OpenParable
Skip to content
← Back to skills

Curate

Productivity
curate

Curate is an Agent Skill for productivity published in the rweekly/rweekly.org repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.

Guide the R Weekly curation team through preparing a new weekly issue. Reads curatinator_latest.md, classifies posts by section, checks for duplicates, and populates draft.md. Use when an editor wants to process the weekly content pipeline.

View on GitHub ↗
QUICK START

How to use this skill

Bring this guide into your coding agent with a prompt tailored to the tool you use.

  1. Open your project in Codex.
  2. Copy and paste the prompt below.
  3. Review files and risks before approving any action.
Prompt to paste
Inspect the Agent Skill at https://github.com/rweekly/rweekly.org/blob/HEAD/.claude/skills/curate/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/curate, but wait for my approval before writing files or running scripts.

Copying this prompt does not install or run the skill. Review third-party files before use.

R Weekly Release Curation

Live Context

  • Current draft: !cat draft.md

Your Task

You are helping the R Weekly curation team prepare the weekly issue. Work through the candidate content from curatinator_latest.md and populate draft.md.

Classification Rules

For each RSS POST, decide:

  1. Is it R-related? If not, skip it entirely.
  2. Is it already in the draft or flagged as a duplicate? If so, skip it.
  3. Which section does it belong to?
Section in draft.mdUse when
### TutorialsR tutorials showing how to use packages/tools; code is usually embedded
### InsightsArticles about R and data science in general; usually no code
### R in the Real WorldAnalyses using R on real-world data
### R in OrganizationsR use cases in organizations / companies
### R in AcademiaR use cases in academic / research settings
### Videos and PodcastsVideos, screencasts, podcasts about R
### ResourcesBooks, slides, cheatsheets, websites, longer learning resources
### Gist & CookbookShort code snippets, gists, recipes
### Shiny AppsShiny applications
### R InternationallyNon-English R content
### Call for ParticipationR groups, competitions, community calls
### Upcoming Events in 3 MonthsUpcoming R events (max 3 links)
### Grants & FundingGrants, funding opportunities related to R
### DatasetsNewly released or noteworthy datasets
### ConnectR jobs, communities
### rtistryGenerative art made with R

For CRANberries NEW entries: add under ### New Packages -> **CRAN**. For CRANberries UPDATED entries: add under ### Updated Packages.

Do NOT add anything to ### Highlight — editors vote for that section separately.

Link Format

+ [Title](URL)

For updated packages, preserve the diffify link if present:

+ [{pkgname} version](https://cran.r-project.org/package=pkgname) - [diffify](https://diffify.com/R/pkgname)

Images (optional, editor discretion):

![Alt text](https://raw.githubusercontent.com/...)

Fetching Page Content

To inspect a URL's content before classifying it, use any of:

  • WebFetch tool — built-in; use it directly.
  • curl https://r.jina.ai/https://www.example.com — fallback if WebFetch fails.
  • curl https://defuddle.md/example.com — second fallback.

Steps

  1. Check if any open Merge Request exists at https://github.com/rweekly/rweekly.org, if any prompt the user to check for then and continue only when the user has told you to.
  2. Run the script at scripts/curatinator.R.
  3. Read the current draft.md and curatinator_latest.md.
  4. Check for duplicate with scripts/find_duplicates.R; skip any flagged URLs.
  5. Process RSS POSTS: for each link, classify and add to the correct section in draft.md. Skip non-R content.
  6. Process CRANberries NEW: add new CRAN packages under ### New Packages -> **CRAN**.
  7. Process CRANberries UPDATED: add updated packages under ### Updated Packages.
  8. Edit draft.md using the Edit tool to insert the new links into the appropriate sections.
  9. Report a summary:
    • How many RSS posts were added (and to which sections)
    • How many CRAN new/updated packages were added
    • How many items were skipped (not R-related or duplicates)
    • Any items that were ambiguous and need editor review

Keep the existing content and structure of draft.md intact. Add new links at the bottom of each section, above any closing HTML comments.