blog-posting-auto: Skill for Claude Code

.claude/skills/blog-pipeline/SKILL.md

blog-pipeline is a skill for Claude Code from unclejobs-ai/blog-posting-auto. It costs 96 tokens per session (1,664 once invoked), scanned B, original, MIT.

A six-stage workflow that researches, checks, plans, writes, reviews, and publishes a Korean blog article to a Notion database. Notion is a workspace for documents and databases.

In plain words
What is it for?
It is for producing a researched Korean blog post from a topic or keyword, saving drafts during the process, and optionally creating the final article in Notion.
Why use it?
It separates fact checking from writing, so later stages use verified sources and unsupported claims can be isolated. Publishing requires the database settings and the user’s explicit approval.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: reads .claude/ paths.

This is unclejobs-ai/blog-posting-auto's own configuration. It tells Claude Code how to work on blog-posting-auto itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything blog-posting-auto configures →

Reuse

Borrowing it

Nothing to install: this file belongs to unclejobs-ai/blog-posting-auto. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/unclejobs-ai/blog-posting-auto/main/.claude/skills/blog-pipeline/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/unclejobs-ai/blog-posting-auto

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for blog-pipeline

README.md
[![agentmods](https://agentmods.dev/badge/skills/unclejobs-ai/blog-posting-auto/blog-pipeline/github.svg)](https://agentmods.dev/skills/unclejobs-ai/blog-posting-auto/blog-pipeline)
Your own site
<a href="https://agentmods.dev/skills/unclejobs-ai/blog-posting-auto/blog-pipeline"><img src="https://agentmods.dev/badge/skills/unclejobs-ai/blog-posting-auto/blog-pipeline/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for blog-pipeline

Your own site · 80×15
<a href="https://agentmods.dev/skills/unclejobs-ai/blog-posting-auto/blog-pipeline"><img src="https://agentmods.dev/badge/skills/unclejobs-ai/blog-posting-auto/blog-pipeline.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 96 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,664 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00096 $0.01664
Opus 5 $0.00048 $0.00832
Sonnet 5 $0.00019 $0.00333
Haiku 4.5 $0.00010 $0.00166

Measured 12d ago against content hash 62f1243266d6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade B, and why

blog-pipeline scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

- 금지표현 grep 0건: `grep -nE -f .claude/style/forbidden.patterns workspace/{RUN_ID}/draft.md`
.claude/skills/blog-pipeline/SKILL.md · 163 lines

How it starts

The opening of the file, as written. The whole thing — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/blog-pipeline

블로그 글 한 편을 6단계 서브에이전트 직렬 실행으로 생성하고 Notion에 발행하는 워크플로우. Researcher가 모은 사실을 Fact-Checker가 원본 URL 재방문으로 검증, downstream(Planner/Writer/Reviewer)은 verified.md만 사실 근거로 사용.

실행 순서

오케스트레이터(메인 세션)가 다음을 순서대로 수행:

0. 준비

  1. RUN_ID + TODAY 생성: slug는 주제에서 한국어→영어 음차 또는 핵심 명사.
    RUN_ID="$(date +%Y%m%d-%H%M%S)-{slug}"
    TODAY="$(date +%Y-%m-%d)"
    mkdir -p workspace/$RUN_ID
    
    TODAY는 모든 서브에이전트 호출 시 prompt에 박아 전달 — Researcher 최신성 쿼리, Fact-Checker staleness 판정 기준.
  2. workspace/{RUN_ID}/meta.json 초기 기록:
    {
      "run_id": "...",
      "topic": "...",
      "today": "YYYY-MM-DD",
      "started_at": "ISO-8601",
      "stages": {}
    }
    
  3. .env 존재 + NOTION_DATABASE_ID 채워졌는지 확인. 없으면 사용자에게 알리고 Publisher 단계는 skip 옵션 안내.

1. Researcher

Agent(subagent_type="blog-researcher", prompt=<<<
RUN_ID: {RUN_ID}
TODAY:  {TODAY}      ← 최신성 쿼리 기준
TOPIC:  {사용자 입력 주제}

workspace/{RUN_ID}/research.md 생성.
모든 WebSearch 쿼리에 {TODAY 연도} 또는 "최신" 키워드 포함.
각 사실에 source-date 메타 부착.
>>>)

검증: workspace/{RUN_ID}/research.md 존재 + 4KB 이상 + 각 사실에 (source-date: ...) 메타 존재.

1.5. Fact-Checker

Agent(subagent_type="blog-fact-checker", prompt=<<<
RUN_ID: {RUN_ID}
TODAY:  {TODAY}      ← staleness 판정 기준 (TODAY-12개월 미만 출처만 통과)

workspace/{RUN_ID}/research.md의 각 주장을 원본 URL 재방문해 검증.
time-sensitive(가격·시간·정책·버전) 사실은 source-date 12개월 초과면 rejected (stale-source).
research.verified.md + research.rejected.md 생성.
>>>)

검증:

  • research.verified.md 존재 + research.rejected.md 존재 (빈 파일이어도 OK)
  • stdout 통계 라인 [fact-checker] ... verified=M rejected=N-M ratio=M/N% 캡처
  • verified 비율 < 50% → 자동 RETRY: Researcher 재호출 (최대 2회). 그래도 50% 미만이면 사용자 결정 요청.
  • verified 비율 ≥ 50%면 다음 단계 진행.

2. Planner

Agent(subagent_type="blog-planner", prompt=<<<
RUN_ID: {RUN_ID}

workspace/{RUN_ID}/research.verified.md를 읽고 plan.md 작성.
research.md는 참고만, verified에 없는 사실은 절대 사용 금지.
>>>)

검증: plan.md 존재 + 섹션 5개 이상.

3. Writer

Agent(subagent_type="blog-writer", prompt=<<<
RUN_ID: {RUN_ID}

plan.md 따라 draft.md 작성.
사실 출처는 research.verified.md만.
>>>)

Read the full file on GitHub · 163 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 12d ago First seen · 163 lines · 96 tokens per session scan B 62f1243266d6

Subscribe to this mod's changes

blog-pipeline is a skill published in the GitHub repository unclejobs-ai/blog-posting-auto (42 stars, last pushed 3mo ago), licensed MIT. It adds 96 tokens to every session and 1,664 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens