open-source-website: Skill for Claude Code

.claude/skills/review-post/SKILL.md

review-post is a skill for Claude Code from posit-dev/open-source-website. It costs 18 tokens per session (1,159 once invoked), scanned A, original, MIT.

A content review guide for blog posts that compares the article with its frontmatter, the metadata at the top, and checks accessibility issues.

In plain words
What is it for?
Use it to review changed posts, check titles and descriptions against the text, find accessibility gaps, and prepare the post for human review.
Why use it?
It finds claims in the metadata that do not match the article and highlights content problems that a mechanical validator may miss.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter.

This is posit-dev/open-source-website's own configuration. It tells Claude Code how to work on open-source-website 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 open-source-website configures →

Reuse

Borrowing it

Nothing to install: this file belongs to posit-dev/open-source-website. 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/posit-dev/open-source-website/main/.claude/skills/review-post/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/posit-dev/open-source-website

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 review-post

README.md
[![agentmods](https://agentmods.dev/badge/skills/posit-dev/open-source-website/review-post/github.svg)](https://agentmods.dev/skills/posit-dev/open-source-website/review-post)
Your own site
<a href="https://agentmods.dev/skills/posit-dev/open-source-website/review-post"><img src="https://agentmods.dev/badge/skills/posit-dev/open-source-website/review-post/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 review-post

Your own site · 80×15
<a href="https://agentmods.dev/skills/posit-dev/open-source-website/review-post"><img src="https://agentmods.dev/badge/skills/posit-dev/open-source-website/review-post.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 18 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,159 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00018 $0.01159
Opus 5.5 $0.00007 $0.00464
Sonnet 5.5 $0.00004 $0.00232
Haiku 4.5 $0.00002 $0.00116

Measured 2mo ago against content hash 8890793bc479, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

review-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 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.

.claude/skills/review-post/SKILL.md · 81 lines

How it starts

The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Review a blog post's content the way a reviewer would — checking that the content lines up with its frontmatter, surfacing things authors commonly miss, and flagging accessibility issues. Complements the check-post skill, which validates frontmatter mechanically; this skill reads the actual post text.

This skill does not check writing style. At the end, remind the author to get a human review for tone, clarity, and flow.

Step 1: Identify the post

If the user provided a path in their request, use that. Otherwise, look for blog posts changed on the current branch:

git diff --name-only --diff-filter=d origin/main...HEAD -- 'content/blog/**/index.md' 'content/blog/**/index.qmd'

If no changed posts are found, ask the user which post to review.

Step 2: Read the post

For each post, read both the frontmatter and the body. If an index.qmd exists, prefer it as the source of truth; otherwise read index.md. You need the actual prose, not just the metadata.

Step 3: Content vs. frontmatter consistency

Compare what the post actually says to what its frontmatter claims. Flag mismatches:

  • description drift — does the description still summarize the post accurately? Descriptions written by the new-post skill often stop matching the finished draft.
  • software / languages / topics — do the values reflect what the post is actually about? If the post discusses ggplot2 but software only lists dplyr, flag it. If the inferred topics no longer fit, flag it. Suggest the values that would match.
  • source — if the post is clearly about one of the projects with a blog listing page (positron, tidyverse, ai, shiny, great_tables, plotnine, pointblank, quarto) and source isn't set, flag it. See content/blog/_authoring-guide.md for the rule.
  • title — does it match the post's actual focus, or has the angle shifted during writing?

Step 4: Things authors miss

  • Placeholders left in the draft — search the body for TODO, TBD, XXX, FIXME, lorem ipsum, [insert ...], [link], etc. List each occurrence with line context.
  • Internal blog links use the permalink pattern — flag any links that look like /blog/<source>/<year>/<slug>/ or other content-directory paths instead of /blog/YYYY-MM-DD_slug/. (See "Linking to other blog posts" in the authoring guide.)
  • Code blocks have a language tag — fenced code blocks should open with a language (```r, ```python, ```sh, etc.), not bare ```.
  • .qmd images use fig-alt — alt text in .qmd should be ![](path){fig-alt="..."}, not ![alt](path) (the bracket text becomes a caption in Quarto).

Read the full file on GitHub · 81 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. 2mo ago First seen · 81 lines · 18 tokens per session scan A 8890793bc479

Subscribe to this mod's changes

review-post is a skill published in the GitHub repository posit-dev/open-source-website (65 stars, last pushed yesterday), licensed MIT. It adds 18 tokens to every session and 1,159 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.

Related

review-post compared with skills from other repositories

review-post next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
review-postposit-dev/open-source-websiteSkill65yesterdayMITA18Claude Code
imagegenopenai/codexSkill134ktodayApache-2.0A113Codex
local-ai-agentsmicrosoft/ai-agents-for-beginnersSkill79ktodayMITA200Claude Code, Codex
playwright-climicrosoft/playwrightSkill99ktodayApache-2.0A19Claude Code
systematic-debuggingobra/superpowersSkill314k3d agoMITA21Claude Code
next-cache-components-adoptionvercel/next.jsSkill143ktodayMITA95Claude Code
chat-pet-sprite-creationmicrosoft/vscodeSkill195ktodayMITA53Claude Code, Codex