agentmods.dev

publish-qiita

publish-qiita is a skill for Claude Code, Codex from LienJack/learn-agent. It costs 33 tokens per session (498 once invoked), scanned A, original, MIT.

A workflow for preparing and publishing local Astro blog articles to Qiita, a Japanese developer publishing platform, through its API. It supports private publication by default and can update existing articles.

In plain words
What is it for?
Use it to dry-run, create, update, or explicitly publish Japanese articles on Qiita. It handles platform formatting, image URLs, tags, publication visibility, and existing article IDs.
Why use it?
It creates a checked Qiita copy while keeping the source Markdown as the original. It also helps catch broken image links and unsafe tags before publication.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

not rated 26repo 3mo ago A scan 33 tokens original MIT

Good fit Use it to dry-run, create, update, or explicitly publish Japanese articles on Qiita. It handles platform formatting, image URLs, tags, publication visibility, and existing article IDs.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/lienjack/learn-agent/publish-qiita
View source ↗ LienJack/learn-agent blog.lienjack.com
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add LienJack/learn-agent --skill publish-qiita
Clone the repo
git clone --depth 1 https://github.com/LienJack/learn-agent

Made for: Claude Code, Codex.

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 publish-qiita

README.md
[![agentmods](https://agentmods.dev/badge/skills/lienjack/learn-agent/publish-qiita/github.svg)](https://agentmods.dev/skills/lienjack/learn-agent/publish-qiita)
Your own site
<a href="https://agentmods.dev/skills/lienjack/learn-agent/publish-qiita"><img src="https://agentmods.dev/badge/skills/lienjack/learn-agent/publish-qiita/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 publish-qiita

Your own site · 80×15
<a href="https://agentmods.dev/skills/lienjack/learn-agent/publish-qiita"><img src="https://agentmods.dev/badge/skills/lienjack/learn-agent/publish-qiita.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 498 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00033 $0.00498
Opus 5.5 $0.00013 $0.00199
Sonnet 5.5 $0.00007 $0.00100
Haiku 4.5 $0.00003 $0.00050

Measured 2mo ago against content hash 6832880031aa, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

publish-qiita scanned grade A with 0 findings 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 2mo 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.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

publish/skills/publish-qiita/SKILL.md · 56 lines

What it actually says

Qiita 发布流程

你在本仓库内发布 Qiita 文章时，必须使用项目内命令，不要绕过 publish/ 中控台。

1. 发布前检查

先运行试发布：

publish/bin/publish-qiita --dry-run <article.md>

检查输出中的：

  • publish/runs/.../record.json
  • publish/artifacts/.../*.qiita.md
  • publish/artifacts/.../*.qiita.json

2. 默认私密发布

确认检查摘要后，默认创建或更新 Qiita private item：

publish/bin/publish-qiita --yes <article.md>

3. 公开发布

只有用户明确确认公开发布时，才使用：

publish/bin/publish-qiita --public --yes <article.md>

4. 更新已有文章

优先使用源文 frontmatter 的 qiita_id 或 publish/qiita-items.json 映射。必要时可以显式指定：

publish/bin/publish-qiita --item-id <qiita_item_id> --yes <article.md>

5. 安全规则

  • 不要在运行记录里写入 token、cookie 或私密请求头。
  • 不要在没有 --yes 的情况下调用 Qiita 写接口。
  • 源 Markdown 是内容源头；Qiita 发布副本只写入 publish/artifacts/。
  • 本地图片必须先转换成公开 URL，使用 QIITA_IMAGE_BASE_URL、PUBLISH_IMAGE_BASE_URL 或 PUBLISH_IMAGE_UPLOAD_COMMAND。
  • 使用 QIITA_IMAGE_BASE_URL 或 PUBLISH_IMAGE_BASE_URL 时，base URL 必须指向源文章所在目录的公网路径；不要只写仓库根路径，否则 assets/... 会被拼成不存在的 .../main/assets/...。
  • 发布前检查 publish/artifacts/.../*.qiita.md 中所有图片 URL，并用 HEAD 请求确认返回 200；发现 404 时先修正 base URL，再重新生成和发布。
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. 2mo ago First seen · 56 lines · 33 tokens per session scan A 6832880031aa

Subscribe to this mod's changes

publish-qiita is a skill published in the GitHub repository LienJack/learn-agent (26 stars, last pushed 3mo ago), licensed MIT. It adds 33 tokens to every session and 498 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Writing and docsai-agentblogcode-analysisknowledge-basetechnical-writing
Related

publish-qiita compared with skills from other repositories

publish-qiita next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
publish-qiitaLienJack/learn-agentSkill263mo agoMITA33Claude Code, Codex
wiki-curationCiao1019/PetrichorSkill1541mo agoApache-2.0A21Claude Code, Codex
research-noteCiao1019/PetrichorSkill1541mo agoApache-2.0A19Claude Code, Codex
Technical Blog Post WriterNotysoty/openagentskillsSkill92mo agoMITA17Claude Code, Codex
technical-documentationJPeetz/agent-skillsSkill159d agononeB82Claude Code, Codex
blog-writing-guidezebbern/termstackSkill46mo agononeA60Claude Code, Codex
Help Article Writerjmsktm/claude-settingsSkill109mo agononeA18Claude Code, Codex