Improve Claude Md
This takes your bloated CLAUDE.md and rewrites it using conditional `<important if>` blocks to fight instruction dilution. The problem: Claude Code tells the model that context "may or may not be relevant," so it ignores chunks of your instructions. The fix: wrap domain-specific rules in XML conditions that mirror Claude's own system prompt structure, keeping foundational context bare at the top. It strips out linter territory, deletes stale code snippets, and splits broad rule lists into targeted blocks. You end up with a leaner file where every instruction has an explicit relevance trigger. Worth running if your CLAUDE.md is over 200 lines or you notice Claude ignoring half your guidelines.
- skills.sh installs
- 240
- GitHub stars
- 53
- last updated
- Aug 21, 2026
Install
$ npx -y skills add dexhorthy/slopfiles --skill improve-claude-md --agent claude-codeInstalls into .claude/skills of the current project.
Files
When the user provides a CLAUDE.md file (or asks you to improve one), rewrite it following the principles and structure below.
Core Problem
Claude Code injects a system reminder with every CLAUDE.md that says:
"this context may or may not be relevant to your tasks. You should not respond to this context unless it is highly relevant to your task."
This means Claude will ignore parts of your CLAUDE.md it deems irrelevant. The more content that isn't applicable to the current task, the more likely Claude is to ignore everything — including the parts that matter.
Solution: <important if="condition"> Blocks
Wrap conditionally-relevant sections of the CLAUDE.md in <important if="condition"> XML tags. This exploits the same XML tag pattern used in Claude Code's own system prompt, giving the model an explicit relevance signal that cuts through the "may or may not be relevant" framing.
Principles
1. Foundational context stays bare, domain guidance gets wrapped
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageDetails
- Repository
- github.com/dexhorthy/slopfiles
- First seen
- Jun 3, 2026
Recommended
cavemanjuliusbrussee/cavemanUltra-compressed communication mode. Cuts output tokens 65% (measured) by speaking like caveman while keeping full technical accuracy. Supports intensity levels618.3Kskills.sh installs
improveshadcn/improveSurvey any codebase as a senior advisor and produce prioritized, self-contained implementation plans for OTHER models/agents to execute. Strictly read-only on s40Kskills.sh installs
systematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes326.7Kskills.sh installs
karpathy-guidelinesforrestchang/andrej-karpathy-skillsBehavioral guidelines to reduce common LLM coding mistakes through explicit assumptions, simplicity, and verifiable success criteria.17.9Kskills.sh installs
find-skillsvercel-labs/skillsHelps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express int4.3Mskills.sh installs