lousy-agentslousy-agents/skills/CLAUDE.md

skills

CLAUDE.md1 starsChanged 58 days agoBSD-2-ClauseView on GitHub

@.github/copilot-instructions.md

In this repository18 other files it gives its agents.
- AGENTS.mdAGENTS.md
- .github/copilot-instructions.mdCopilot instructions
- code-tidySkill
- curate-releaseSkill
- customer-strategy-forgeSkill
- designing-for-intentSkill
- feature-to-planSkill
- go-testable-designSkill
- instruction-styleSkill
- issue-refine-loopSkill
- mutation-hunterSkill
- optimize-prompt-loopSkill
- plan-to-graphSkill
- rugged-evil-testerSkill
- skill-reviewerSkill
- spec-auditorSkill
- to-earsSkill
- triaging-pr-reviewsSkill

The file

We split this CLAUDE.md into the rules it gives an agent

4 rules. About 0 are common, 0 are distinctive, and 4 are very specific to this project.

≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
4
Very specific
Tied to their project's names, files or tools. Probably skip.

Common
Distinctive
Very specific

Very specific:
When updating project conventions, pull request requirements, or core mandates, you MUST apply those changes to …
line 9
Very specific:
Follow the guidelines in the imported instructions for evaluating and linting your work using MCP tools and the skill-reviewer skill.
line 13
Very specific:
Run the lint suite via the Bash tool: npx -y @lousy-agents/cli lint.
line 17
Very specific:
Use the lousy-agents MCP server tools directly when you need fine-grained signals: mcp__lousy-agents__analyze_instruction_quality, …
line 19

≈ “Common” is an estimate: at least 1 in 5 of the 26,980 CLAUDE.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.

Files

CLAUDE.md

Lousy Agents Skills — Claude Code Context

⚠️ Source of Truth

The foundational mandates, core philosophy, and strict negative constraints for this repository are managed centrally and imported below.

@.github/copilot-instructions.md

Agentic Parity Mandate

When updating project conventions, pull request requirements, or core mandates, you MUST apply those changes to .github/copilot-instructions.md rather than this file. This file should only contain Claude-specific operational instructions.

Claude Workflow Instructions

Utilize the .claude/settings.local.json file for any local Claude configurations as needed.
Follow the guidelines in the imported instructions for evaluating and linting your work using MCP tools and the skill-reviewer skill.

Commands

Claude-specific tool surfaces for the canonical commands documented in .github/copilot-instructions.md:

Run the lint suite via the Bash tool: npx -y @lousy-agents/cli lint.
Invoke the skill-reviewer skill via the Skill tool (it is listed in the available-skills surface).
Use the lousy-agents MCP server tools directly when you need fine-grained signals: mcp__lousy-agents__analyze_instruction_quality, mcp__lousy-agents__validate_instruction_coverage, mcp__lousy-agents__analyze_action_versions, etc.