. It installs this SKILL.md into that agent.
npx skills add MiniMax-AI/mcode-stack --skill evidence-first-review -a claude-code -yPaste the copied command in a terminal. It installs this SKILL.md into that agent.
npx skills add MiniMax-AI/mcode-stack --skill evidence-first-review -a codex -yPaste the copied command in a terminal. It installs this SKILL.md into that agent.
npx skills add MiniMax-AI/mcode-stack --skill evidence-first-review -a grok -ySend the copied message in a Grok Bot chat. The Bot fetches this SKILL.md from GitHub and adds it to the skills all your Bots share.
Install this skill: https://github.com/MiniMax-AI/mcode-stack/tree/HEAD/stacks/ronny/skills/evidence-first-reviewFrom the publisher
"All tests pass, ready to merge" is a claim, not evidence. We read what the agent actually ran before we read what it says about it. The bar for accepting the work: we could defend it to the person who will maintain it, and we can say what our checks would miss.
This skill is about owning the result. For a clean-context code review of the
diff itself, pair it with independent-review.
Open the transcript or tool log, not the final message. For each command that supports "done": did it run on the final code, did it exit 0, does the output say what the summary says? Typical gaps we find:
-t compaction that skipped the suite that matters;If we cannot fill the right column, we do not understand the check yet.
Ask the agent: which defaults did you pick, what did you leave out of scope, and where did you reinterpret the requirement because two parts clashed? These are the choices that end up in production without anyone deciding them. Each one is accepted, changed or sent back.
Ask: what would have to be true for this to be wrong? Then check that one thing ourselves. For analysis and docs, open two of the cited sources and recompute one number the conclusion depends on.
When we report the work to others, we lead with the evidence (commands and results), then: what was checked, one thing that was not, and the key decisions.
Review an agent's finished work by reading the evidence before its summary, naming what each check proves and what it misses, pulling out the decisions it made silently, and trying to falsify the resu
---name: evidence-first-reviewdescription: Review an agent's finished work by reading the evidence before its summary, naming what each check proves and…---# stacks/ronny/skills/evidence-first-review/SKILL.mdOverview
Review an agent's finished work by reading the evidence before its summary, naming what each check proves and what it misses, pulling out the decisions it made silently, and trying to falsify the result before accepting it. Use when a MiniMax Code session, subagent or cloud agent reports a task done, before merging its PR or acting on its analysis.
FAQ
Download stacks/ronny/skills/evidence-first-review/SKILL.md from the publisher, or copy the path and open the repository. PlugMCP lists the skill and does not host the file.
The publisher keeps it at https://github.com/MiniMax-AI/mcode-stack.
Claude, Cursor, Codex, and Grok Build can read a SKILL.md you add from the publisher's repository. Grok Bot installs it when you send the skill's GitHub folder link in a chat.