principle-sequence-verifiable-units
Sequence verifiable units. Apply when multi-step work (a sweep, a migration, a run of similar edits) or the order of commits in a change.
- License 许可
- MIT
- 最近更新
- 2026-11-15
- Stars
- ★ 2
- Forks
- 0
01 前言 Front Matter
- name
- principle-sequence-verifiable-units
- license
- MIT
- metadata
- { "source": "pstack principle-sequence-verifiable-units, MIT, Copyright (c) 2026 Lauren Tan, github.com/cursor/plugins, adapted; checked against pstack 0.15.36 at commit 0bb6f37" }
- description
- Sequence verifiable units. Apply when multi-step work (a sweep, a migration, a run of similar edits) or the order of commits in a change.
03 SKILL.md 正文
<!-- Generated by scripts/build.mjs from the sources; edit the source, then run npm run build. -->
Sequence verifiable units
Order the work as a sequence of small units, each ending in a state you can check, and do not advance until the current one passes.
Why. A break caught at the unit that caused it is cheap to find. A break caught after a batch is buried, and you have already built on a broken base. A sequence a reviewer can replay turns "trust me" into "watch it go red, then green".
Doing the work. In a sweep, a migration or any run of similar edits, verify each change before starting the next. Each unit is a bracket: a known-good state, one change, the check, then on. Start from a clean base so every check measures against the real baseline. When a script does the edits, the per-unit check is nearly free; run it anyway.
Delivery. Order the units, and the commits that will carry them, so the sequence proves the work: the failing test first, then the fix; a removal before the reshape; a baseline capture before the treatment; the scaffold before the feature. Each unit stands on its own, and the sequence reads as an argument.
Keep each check real (see "prove it works").
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.