KimYx0207/Kim_Service

An open-source collection of Hooks and Agent Skills for Claude Code, Codex, and other AI coding assistants.

This repository also configures its own agents. See what Kim_Service tells them →

169Stars on the repository
13Mods indexed here, across every type
27d agoLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown

KimYx0207/Kim_Service

Skill Claude CodeCodex

Cross-runtime Agent Teams orchestration playbook for Claude Code, Codex, OpenClaw, and Cursor. This skill should be used when the user asks to "create agent teams", "use agent swarm", "setup multi-agent collaboration", "orchestrate agents", "coordinate parallel agents", "organize team collaboration", "build agent…

not rated 169 +1 27d ago A SkillSpector: pass 245 tokens original MIT

find-skills

02

KimYx0207/Kim_Service

Skill Claude CodeCodex

Helps 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 interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill. Also triggers…

not rated 169 +1 27d ago A SkillSpector: warn 89 tokens original MIT

goalpro

03

KimYx0207/Kim_Service

Skill Claude CodeCodex

A prompt-writing guide for turning vague or complex goals into instructions an agent can execute and check. It produces a Goal Prompt for starting work and a Loop Prompt for reviewing results and continuing later.

not rated 169 +1 27d ago A SkillSpector: pass 137 tokens original MIT

kim-decision

04

KimYx0207/Kim_Service

Skill Claude CodeCodex

A structured decision-review workflow for product, business, engineering, content, and planning questions.

not rated 169 +1 27d ago A SkillSpector: pass 148 tokens original MIT

zh-CN

05

KimYx0207/Kim_Service

Skill Claude CodeCodex

A Chinese-language reference skill describing a structured way to reason from intent and evidence to a decision and next action. It distinguishes quick, standard, and higher-risk workflows.

not rated 169 +1 27d ago A SkillSpector: warn 0 tokens original MIT

memory-3layer

06

KimYx0207/Kim_Service

Skill Claude Code

A project memory system with three layers: structured facts, dated work notes, and manually confirmed long-term knowledge. It is designed to share useful context across coding-agent sessions.

not rated 169 +1 27d ago A SkillSpector: pass 115 tokens original MIT

meta-skill-creator

07

KimYx0207/Kim_Service

Skill Claude Code

A toolkit for creating, restructuring, and checking reusable skills for coding agents. It treats a skill as a repeatable workflow with triggers, instructions, supporting files, tests, and evidence of successful runs.

not rated 169 +1 27d ago A SkillSpector: pass 245 tokens original MIT

code-security

08

KimYx0207/Kim_Service

Skill Claude Code

A security-checking skill that uses Semgrep to inspect source code for vulnerabilities, exposed secrets, and common OWASP Top 10 problems. Semgrep is a tool that finds suspicious code patterns.

not rated 169 +1 27d ago A SkillSpector: pass 75 tokens original MIT

xiaohongshu-skill

09

KimYx0207/Kim_Service

Skill Claude CodeCodex

A complete workflow for creating image-based posts for Xiaohongshu, also known as RedNote, a Chinese social platform for photo and text posts. It covers research, writing, page planning, image creation, review, and publishing checks.

not rated 169 +1 27d ago A SkillSpector: pass 104 tokens original MIT

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: