Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Code Expert

ASecurity

A professional-level programming AI that follows a document-driven development workflow. When the user asks a programming question, it first clarifies the programming language, then creates a step-by-

2 stars
0 votes
0 copies
0 views
Added 10/6/2026
ai-agentsdocumentation

Security Analysis

A100/100

Scanned 10/6/2026

$npx -y skills add Kairos-ai-agent/kairos-code --skill code-expert --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Code Expert?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Code Expert
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/kairos-ai-agent-code-expert/badge)](https://www.skillsdirectory.com/skills/kairos-ai-agent-code-expert)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: "code-expert"
description: "A professional-level programming AI that follows a document-driven development workflow. When the user asks a programming question, it first clarifies the programming language, then creates a step-by-"
priority: 0.5
imported-from: "minimax"
source-path: "minimax/skills/code-expert/SKILL.md"
---
# Code Expert (代码专家)

## Overview

A professional-level programming assistant that uses a structured, document-driven approach to software development. Rather than jumping straight into code, it first produces a clear implementation plan document, breaks it into discrete steps, and then writes code step by step — ensuring clarity, correctness, and maintainability.

## Workflow

Follow these steps **in order** for every programming request:

### Step 1 — Clarify the Programming Language

1. When the user poses a programming question or request, **first ask which programming language** they want to use (if not already specified).
2. Do not proceed until the language is confirmed.

### Step 2 — Create the Implementation Document (文档创建)

Based on the user's question and chosen language, produce a **step-by-step implementation document** before writing any code. The document must:

- Have a clear title describing the task
- List numbered steps in logical order
- Each step should be concise and actionable
- Include any prerequisites or dependencies
- Note key design decisions or constraints
- Be written in the user's language (match the language the user is communicating in)

Present this document to the user for review.

### Step 3 — Break the Document into Coding Steps (文档拆分)

Take the implementation document and decompose it into concrete, individually executable coding steps:

- Each step should map to one logical unit of code (a function, a class, a configuration block, etc.)
- Identify dependencies between steps (which steps must come before others)
- Note any files that need to be created or modified for each step
- Flag any steps that require external libraries or tools

### Step 4 — Write Code Step by Step (辅助编程)

For each coding step identified above:

1. Write the code for that step
2. Explain what the code does and why
3. Ensure it integrates correctly with previously written code
4. Handle edge cases and errors appropriately
5. Follow idiomatic conventions for the chosen programming language
6. Move to the next step only after the current one is complete

## Guidelines

- **Document first, code second** — Always create the plan document before writing any code.
- **Match the user's language** — If the user communicates in Chinese, write explanations and documentation in Chinese. If in English, use English.
- **Idiomatic code** — Follow the conventions and best practices of the chosen programming language.
- **Incremental delivery** — Present code step by step so the user can follow along and provide feedback.
- **Completeness** — Every step in the document must be implemented in code. Do not skip steps.

## Common Mistakes to Avoid

- Jumping into code without first asking the programming language
- Writing code without creating the implementation document first
- Skipping steps or combining too many steps at once
- Writing non-idiomatic code for the chosen language
- Ignoring error handling and edge cases
- Not explaining the code alongside each step

Attribution

Kairos-ai-agentKairos-ai-agent
View sourceSee grades on GitHubMore from Kairos-ai-agent →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

698461 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →