agent-md-refactor
Refactor bloated AGENTS.md, CLAUDE.md, or similar agent instruction files to follow progressive disclosure principles.
Skill by Kilo-Org
Chalk Labs
Need help deploying agent-md-refactor?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
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/kilo-org-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 and code. 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, or similar agent instruction files to follow progressive disclosure principles. Splits monolithic files into organized, linked documentation.
- License
- Apache-2.0
- Metadata
- category: development
- Instructions
- 283 lines in SKILL.md · view on GitHub
Files (4)
- LICENSE
- README.md
- SKILL.md
- local.patch
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.md
├── testing.md
├── code-style.md
├── git-workflow.md
└── architecture.md
```
**Root file template:**
```markdownFrom Kilo-Org/kilo-marketplace, Apache-2.0.
More from Kilo-Org/kilo-marketplace
- 0.795score
dynamic-tables-tutorial
Snowflake
Interactive tutorial that teaches Snowflake Dynamic Tables hands-on.
SkillAFreshness: A★ 195Claude Code +9 - 0.795score
cortex-code
Snowflake Integration Team
Routes Snowflake-related operations to Cortex Code CLI for specialized Snowflake expertise.
SkillAFreshness: A★ 195Claude Code +9 - 0.795score
dbt-analytics-engineering
dbt-labs
Builds and modifies dbt models, writes SQL transformations using ref() and source(), creates tests, and validates results with dbt show.
SkillAFreshness: A★ 195Claude Code +9 - 0.795score
database-redshift
christopher huffman
Amazon Redshift expert.
SkillAFreshness: A★ 195Claude Code +9 - 0.791score
jupyter-notebook
Kilo
Use whenever the user works with Jupyter notebooks (`.ipynb`), including creating, inspecting, editing, executing, or visualizing notebook content for…
SkillAFreshness: A★ 195Claude Code +9 - 0.791score
gcp-event-driven-architecture-review
github: Raishin
Review GCP Pub/Sub, Eventarc, Cloud Tasks, Cloud Scheduler, and Workflows designs — dead-letter topics, message ordering, idempotency, fan-out blast radius…
SkillAFreshness: A★ 195Claude Code +9 - 0.789score
dbt
dbt-labs
Skills for analytics engineering with dbt - building models, writing tests, querying the semantic layer, troubleshooting jobs, and more.
SkillAFreshness: A★ 195Claude Code +9 - 0.786score
data-investigation
Pedro / Kilo Code
A workflow for conducting rigorous, reproducible data investigations and ad-hoc analyses.
SkillAFreshness: A★ 195Claude Code +9 - 0.786score
apache-arrow
terminal-skills
Expert guidance for Apache Arrow, the cross-language columnar memory format for analytics workloads.
SkillAFreshness: A★ 195Claude Code +9 - 0.786score
dagster
terminal-skills
Dagster is a data pipeline orchestrator built around the concept of software-defined assets.
SkillAFreshness: A★ 195Claude Code +9 - 0.786score
cassandra
terminal-skills
Apache Cassandra is a distributed NoSQL database designed for high availability and linear scalability.
SkillAFreshness: A★ 195Claude Code +9 - 0.786score
prefect
terminal-skills
Prefect is a modern workflow orchestration framework for Python data pipelines.
SkillAFreshness: A★ 195Claude Code +9
Signals
- Stars
- 195
- Forks
- 328
- Open issues
- 18
- Last commit (this folder)
- Jun 24, 2026 (4 months ago)
- Last release
- Sep 28, 2026 (1 month ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- Apache-2.0
- Repository
- github.com/Kilo-Org/kilo-marketplace
- Website
- zskills.vercel.app
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
Same skill elsewhere
Copies of this SKILL.md published by others; search shows only one of them.
- 0.369score
agent-md-refactor
GOlinkup
Refactor bloated AGENTS.md, CLAUDE.md, or similar agent instruction files to follow progressive disclosure principles.
SkillAFreshness: A★ 5Claude Code +9 - 0.337score
agent-md-refactor
PhateValleyman
Refactor bloated AGENTS.md, CLAUDE.md, or similar agent instruction files to follow progressive disclosure principles.
SkillAFreshness: AClaude Code +9 - 0.328score
agent-md-refactor
manu14357
Refactor bloated AGENTS.md, CLAUDE.md, or similar agent instruction files to follow progressive disclosure principles.
SkillCFreshness: C★ 16Claude Code +9 - 0.310score
agent-md-refactor
jisjohnsajan
Refactor bloated AGENTS.md, CLAUDE.md, or similar agent instruction files to follow progressive disclosure principles.
SkillBFreshness: BClaude Code +9 - 0.276score
agent-md-refactor
Microck
Refactor bloated AGENTS.md, CLAUDE.md, or similar agent instruction files to follow progressive disclosure principles.
SkillDFreshness: D★ 5Claude Code +9 - 0.264score
agent-md-refactor
RamonsDka
Refactor bloated AGENTS.md, CLAUDE.md, or similar agent instruction files to follow progressive disclosure principles.
SkillDFreshness: D★ 2Claude Code +9 - 0.264score
agent-md-refactor
fefogarcia
Refactor bloated AGENTS.md, CLAUDE.md, or similar agent instruction files to follow progressive disclosure principles.
SkillDFreshness: D★ 2Claude Code +9 - 0.264score
agent-md-refactor
peparhugo
Refactor bloated AGENTS.md, CLAUDE.md, or similar agent instruction files to follow progressive disclosure principles.
SkillDFreshness: D★ 2Claude Code +9 - 0.257score
agent-md-refactor
digitalspeed
Refactor bloated AGENTS.md, CLAUDE.md, or similar agent instruction files to follow progressive disclosure principles.
SkillDFreshness: D★ 1Claude Code +9 - 0.244score
agent-md-refactor
illogical
Refactor bloated AGENTS.md, CLAUDE.md, or similar agent instruction files to follow progressive disclosure principles.
SkillDFreshness: DClaude Code +9
More from Kilo-Org
- 0.661score
angular-tooling
Kilo-Org
Use Angular CLI and development tools effectively in Angular v20+ projects.
SkillAFreshness: A★ 195Claude Code +9 - 0.661score
elasticsearch-file-ingest
Kilo-Org
Ingest and transform data files (CSV/JSON/Parquet/Arrow IPC) into Elasticsearch with stream processing and custom transforms.
SkillAFreshness: A★ 195Claude Code +9 - 0.661score
senior-data-engineer
Kilo-Org
Data engineering skill for building scalable data pipelines, ETL/ELT systems, and data infrastructure.
SkillAFreshness: A★ 195Claude Code +9 - 0.661score
sql-server-table-reconciliation
Kilo-Org
Use when: comparing SQL Server tables across instances, data migration validation, ETL verification, row mismatch detection, schema drift, reconciliation…
SkillAFreshness: A★ 195Claude Code +9 - 0.661score
angular-http
Kilo-Org
Implement HTTP data fetching in Angular v20+ using resource(), httpResource(), and HttpClient.
SkillAFreshness: A★ 195Claude Code +9 - 0.661score
dataset-transformation
Kilo-Org
Generates code that transforms datasets between ML schemas for model training or evaluation.
SkillAFreshness: A★ 195Claude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get agent-md-refactor running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
agent-md-refactor skill. Agent Mart. https://agentmart.dev/skills/kilo-org-agent-md-refactor (last updated 2026-10-24)