principle-prove-it-works
Prove it works. Apply when before declaring a task done, or when judging a claim that something works.
- License 许可
- MIT
- 最近更新
- 2026-11-15
- Stars
- ★ 2
- Forks
- 0
01 前言 Front Matter
- name
- principle-prove-it-works
- license
- MIT
- metadata
- { "source": "pstack principle-prove-it-works, MIT, Copyright (c) 2026 Lauren Tan, github.com/cursor/plugins, adapted; checked against pstack 0.15.36 at commit 0bb6f37" }
- description
- Prove it works. Apply when before declaring a task done, or when judging a claim that something works.
03 SKILL.md 正文
<!-- Generated by scripts/build.mjs from the sources; edit the source, then run npm run build. -->
Prove it works
Verify the result by checking the real thing directly. Do not infer it from a proxy, a self-report or "it compiles".
Why. Unverified work has unknown correctness. Indirect checks (a file's timestamp, fresh-looking output, an agent's own report, a cached screenshot) feel cheaper than direct observation, and acting on a wrong inference costs far more.
Check the real thing.
- Run the feature and inspect the diff.
- Read the actual value, not a cached or derived copy of it.
- Check that a process is alive directly, not through state derived from it.
- When a check fails, suspect the way you observed before you suspect the system.
Script the check when you can. The strongest proof is a command that re-runs the same comparison, not a one-time look. Write it, run it, and keep its output visible to the user, where a reviewer can re-run it. Commit it only when a large change, such as a port or a migration, needs a trail that someone can audit later.
Stop claiming when the evidence stops. Say what you ran and what you saw, and what you did not verify.
04 同仓库更多 Skills
writing-standard
Write at 80% of Simplified Technical English. Apply to any text an agent writes for a person: messages, reports, specs, findings, reviews, plans.
sage
The state tool of sage mode: records tasks, routes, agent runs, findings, verdicts by head SHA and the user's gates in ~/.claude/sage/<project>/. Use in sage mode for every change of a task's state, and before any merge. Claude Code only.
sage-help
Help with sage: how to set it up, switch sage mode and autopilot, read the board, answer the chief's questions, pick a skill or a principle, fix a run that went wrong, and find where sage keeps its files. The user types /sage:sage-help (or /sage-help) with a question. Load it only when the user types it; do not load it on your own. Claude Code only.
report
The report that every sage agent ends with: STATUS, RESULT, EVIDENCE, FINDINGS, QUESTIONS, NOT VERIFIED, BRANCH. Use at the end of any task that the sage chief of staff gave you. Claude Code only.
remote-control
Set up Remote Control, so that the user can follow, steer and start Claude Code sessions from the Claude app on a phone. It turns Remote Control on for every new session, and it can run a server in a folder (such as ~/workspace) that starts at each login. Use when the user asks to reach sessions or start new ones from a phone, or to set up, check or undo Remote Control. Claude Code only.
readme-guide
Write a project README. Apply when you write, change or review a README of any project, in any language.