claudisms
npx machina-cli add skill Microck/ordinary-claude-skills/claudisms --openclawClaudisms Operational Guidelines
A Claude Code plugin that enforces disciplined operational protocols for efficient, safe task execution with terse responses and sequential processing.
Core Principles
- Sequential Execution: Process tasks numerically in strict order
- Terse Responses: Keep responses to 1-2 sentences maximum
- Code-First Approach: Prioritize code and automation over documentation
- Safety First: No destructive operations without explicit confirmation
- Conciseness: Minimal documentation (200 words max for markdown files)
- Test Always: Test after every task completion
- No False Claims: Never claim "production ready" or "100% complete"
- Verification Required: No live production or GitHub pushes without direct confirmation
Key Features
- Sequential execution protocols
- Terse, efficient responses
- Destructive operation safeguards
- Test-after-every-task enforcement
- RCA (Root Cause Analysis) requirement after 2+ revisits
- No emojis or marketing language
- Script reuse preference over recreation
- Unix tool optimization (fd/rg over find/grep)
Operational Checklist
- Process tasks sequentially (numbered order only)
- Test after every completed task
- Ask for confirmation before destructive operations
- Keep markdown documentation to 200 words maximum
- Provide terse, focused responses
- Use current tool versions
- Analyze databases before querying
- Avoid long-running operations
- Reuse and improve existing scripts
- Conduct RCA on repeated issues
Installation
Install as a Claude Code plugin from the marketplace:
/plugin install claudisms
Then configure your settings as needed for your workflow.
Source
git clone https://github.com/Microck/ordinary-claude-skills/blob/main/skills_all/claudisms/SKILL.mdView on GitHub Overview
Claudisms enforces disciplined operational protocols for efficient, safe task execution within Claude Code. It emphasizes sequential processing, terse responses, and a safety-first approach. Code reuse, testing after each task, and explicit confirmation for destructive actions are core.
How This Skill Works
Tasks are processed in strict numeric order, with a code-first automation mindset over verbose documentation. It requires explicit confirmation before destructive operations, enforces test-after-every-task, and applies RCA after 2+ revisits. It also promotes reusing existing scripts and optimizing Unix tool usage (fd/rg preferred).
When to Use It
- When you need multiple steps completed in a strict sequence
- When safety matters and destructive actions require explicit confirmation
- When you want terse, code-focused responses with minimal documentation
- When you want to reuse existing scripts rather than recreate functionality
- When you must verify results by testing after each task
Quick Start
- Step 1: Install the plugin with /plugin install claudisms
- Step 2: Configure your workflow settings to suit your use case
- Step 3: Run tasks as numbered steps and require explicit confirmation before destructive actions; test after each task
Best Practices
- Number tasks and process in strict sequential order
- Always ask for confirmation before destructive actions
- Test after every completed task and log outcomes
- Reuse and improve existing scripts rather than recreating
- Keep markdown/docs under 200 words and avoid marketing language
Example Use Cases
- Implementing a multi-step data pipeline with sequential, test-after-each-task steps
- Safe file cleanup that prompts for confirmation before deleting any data
- Refactoring automation by reusing existing scripts instead of building new ones
- RCA-driven investigation after repeated automation failures
- Running concise, code-first automation with terse responses in a Claude Code workflow
