agent-config-maintenance

Refactor Codex configuration files and Agent Skills by splitting concerns, deduplicating instructions, and reorganizing guidance across AGENTS.md, project docs, and skills. Use when asked to clean up AGENTS.md, move instructions into skill bundles, or standardize agent setup rules.

16 stars

Best use case

agent-config-maintenance is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Refactor Codex configuration files and Agent Skills by splitting concerns, deduplicating instructions, and reorganizing guidance across AGENTS.md, project docs, and skills. Use when asked to clean up AGENTS.md, move instructions into skill bundles, or standardize agent setup rules.

Teams using agent-config-maintenance should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/agent-config-maintenance/SKILL.md --create-dirs "https://raw.githubusercontent.com/diegosouzapw/awesome-omni-skill/main/skills/data-ai/agent-config-maintenance/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/agent-config-maintenance/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How agent-config-maintenance Compares

Feature / Agentagent-config-maintenanceStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Refactor Codex configuration files and Agent Skills by splitting concerns, deduplicating instructions, and reorganizing guidance across AGENTS.md, project docs, and skills. Use when asked to clean up AGENTS.md, move instructions into skill bundles, or standardize agent setup rules.

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

Related Guides

SKILL.md Source

# Agent Config Maintenance

## Scope

- Target files: `AGENTS.md`, project-doc sections, `skills/*/SKILL.md`, and any references under `skills/*/references/`.
- Focus on separation of concerns: global agent rules vs task-specific workflows.

## Workflow

1. Inventory instructions
   - Use `rg` to find duplicate or conflicting rules across AGENTS, project docs, and skills.
   - Note which rules are global constraints vs task-specific procedures.
2. Decide the split
   - Keep only global, always-on constraints in `AGENTS.md`.
   - Move task-specific procedures into the relevant skill `SKILL.md` or `references/`.
   - Remove duplicated bullets after moving.
3. Update skill metadata
   - Fill `SKILL.md` frontmatter with `name` and a trigger-ready `description`.
   - Keep the description explicit about when to use the skill.
4. Write the skill body
   - Use imperative form.
   - Keep core workflow in `SKILL.md`.
   - Move large checklists or detailed examples into `references/` and link them.
5. Validate consistency
   - Ensure AGENTS and skills do not contradict each other.
   - Verify naming conventions (lowercase + hyphen).
   - Confirm only necessary files exist; avoid extra docs.

## Quality gates

- Keep `SKILL.md` under 500 lines.
- Avoid duplication between `SKILL.md` and any reference files.
- If adding scripts, run them once to validate behavior.

Related Skills

import-existing-ai-config

16
from diegosouzapw/awesome-omni-skill

Import existing AI tool configurations (from Claude, Copilot, or Cursor) into universal-ai-config templates. Converts target-specific files into universal templates.

EchoKit Config Generator

16
from diegosouzapw/awesome-omni-skill

Generate config.toml for EchoKit servers with interactive setup for ASR, TTS, LLM services, MCP servers, API key entry, and server launch

claude-config-management

16
from diegosouzapw/awesome-omni-skill

Claude Code設定(リポジトリルート)の構成管理ガイド。ファイルレベルsymlinkによる設定管理、管理対象の追加・削除、Taskfileタスクの実行方法を提供する。「設定ファイルを追加して」「新しいスキルを追加して」「symlinkの状態を確認して」「Claude設定を変更して」のようにClaude Code設定の構成変更を行うときに使用する。

bigconfig-generator

16
from diegosouzapw/awesome-omni-skill

Use this skill when creating or updating Bigeye monitoring configurations (bigconfig.yml files) for BigQuery tables. Works with metadata-manager skill.

ai-agent-config

16
from diegosouzapw/awesome-omni-skill

Manage AI coding skills across platforms (Claude Code, Antigravity, Cursor, Windsurf) using ai-agent-config CLI. Use when the user wants to sync skills to/from GitHub, install to multiple platforms, add custom skill sources, or configure skill management settings.

shellcheck-configuration

16
from diegosouzapw/awesome-omni-skill

Master ShellCheck static analysis configuration and usage for shell script quality. Use when setting up linting infrastructure, fixing code issues, or ensuring script portability.

clippy-configuration

16
from diegosouzapw/awesome-omni-skill

Use when configuring Clippy for Rust projects with TOML config, lint groups, attributes, and workspace setup.

clawdbot-config

16
from diegosouzapw/awesome-omni-skill

Comprehensive Clawdbot configuration and skills system management. Use when working with Clawdbot setup, configuration files, creating/modifying AgentSkills-compatible skills with YAML frontmatter, troubleshooting agent behavior, managing channels, workspace, sandbox, or multi-agent routing.

pre-configured-apis-rules

16
from diegosouzapw/awesome-omni-skill

Rules for using pre-configured APIs in the project, using them only if they are required by the project.

n8n-node-configuration

16
from diegosouzapw/awesome-omni-skill

Operation-aware node configuration guidance. Use when configuring nodes, understanding property dependencies, determining required fields, choosing between get_node detail levels, or learning commo...

mtls-configuration

16
from diegosouzapw/awesome-omni-skill

Configure mutual TLS (mTLS) for zero-trust service-to-service communication. Use when implementing zero-trust networking, certificate management, or securing internal service communication.

langchain4j-vector-stores-configuration

16
from diegosouzapw/awesome-omni-skill

Configure LangChain4J vector stores for RAG applications. Use when building semantic search, integrating vector databases (PostgreSQL/pgvector, Pinecone, MongoDB, Milvus, Neo4j), implementing embedding storage/retrieval, setting up hybrid search, or optimizing vector database performance for production AI applications.