new-post

A setup guide for creating a new blog post on the Posit open-source website, including its metadata, branch, and optional working environment.

In plain words
What is it for?
Use it to start a post, infer its frontmatter from the topic, choose Markdown or Quarto format, and prepare the related project setup.
Why use it?
It reduces the setup work and helps ensure a new post follows the site's expected structure before it is written.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/posit-dev/open-source-website/new-post
Any agent
npx skills add posit-dev/open-source-website --skill new-post
Clone the repo
git clone --depth 1 https://github.com/posit-dev/open-source-website

Made for: Claude Code, Codex.

Per session 20 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,649 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00020 $0.01649
Opus 5 $0.00010 $0.00825
Sonnet 5 $0.00004 $0.00330
Haiku 4.5 $0.00002 $0.00165

Measured 2d ago against content hash 35f2ee07d558, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

new-post 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 2d 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.

.claude/skills/new-post/SKILL.md · 123 lines

How it starts

The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Help the user create a new blog post for the Posit open-source website. Work through these steps in order.

Step 0: Preflight check

Description: "Checking whether you're working from a direct clone or a fork"

git remote get-url origin

If the remote URL does not contain posit-dev/open-source-website, note to the user:

Looks like you're working from a fork. That's supported — you'll just need to comment /deploy-preview on your PR once to trigger the preview build (fork PRs can't auto-deploy because the workflow runs with a read-only token). If you're a member of the posit-dev org, the smoother path is to clone posit-dev/open-source-website directly so branch PRs get auto-deploy.

Then ask whether they'd like to continue from the fork or stop to re-clone.

Step 1: Gather information

Ask the user for anything not already provided in their request:

  • Title — the post title
  • Topic — a brief description of what the post is about (use this to infer frontmatter)
  • Author(s) — full name(s) of the people writing the post
  • Format — default to .qmd. It supports executable code and Quarto features (tabsets, callouts, multi-column layouts), so it's the right choice for most posts. Use .md only when the post is straight prose with no code blocks and none of those Quarto features. Offer .ipynb if the user prefers writing in Jupyter. For .qmd posts that will execute code, also ask whether it's R, Python, or both.

Step 2: Infer frontmatter

From the title and topic, reason about:

  • slug — only needed if it should differ from the folder name; otherwise the folder name is used automatically
  • software — folder names from content/software/ that the post is about (e.g. ggplot2, quarto, great-tables)
  • languages — programming languages featured (R, Python, etc.)
  • topics — one or more from the fixed set in data/topics.yaml: Machine Learning, Artificial Intelligence, Visualization, Interactive Apps, Publishing, MLOps and Admin, Data Wrangling, Best Practices, Community
  • source — set if the post belongs to one of the projects with its own blog listing page, so it appears there (e.g. source: tidyverse/blog/q/tidyverse/). Older project blog URLs (e.g. tidyverse.org/blog/) redirect to these listing pages, so this is how a new post stays visible to those readers. Valid values: positron, tidyverse, ai, shiny, great_tables, plotnine, pointblank, quarto. Infer from the inferred software/topic (e.g. dplyr/ggplot2 → tidyverse, Positron → positron); confirm with the user. Omit only if the post genuinely doesn't belong to any of these projects.
  • description — a draft 1–2 sentence description of the post

Read the full file on GitHub · 123 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. 2d ago First seen · 123 lines · 20 tokens per session scan A 35f2ee07d558

Subscribe to this mod's changes

new-post is a skill published in the GitHub repository posit-dev/open-source-website (50 stars, last pushed 3d ago), licensed MIT. It adds 20 tokens to every session and 1,649 once invoked, about $0.0001 per session on Opus 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.

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

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

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 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

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens