← 返回 Skills 市场
desmondforward

Seven-Step Rigor

作者 Anthony Young · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ✓ 安全检测通过
20
总下载
1
收藏
0
当前安装
2
版本数
在 OpenClaw 中安装
/install seven-step-rigor
功能描述
Enforces a strict seven-step improvement process: clarify goals, delete unnecessary parts, simplify, speed up cycles, automate stable tasks, prefer end testi...
使用说明 (SKILL.md)

Seven Step Rigor

Use this skill to keep improvement work in the right order. Do not jump to speed, automation, or extra checks before proving the thing should exist and is shaped correctly.

Operating rule

Follow these stages in order:

  1. Make the requirements less dumb.
  2. Delete the part or process.
  3. Simplify or optimize only what survives.
  4. Accelerate cycle time.
  5. Automate.
  6. Prefer end-process testing when possible.
  7. Keep the human briefed, briefly.

If the task is small, compress the write-up, but keep the ordering.

Required working format

For substantial work, structure thinking and execution around these fields:

  • Outcome: what success changes in the world
  • Constraints: safety, scope, compatibility, reversibility, and time limits
  • Success test: the smallest clear check that proves the job worked
  • Deletion candidates: what can be removed entirely
  • Survivors to simplify: what remains after deletion
  • Cycle-time move: the feedback-loop improvement worth making
  • Automation decision: what, if anything, is stable enough to automate
  • Test-placement decision: why end-process checks are enough, or why an in-process guard must stay
  • Checkpoint: what changed, why, evidence, next risk

Stage instructions

1) Make the requirements less dumb

Rewrite the ask as outcome, constraints, and success test.

Challenge:

  • inherited assumptions
  • decorative requirements
  • legacy habits
  • work that exists only because "that is how it is done"

Ask at most one high-information question when a wrong assumption would be costly. Otherwise make the safest reasonable assumption and proceed.

2) Delete the part or process

Attempt subtraction before improvement.

Look for removable:

  • steps
  • prompts
  • branches
  • handoffs
  • tests
  • approvals
  • wrappers
  • dependencies
  • duplicate status updates

Keep a short note of what was deleted and why. Apply deletion pressure hard enough that some things occasionally need to be restored later.

3) Simplify or optimize only what survives

Only now simplify structure, wording, state, interfaces, or dependencies.

Prefer:

  • fewer branches
  • fewer moving parts
  • fewer state transitions
  • tighter prompts
  • simpler interfaces
  • convergent logic over special cases

Do not optimize anything whose existence is still in doubt.

4) Accelerate cycle time

After the shape is right, shorten feedback loops.

Prefer:

  • smaller batches
  • earlier proof of correctness
  • the smallest meaningful verification gate
  • faster local checks before heavier validation

Speed is useful only after direction is credible.

5) Automate

Automate only stable, repetitive, well-understood work.

Automation must be:

  • reversible
  • inspectable
  • scoped to a proven need

Do not automate ambiguity, churn, or waste.

6) Prefer end-process testing when possible

Default to the latest reliable test that catches the real failure.

Remove in-process checks that only add latency unless they prevent:

  • expensive damage
  • safety issues
  • materially faster diagnosis

Every test or gate must earn its cost.

7) Keep the human briefed, briefly

Send concise checkpoints with:

  • what changed
  • why
  • evidence
  • next risk

Avoid narration spam. One solid update beats many fragments.

Default execution checklist

Use this checklist for substantial work:

  • requirement rewrite
  • deletion candidates
  • simplification decision
  • cycle-time decision
  • automation decision
  • test-placement decision
  • brief checkpoint with verification

Quality bar

A good result from this skill usually shows these traits:

  • at least one assumption was challenged or removed
  • deletion was considered before optimization
  • automation was deferred unless stability was demonstrated
  • verification matched the real failure mode
  • the final update was brief but evidence-backed
安全使用建议
This skill appears safe to install as a procedural aid. When using it on important systems, review any suggested deletions, simplifications, or automation before applying them, but the artifacts do not show suspicious behavior.
功能分析
Type: OpenClaw Skill Name: seven-step-rigor Version: 1.0.0 The skill bundle defines a procedural framework for an AI agent to follow when performing optimization or refactoring tasks. The instructions in SKILL.md focus on lean engineering principles—such as challenging assumptions, deleting unnecessary components, and ensuring automation is stable and reversible—while explicitly requiring the agent to consider safety, scope, and human briefing. No malicious code, data exfiltration attempts, or harmful prompt-injection patterns were identified.
能力评估
Purpose & Capability
The stated purpose and SKILL.md content align around a seven-step improvement workflow; no runtime capabilities are requested.
Instruction Scope
The instructions guide ordering of analysis and include safety, scope, reversibility, and verification considerations; they do not show tool forcing, hidden authority, or goal redirection outside the skill purpose.
Install Mechanism
No install specification, code files, required binaries, environment variables, or credentials are present.
Credentials
The skill does not request filesystem, network, account, shell, or device access.
Persistence & Privilege
No persistence, background execution, privileged access, memory storage, or credential use is described.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install seven-step-rigor
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /seven-step-rigor 触发
  4. 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v0.1.0
Initial release with stronger trigger metadata for improvement, redesign, refactor, and automation sequencing work.
v1.0.0
Initial release of seven-step-rigor skill. - Enforces a strict seven-step sequence for all improvement work: clarify requirements, delete, simplify, accelerate, automate, validate, and summarize. - Provides clear guidance and checklists for each stage, ensuring deletion and simplification are prioritized before automation or optimization. - Includes structured formats for outcome, constraints, success tests, and checkpoints. - Optimized for workflows involving process improvements, refactoring, automation, or rethinking operations. - Encourages brief, evidence-backed human updates and evidence-based decisions at every stage.
元数据
Slug seven-step-rigor
版本 1.0.0
许可证 MIT-0
累计安装 0
当前安装数 0
历史版本数 2
常见问题

Seven-Step Rigor 是什么?

Enforces a strict seven-step improvement process: clarify goals, delete unnecessary parts, simplify, speed up cycles, automate stable tasks, prefer end testi... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 20 次。

如何安装 Seven-Step Rigor?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install seven-step-rigor」即可一键安装,无需额外配置。

Seven-Step Rigor 是免费的吗?

是的,Seven-Step Rigor 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

Seven-Step Rigor 支持哪些平台?

Seven-Step Rigor 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。

谁开发了 Seven-Step Rigor?

由 Anthony Young(@desmondforward)开发并维护,当前版本 v1.0.0。

💬 留言讨论