Live survey304 models · 14 providers · 23,592 auditsAudited implement · SAFE →What changedHow we verifyllms.txt

Agent skill · Audited from source

Release Post

skill · posit-dev/skillsMIT licenceAudited 14 Nov 2026 · source 9882b8d1a3f5

★ 565pushed 1 day agoversion 1.0
✓SAFEGrade B · 89/100 · 14 Nov 2026 · 9882b8d
565repo stars · whole posit-dev/skills

Is it safe? Yes — SAFE, grade B (89/100). We read this skill's source at commit 9882b8d1a3f5 and found no filesystem, network or shell access and no hard-coded secrets. What it does: Create professional package release blog posts following Tidyverse or Shiny blog conventions. Use when the user needs to: (1) Write a release announcement blog post for an R or Python package for tidyverse.org or…

Ask an AI about this pageGChatGPTCClaudePPerplexityGeGeminiXGrok
More
Cite

Cite this page

ModelsAtlas. “Release Post (posit-dev/skills)”. Retrieved 14 Nov 2026. https://modelsatlas.com/skills/posit-dev/release-post

Trust audit

Audit 0.4.1 · source read 14 Nov 2026

Trust score89/100✓SAFE B
0 critical0 high0 medium0 low0 info

SAFE means nothing in the source contradicts what the skill says it does. Grade B is shared by 17,406 of 18,389 audited skills.

What the source does

  • FilesystemNone observedNo reads or writes in the source
  • NetworkNone observedNo outbound calls in the source
  • ShellNone observedNo commands run in the source
  • DependenciesPinnedNothing floats
  • SecretsNone foundNo keys in source

Five audit layers

LayerWhat we checkResultFindings
L0 ProvenanceRepo owner, licence, archive status, activityPASS0
L1 Static sourceSecrets, path traversal, supply chain, hidden codePASS0
L2 InstructionsPrompt injection, authority framing, hidden directivesPASS0
L3 InventoryThe files and declarations match the sourcePASS0
L4 SandboxRun in isolation and watch behaviourSKIPPED why0

Gates applied: no behavioural pass.

Findings (0)

No findings at any severity. We re-audit when the source changes.

Audit 0.4.1 · source sha 9882b8d1a3f5 · 14 Nov 2026Report an issue or request a re-scan

Provenance

Who published it, and what the verdict is pinned to

  • Publisherposit-dev GitHub organizationOwner of the repository this skill is read from
  • Source folderposit-dev/skills/open-source/release-postThe exact folder we audited
  • LicenceMITAs the repository states it
  • Commit pinned for this verdict9882b8d1a3f5A new audit runs when the source changes
  • Repository statusNot archivedLast push 1 day ago
  • Sandboxed runNot runSkills are read, not executed; layer L4 is skipped

What it tells the agent

Full source on GitHub ↗

Its description: Create professional package release blog posts following Tidyverse or Shiny blog conventions. Use when the user needs to: (1) Write a release announcement blog post for an R or Python package for tidyverse.org or…

---
name: release-post
description: >
  Create professional package release blog posts following Tidyverse or Shiny blog conventions.
  Use when the user needs to: (1) Write a release announcement blog post for an R or Python package
  for tidyverse.org or shiny.posit.co, (2) Transform NEWS/changelog content into blog format,
  (3) Generate acknowledgments sections with contributor lists, (4) Format posts following specific
  blog platform requirements. Supports both Tidyverse (hugodown) and Shiny (Quarto) blog formats with
  automated contributor fetching and comprehensive style guidance.
metadata:
  author: Garrick Aden-Buie (@gadenbuie)
  version: "1.0"
license: MIT
---

# Package Release Post

Create professional R/Python package release blog posts following Tidyverse or Shiny blog conventions.

## Quick Start

1. **Identify the blog platform**: Tidyverse (tidyverse.org) or Shiny (shiny.posit.co)
2. Verify NEWS.md or changelog exists for the package
3. Gather package info: name, version, repository (e.g., "tidyverse/dplyr")
4. Follow the workflow below
5. Use `scripts/get_contributors.R` to generate acknowledgments
6. Reference the appropriate formatting guide for final polish

## Platform Selection

This skill supports two blog platforms with different formatting requirements:

- **Tidyverse blog** (tidyverse.org)
  - Uses hugodown
  - R packages primarily
  - More rigid structure and conventions
  - See `references/tidyverse-formatting.md`

- **Shiny blog** (shiny.posit.co)
  - Uses Quarto
  - R and Python packages
  - More flexible, feature-focused structure
  - See `references/shiny-formatting.md`

**First, determine which platform the post is for**, then follow the general workflow and apply platform-specific formatting.

## General Workflow

These steps apply to both platforms. Content guidelines are based on Tidyverse best practices but adapt them as needed for Shiny posts.

### Step 1: Gather Information

Collect required information:

- **Platform**: Tidyverse or Shiny blog?
- **Package name and version**: e.g., "dplyr 1.2.0" or "shiny 1.9.0"
- **Repository**: GitHub repo in "owner/repo" format
- **Package language**: R or Python
- **NEWS content**: Read the package's NEWS.md, CHANGELOG, or NEWS
- **Package description**: One-sentence core purpose
- **Previous release tag**: For contributor fetching (optional)
- **Featured image**: For frontmatter (optional but recommended)

### Step 2: Structure the Post

Create the post outline following this order:

1. **Frontmatter**: Platform-specific YAML (see formatting references)

2. **Title and Opening**:
   - Title: Package name and version
   - Opening: Announcement with one-sentence package description
   - Installation: Code block with installation command
   - Overview: Brief summary with link to full release notes

3. **Main Content** (choose appropriate sections):
   - **Migration guide** (if breaking changes) - Always first when present
   - **Lifecycle changes** (deprecations, soft-deprecations, defunct)
   - **Feature sections** (one per major feature, descriptive headings)
   - **Minor improvements** (bulleted list)

4. **Acknowledgements** (when appropriate):
   - Use `scripts/get_contributors.R`
   - Format: "A big thank you to all the folks who helped make this release happen:"
   - Comma-separated GitHub links

### Step 3: Apply Content Guidelines

Follow the best practices in `references/content-guidelines.md`:

- **Opening style**: "We're [random adjective expressing excitement] to announce the release of..."
- **Section organization**: Migration → Lifecycle → Features → Improvements → Acknowledgements
- **Tone**: Conversational, professional, enthusiastic but authentic
- **Technical precision**: Use exact function names in backticks
- **Focus on benefits**: Explain "why" not just "what"
- **Code examples**: Realistic, well-commented, properly formatted

### Step 4: Transform NEWS Content

Convert NEWS.md bullets to blog-friendly content:

- **Research features thoroughly**: Don't just copy NEWS bullets—read function docs, check PRs, understand the context
- **Expand context**: Why changes matter, not just what changed
- **Add complete code examples**: Show realistic usage with full workflows, not just function signatures
- **Explain concepts first**: For unfamiliar features, explain what they are and how they work before showing code
- **Group thematically**: Combine related NEWS items into coherent sections
- **Use conversational tone**: Transform terse bullets into prose
- **Link documentation**: Add relevant links to docs and resources
- **Highlight breaking changes**: Make migration paths clear
- **Multi-language parity** (Shiny only): For R+Python packages on the Shiny blog, ensure all examples show both languages in tabsets

### Step 5: Apply Platform-Specific Formatting

**For Tidyverse posts**, read `references/tidyverse-formatting.md` and apply:
- hugodown frontmatter with `slug`, `photo.url`, `photo.author`
- Specific slug format: `packagename-x-y-z` (hyphens replace dots)
- R code blocks with `r` language identifier
- Acknowledgements always included as final section

**For Shiny posts**, read `references/shiny-formatting.md` and apply:
- Quarto frontmatter with YAML anchors for social media
- Flexible title formatting
- Use tabsets for Python/R or Express/Core variations
- Platform-specific code block attributes
- Acknowledgements optional, varies by post type
- May use lead paragraphs, callouts, embedded media

### Step 6: Generate Acknowledgements

Run the contributor script:

```bash
Rscript scripts/get_contributors.R "owner/repo"
```

Or with a specific starting tag for the previous version (or tag used for last release post):

```bash
Rscript scripts/get_contributors.R "owner/repo" "v1.0.0"
```

Copy the markdown output into the Acknowledgements section.

### Step 7: Review and Polish

Platform-agnostic checklist:

- [ ] Frontmatter complete with all required fields
- [ ] Opening clearly states pa

Excerpt, first 6,000 characters of SKILL.md, verbatim from the audited commit. It is text from someone else’s repository, quoted so you can judge it before your agent reads it.

Install

Pinned to the audited commit 9882b8d

Download folder ↗
pip install packagename
pip install "packagename[extra]"

Commands as the repository documents them: shown, never run by us. Our verdict covers commit 9882b8d1a3f5 only.

Works in

The author has not said which agents this skill supports, and we have not tested it in any.

Audit history

Every audit, every source change

  1. ✓SAFE B 89 / 100

    first audit · source 9882b8d1a3f5

README badge

For maintainers · shows the latest audit

ModelsAtlas: SAFE BMODELSATLASSAFE · B
[![ModelsAtlas: SAFE B](https://modelsatlas.com/skills/posit-dev/release-post/badge.svg)](https://modelsatlas.com/skills/posit-dev/release-post/)

The badge shows our verdict and grade for this skill, and links back to this page. It changes when the audit does.

Similar skills

ponytail✓SAFE

dietrichgebert/ponytail

Lazy senior dev mode: the smallest change that fully solves the task, and a reply a busy human understands in one read. Use on any coding task (writing, fixing, refactoring, reviewing, choosing dependencies) and when…

★ 160kGrade B
customer-research✓SAFE

coreyhaines31/marketingskills

When the user wants to run or synthesize customer research, or asks what customer quotes, reviews, or feedback really mean, what is safe to conclude, and what to ask next: interviews, surveys, voice of customer,…

★ 60kGrade B
cro✓SAFE

coreyhaines31/marketingskills

When the user wants more conversions from a page or form, or asks why a page isn't converting, what to change first, or whether to add or remove a field or element: landing and pricing pages, lead forms, or a URL shared…

★ 60kGrade B
copywriting✓SAFE

coreyhaines31/marketingskills

When the user wants to write or rewrite page copy (homepage, landing, pricing, feature), or asks which headline, promise, or message to lead with. Diagnoses the input first (blank brief, real voice, or point edit) and…

★ 60kGrade B
i-have-adhd✓SAFE

ayghri/i-have-adhd

Shape output for a reader with ADHD: lead with the next action, number multi-step work, restate state across turns, suppress tangents, give specific time estimates, make wins visible. Invoke with /i-have-adhd; stays on…

★ 58kGrade B
content-strategy✓SAFE

coreyhaines31/marketingskills

When the user wants to plan a content strategy, decide what content to create, or figure out what topics to cover. Also use when the user mentions "content strategy," "what should I write about," "content ideas," "blog…

★ 58kGrade B

Add this badge to your README

[![ModelsAtlas: SAFE B](https://modelsatlas.com/skills/posit-dev/release-post/badge.svg)](https://modelsatlas.com/skills/posit-dev/release-post/)

Questions about Release Post

What does the Release Post skill do?
A collection of Claude Skills from Posit
Is Release Post safe to install?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean skill reads B.
What can Release Post access on my machine?
The audit observed no filesystem, network or shell use at all in its source.
How current is this page?
The grade is for one exact copy of the source (9882b8d1a3f5), read on 2026-11-14. The repository is watched, and a new audit runs when it changes — this is the first audit.

Sources

Spotted something wrong? Report a correction · Methodology

Keep going in your AI

Opens with this page as the source. We add nothing else to the prompt.