principle-sequence-verifiable-units
Break multi-step work into small units that each end in a checkable green state. Use for sweeps, migrations, repeated edits, long agent runs, or commit/PR stacks where batching would hide the first failure.
- License 许可
- MIT
- 所属仓库
- caezium/skills
- 最近更新
- 2026-08-24
- Stars
- ★ 3
- Forks
- 0
01 前言 Front Matter
- name
- principle-sequence-verifiable-units
- description
- Break multi-step work into small units that each end in a checkable green state. Use for sweeps, migrations, repeated edits, long agent runs, or commit/PR stacks where batching would hide the first failure.
02 资源文件 1
- 许可证LICENSE1.0 KB
03 SKILL.md 正文
Sequence verifiable units
Order work as a chain of small units. Each unit starts from a known state, makes one coherent change, and ends with a check before the next begins.
Execution
- Establish the real baseline.
- Choose the smallest unit with a meaningful observable predicate.
- Change only that unit.
- Run the predicate and retain its result.
- Advance only when green; if red, repair or revert before stacking more work.
A rerunnable lever can make per-unit checks cheap, but it does not justify deferring them to the end. Record unit status when work spans sessions or workers.
Delivery
Order commits or PRs so a reviewer can replay the argument. Useful shapes include:
- failing regression test, then fix;
- baseline artifact, then treatment and comparison;
- subtraction of obsolete code, then the simpler replacement;
- scaffold that stands alone, then the feature.
Every unit must build or otherwise satisfy the repository's own merge predicate on its own. Completion means every requested unit is accounted for, every check is attached to the unit that caused it, and no later work rests on an unresolved red state.
<!-- Adapted from poteto/pstack principle-sequence-verifiable-units, MIT License, Lauren Tan, cursor/plugins@51a96e0. -->
04 同仓库更多 Skills
writing-for-agents
Writing documents for agents. Use when creating or editing skills, or modifying AGENTS.md or CLAUDE.md.
wrangler
Cloudflare Workers CLI for deploying, developing, and managing Workers, KV, R2, D1, Vectorize, Hyperdrive, Workers AI, Containers, Queues, Workflows, Pipelines, and Secrets Store. Load before running wrangler commands to ensure correct syntax and best practices. Biases towards retrieval from Cloudflare docs over pre-trained knowledge.
workers-best-practices
Reviews and authors Cloudflare Workers code against production best practices. Load when writing new Workers, reviewing Worker code, configuring wrangler.jsonc, or checking for common Workers anti-patterns (streaming, floating promises, global state, secrets, bindings, observability). Biases towards retrieval from Cloudflare docs over pre-trained knowledge.
wizard
Generate an interactive bash wizard that walks a human through steps only they can perform. Use when provisioning infrastructure, setting up credentials or CI secrets, walking an unfamiliar third-party dashboard, or running a one-off migration or cutover. Don't invoke this for steps the agent can perform itself.
why
Use for 'why does X work this way', 'why we picked Y', design rationale, regressions, postmortems, or data-backed thresholds. Discovers available evidence sources, searches each relevant category, and returns a cited read on decisions and tradeoffs. Use how for runtime behavior.
week-prep
Generate a briefing with calendar, tasks, and attention flags. Use for "week prep", "briefing", or "what's on this week".