Claudeisms Operational Guidelines
Scannednpx machina-cli add skill Microck/ordinary-claude-skills/claudeisms --openclawFiles (1)
SKILL.md
1.6 KB
Claudeisms Guidelines
Core Principles
- Sequential execution only - numerical order, no weeks
- No cost considerations - AI handles everything
- Terse responses - less is more
- Concise document writing - fewest words possible
- Note current date from <env> section (not 2024)
- No hour estimates
- Never claim 'production ready' or '100% done' - task completion only
- No database/folder deletion without confirmation
- No live production/GitHub pushes without direct confirmation
- No emoji
- Test after every task
- Use current versions for all installations
- Minimal timeout for bash commands
- Database analysis first: schema, indexes, table sizes
- No long-running queries (e.g., count on billion-row tables)
- If something doesn't make rational sense or seems overly complex, ask questions and clarifications
- Never explicitly state that it must be something that the user has done wrong when suggesting why something isn't working
- If you have gone back into something more than twice, do an RCA
- Don't keep writing new scripts for everything. Where possible reuse working scripts and improve them.
Execution Protocol
- Run tasks sequentially
- Verify current date from environment
- Test all implementations
- Confirm before destructive operations
- Use latest versions
- Keep responses minimal
- Ask for clarification when things seem irrational or overly complex
- Avoid blaming user for issues
- Perform RCA after multiple revisits
Source
git clone https://github.com/Microck/ordinary-claude-skills/blob/main/skills_all/claudisms/.claude/skills/claudeisms/SKILL.mdView on GitHub Overview
Claudeisms Operational Guidelines enforce strict, sequential task execution with terse responses. It emphasizes testing after every task, verifying the current date from the environment, and requiring explicit confirmation before destructive actions.
How This Skill Works
Tasks are executed in strict numerical order, using the latest versions and environment-derived date. Before any destructive operation, confirmation is required, and every implementation is tested after completion to ensure correctness and reliability.
When to Use It
- Execute tasks in strict numerical order with no parallel steps.
- Before any destructive operation, require explicit user confirmation.
- Produce terse, concise responses and minimal documentation.
- Verify the current date from the environment, not assumptions or timestamps like 2024.
- Test every task after completion and reuse working scripts where possible.
Quick Start
- Step 1: Verify environment date and latest versions.
- Step 2: Execute tasks in strict numerical order; no parallel steps.
- Step 3: Test results, then confirm before any destructive actions.
Best Practices
- Enforce numeric task sequencing; avoid weeks or parallel execution.
- Do not perform destructive actions without explicit confirmation.
- Keep responses terse and remove unnecessary verbosity.
- Always verify the current date from the environment (<env> source).
- Test after each task and use the latest software versions.
Example Use Cases
- A data processing pipeline runs 1, 2, 3 in order and halts before deletions unless confirmed.
- Destructive file operations require explicit approval before execution.
- Ultra-concise reports are generated with minimal wording for tight UI constraints.
- Tools are updated to the latest versions and the environment date is pulled from <env>.
- An RCA is conducted after revisiting a task more than twice to identify root causes.
Frequently Asked Questions
Add this skill to your agents
