agent-md-refactor
"Refactor bloated AGENTS.md, CLAUDE.md, COPILOT.md, or similar agent instruction files to follow progressive disclosure principles.
Skill by jsoehner
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/jsoehner-agent-md-refactor
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: agent-building
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/agent-md-refactor
What's inside
- Skill name
agent-md-refactor- Description
- "Refactor bloated AGENTS.md, CLAUDE.md, COPILOT.md, or similar agent instruction files to follow progressive disclosure principles. Splits monolithic files into organized, linked documentation. Use when user asks to: (1) split agent instructions, (2) refactor AGENTS.md/CLAUDE.md, (3) progressive disclosure for instructions, (4) clean up agent config." "Refactor bloated AGENTS.md, CLAUDE.md, COPILOT.md, or similar agent instruction files to follow progressive disclosure principles. Splits monolithic files into organized, linked documentation. Use when user asks to: (1) split agent instructions, (2) refactor AGENTS.md/CLAUDE.md, (3) progressive disclosure for instructions, (4) clean up agent config."
- License
- MIT
- Instructions
- 326 lines in SKILL.md · view on GitHub
Files (3)
- .openskills.json
- README.md
- SKILL.md
SKILL.md (first lines)
# Agent MD Refactor
Refactor bloated agent instruction files (AGENTS.md, CLAUDE.md, COPILOT.md, etc.) to follow **progressive disclosure principles** - keeping essentials at root and organizing the rest into linked, categorized files.
---
## Triggers
Use this skill when:
- "refactor my AGENTS.md" / "refactor my CLAUDE.md"
- "split my agent instructions"
- "organize my CLAUDE.md file"
- "my AGENTS.md is too long"
- "progressive disclosure for my instructions"
- "clean up my agent config"
---
## Quick Reference
| Phase | Action | Output |
|-------|--------|--------|
| 1. Analyze | Find contradictions | List of conflicts to resolve |
| 2. Extract | Identify essentials | Core instructions for root file |
| 3. Categorize | Group remaining instructions | Logical categories |
| 4. Structure | Create file hierarchy | Root + linked files |
| 5. Prune | Flag for deletion | Redundant/vague instructions |
---
## Process
### Phase 1: Find Contradictions
Identify any instructions that conflict with each other.
**Look for:**
- Contradictory style guidelines (e.g., "use semicolons" vs "no semicolons")
- Conflicting workflow instructions
- Incompatible tool preferences
- Mutually exclusive patterns
**For each contradiction found:**
```markdown
## Contradiction Found
**Instruction A:** [quote]
**Instruction B:** [quote]
**Question:** Which should take precedence, or should both be conditional?
```
Ask the user to resolve before proceeding.
---
### Phase 2: Identify the Essentials
Extract ONLY what belongs in the root agent file. The root should be minimal - information that applies to **every single task**.
**Essential content (keep in root):**
| Category | Example |
|----------|---------|
| Project description | One sentence: "A React dashboard for analytics" |
| Package manager | Only if not npm (e.g., "Uses pnpm") |
| Non-standard commands | Custom build/test/typecheck commands |
| Critical overrides | Things that MUST override defaults |
| Universal rules | Applies to 100% of tasks |
**NOT essential (move to linked files):**
- Language-specific conventions
- Testing guidelines
- Code style details
- Framework patterns
- Documentation standards
- Git workflow details
---
### Phase 3: Group the Rest
Organize remaining instructions into logical categories.
**Common categories:**
| Category | Contents |
|----------|----------|
| `typescript.md` | TS conventions, type patterns, strict mode rules |
| `testing.md` | Test frameworks, coverage, mocking patterns |
| `code-style.md` | Formatting, naming, comments, structure |
| `git-workflow.md` | Commits, branches, PRs, reviews |
| `architecture.md` | Patterns, folder structure, dependencies |
| `api-design.md` | REST/GraphQL conventions, error handling |
| `security.md` | Auth patterns, input validation, secrets |
| `performance.md` | Optimization rules, caching, lazy loading |
**Grouping rules:**
1. Each file should be self-contained for its topic
2. Aim for 3-8 files (not too granular, not too broad)
3. Name files clearly: `{topic}.md`
4. Include only actionable instructions
---
### Phase 4: Create the File Structure
**Output structure:**
```
project-root/
├── CLAUDE.md (or AGENTS.md) # Minimal root with links
└── .claude/ # Or docs/agent-instructions/
├── typescript.mdFrom jsoehner/skills-backup, MIT.
More from jsoehner/skills-backup
- 0.589score
alloydb-omni-access-control
jsoehner
Use these skills when you need to manage user roles, inspect permissions, and verify security-related configuration parameters.
SkillAFreshness: A★ 1Claude Code +9 - 0.589score
alloydb-omni-data
jsoehner
Use these skills when you need to explore the database structure, identify schema objects like views and triggers, and execute SQL queries to interact with…
SkillAFreshness: A★ 1Claude Code +9 - 0.589score
alloydb-omni-health
jsoehner
Use these skills when you need to audit database health, identify storage bloat, find broken indexes, and verify tablespace or maintenance configurations.
SkillAFreshness: A★ 1Claude Code +9 - 0.589score
alloydb-omni-monitor
jsoehner
Use these skills when you need to troubleshoot production issues by identifying locks, tracking long-running transactions, and getting a high-level view of…
SkillAFreshness: A★ 1Claude Code +9 - 0.584score
alloydb-omni-container
jsoehner
You're an expert in AlloyDB Omni running in a container.
SkillAFreshness: A★ 1Claude Code +9 - 0.582score
adr-lifecycle-management
jsoehner
Manage the lifecycle states (Proposed, Accepted, Superseded, Deprecated) and directory structure of Architectural Decision Records.
SkillAFreshness: A★ 1Claude Code +9 - 0.582score
algorithmic-art
jsoehner
Generates high-fidelity interactive algorithmic/generative art using p5.js based on custom-developed aesthetic philosophies and custom UI parameter tuning.
SkillAFreshness: A★ 1Claude Code +9 - 0.582score
adr-governance-orchestrator
jsoehner
Orchestrates the complete lifecycle of Architectural Decision Records (ADRs).
SkillAFreshness: A★ 1Claude Code +9 - 0.582score
adr-authoring
jsoehner
Guide the selection of ADR templates (e.g., MADR, Nygard, Y-Statement) and author high-quality Architectural Decision Records that focus on context…
SkillAFreshness: A★ 1Claude Code +9 - 0.582score
adr-discovery
jsoehner
Proactively identify when a design choice or codebase change requires documenting an Architectural Decision Record (ADR) based on Architecturally Significant…
SkillAFreshness: A★ 1Claude Code +9 - 0.575score
alloydb-omni-kubernetes
jsoehner
You're an expert in AlloyDB Omni Operator running in Kubernetes.
SkillAFreshness: A★ 1Claude Code +9 - 0.575score
adr-gatekeeper
jsoehner
This skill manages the enforcement and auditing of Architectural Decision Records (ADRs) within the project.
SkillAFreshness: A★ 1Claude Code +9
Signals
- Stars
- 1
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Oct 10, 2026 (18 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/jsoehner/skills-backup
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from jsoehner
- 0.589score
alloydb-omni-health
jsoehner
Use these skills when you need to audit database health, identify storage bloat, find broken indexes, and verify tablespace or maintenance configurations.
SkillAFreshness: A★ 1Claude Code +9 - 0.589score
alloydb-omni-monitor
jsoehner
Use these skills when you need to troubleshoot production issues by identifying locks, tracking long-running transactions, and getting a high-level view of…
SkillAFreshness: A★ 1Claude Code +9 - 0.589score
alloydb-omni-access-control
jsoehner
Use these skills when you need to manage user roles, inspect permissions, and verify security-related configuration parameters.
SkillAFreshness: A★ 1Claude Code +9 - 0.589score
alloydb-omni-data
jsoehner
Use these skills when you need to explore the database structure, identify schema objects like views and triggers, and execute SQL queries to interact with…
SkillAFreshness: A★ 1Claude Code +9 - 0.584score
alloydb-omni-container
jsoehner
You're an expert in AlloyDB Omni running in a container.
SkillAFreshness: A★ 1Claude Code +9 - 0.582score
adr-lifecycle-management
jsoehner
Manage the lifecycle states (Proposed, Accepted, Superseded, Deprecated) and directory structure of Architectural Decision Records.
SkillAFreshness: A★ 1Claude Code +9
Cite this page
agent-md-refactor skill. Agent Mart. https://agentmart.dev/skills/jsoehner-agent-md-refactor (last updated 2026-10-24)