Skip to content
cccskills
FreePublished on GitHub

tech-blog-writer

Technical blog post writing guide. rooftopsnow.tistory.com style — Korean formal technical prose, architecture diagrams, code blocks + design intent commentary, table comparisons, checklist wrap-up. Triggers on "blog", "포스팅", "블로그", "기술 글", "tech blog".

The English summary is being prepared. Showing the original description.

See how to install

Files included (1)

  • SKILL.md3.1 KB

SKILL.md (original)

Review the instructions the agent will receive before you install.

Tech Blog Writer (Tistory Style)

Writing Style Rules

ItemRule
ToneFormal Korean ("합니다", "됩니다", "입니다")
PerspectiveFirst person ("In this post", "This is a design decision")
Code explanationDesign intent commentary in > quote blocks
EmphasisBold, inline code, > Note boxes
EmojiDo not use (only when explicitly requested by user)

Post Structure

# Title: [Technical Concept] — [Subtitle/Core Value]

> Date: YYYY-MM-DD | Author: geode-team | Tags: [tag1, tag2]

## Table of Contents
1. Introduction (Problem definition)
2~N. Body sections (Architecture → Implementation → Verification)
N+1. Wrap-up (Summary table + Checklist)

---

## 1. Introduction

Problem definition in 1 paragraph → Solution strategy in 1 paragraph.
Make clear "why the reader should read this."

## 2~N. Body

### Section title: "N. Concept Name + Detailed Description"

Each section pattern:
1. One-line concept summary
2. Architecture diagram (Mermaid or ASCII)
3. Core code block (Python, with type hints)
4. > Design intent commentary block
5. Comparison table (config values, trade-offs, etc.)

## N+1. Wrap-up

### Summary

| Item | Value/Description |
|---|---|
| ... | ... |

### Checklist

- [ ] Item 1
- [ ] Item 2

Code Block Rules

  1. Interface/Protocol first → Implementation later
  2. Type hints must be included
  3. > quote block immediately after code block explaining "why this design"
  4. File path as comment above code block: # geode/infrastructure/ports/llm_port.py
# geode/infrastructure/ports/llm_port.py
class LLMClientPort(Protocol):
    def generate(self, system: str, user: str, **kwargs) -> str: ...
    def generate_json(self, system: str, user: str, **kwargs) -> dict: ...

By abstracting the concrete LLM call implementation (Claude, GPT), models can be swapped by simply replacing the adapter. This is a design decision following the Hexagonal Architecture Port/Adapter pattern.

Diagram Rules

  • Prefer Mermaid (GitHub rendering compatible)
  • Use ASCII diagrams alongside for complex flows
  • 1-2 sentence explanation of core flow immediately after diagram
  • Colors: Tailwind CSS based (fill:#3B82F6, fill:#10B981, etc.)

Length Guide

TypeLengthCode:Explanation ratio
Concept introduction3000-5000 chars3:7
Architecture deep-dive6000-10000 chars4:6
Implementation tutorial8000-12000 chars6:4

Korean Technical Terminology Rules

  • English technical terms: Korean annotation on first appearance: "Port(포트)"
  • Thereafter use English original: "Port"
  • Proper nouns (LangGraph, Anthropic, FastMCP) always in English
  • Abbreviations: spell out on first appearance: "PSI(Population Stability Index)"

Reviews

No reviews yet. Tell others what you thought.

Comments

No login needed. Share how it worked for you, ask a question, or note where it did not run.

No comments yet. Be the first to write one.

Comments are published right away. Do not include personal information such as email addresses or phone numbers. Up to 2 URLs.

0 / 1,000 characters

This form is protected by reCAPTCHA, and the Google Privacy Policy and Terms of Service apply.

More skills from this repository

Audit agent runtimes and their tests for lifecycle inference, capability overload, context pollution, correlated verification, prompt-only control, false success, dead compatibility paths, test-only seams, and complexity without contribution. Use for whole-repository agent audits, slop or dead-code triage, test contribution reviews, large refactors, tool/context simplification, and cleanup requests that need proof before deleting code or tests.

The English summary is being prepared. Showing the original description.

mangowhoiscloud/geode15Updated Oct 22, 2026

Diagnose agent operational failures through default-policy checks, multi-gap analysis, explicit service ownership, request-context lifetime, and degradation-versus-correctness checks.

The English summary is being prepared. Showing the original description.

mangowhoiscloud/geode15Updated Oct 22, 2026

Align, run, audit, and publish GEODE benchmark comparisons against Agent-World arXiv 2604.18292v1 across MCP-Mark, BFCL V4, and tau2-bench. Use for Agent-World or AgentWorld comparison requests, cross-suite agent benchmark design, Tau2 comparator/profile diagnosis, paired thin-runtime-versus-GEODE experiments, mean-accuracy@8 replication, or benchmark comparability and artifact reviews.

The English summary is being prepared. Showing the original description.

mangowhoiscloud/geode15Updated Oct 22, 2026

Verification checklist to prevent fake success. Detects test deletion/disabling, coverage regression, lint bypass, secret exposure. Triggered by "deception", "fake" ("가짜"), "fake success", "verification" ("검증"), "checklist" ("체크리스트"), "deletion detection" ("삭제 탐지"), "regression" keywords.

The English summary is being prepared. Showing the original description.

mangowhoiscloud/geode15Updated Oct 22, 2026

Implement proven backend architecture patterns including Clean Architecture, Hexagonal Architecture, and Domain-Driven Design. Use when architecting complex backend systems or refactoring existing applications for better maintainability.

The English summary is being prepared. Showing the original description.

mangowhoiscloud/geode15Updated Oct 22, 2026

Auto-search and summarize latest AI/agent papers.

The English summary is being prepared. Showing the original description.

mangowhoiscloud/geode15Updated Oct 22, 2026

See all skills by mangowhoiscloud

Report a problem with this skill