claude

yalesites-product

Product team workflows for YaleSites: release prep, ticket creation and grooming, PR feedback, drafting web content for yalesites.yale.edu, keeping tickets in sync with how work actually turns out, UX research context for product decisions, Beacon AI chatbot test question sets and comparison analysis, and read-only migration assessment of a source site against the YaleSites content model.

0 on GitHubby Yale ITS Digital Experiencesv0.17.0updated 3 days agodevelopment
/

Plugin yalesites-product from marketplace yalesites-claude-plugins in yalesites-org/yalesites-claude-plugins. Commands read from the repo's manifest — 2 days ago.

What it installs

Skills (20)

  • backlog-hygiene

    Audit the YaleSites backlog for tickets that don't meet the team's ticket standards and report what needs attention. Read-only: it never edits, closes, or relabels anything. Use when the user asks to check, audit, sweep, review, or clean up the backlog, wants to know which tickets need grooming befo

  • beacon-comparison-review

    Analyze a Beacon AI Tester comparison JSON export (compare-N-M.json, with run_a/run_b metadata, a summary, and per-question pairs with answers and citations) for answer correctness, citation quality, and notable divergences between the two runs. Use for any A/B comparison from the Beacon AI Tester r

  • beacon-question-set

    Build a quick, content-accuracy-only question set for testing Beacon (or the legacy ai_engine) against one site's published content, exported as an upload-ready .txt plus a QA tracking spreadsheet. Use when the user wants to spot-check whether Beacon answers factual questions correctly, e.g. 'make a

  • beacon-test-bank

    Build or extend the full tiered Beacon test bank: a persistent, versioned question set covering content knowledge, whether Beacon knows its limits, guardrails/injection/jailbreak safety, and real-use robustness, backed by a manifest (question ID, tier, expected answer, fail signals) and a single can

  • feature-planning

    Run a planning session for a new YaleSites feature before it becomes a ticket: research the idea from every source we can reach (the yalesites-project code and the component library repos, the portfolio crawl, Pantheon, GitHub history, UX research, the docs site, live sites, and external research on

  • github-screenshots

    Put a screenshot into a YaleSites GitHub issue or comment without anyone dragging it in by hand. `gh` and API tokens cannot upload images, so this commits the image to the `screenshots` branch of yalesites-org/YaleSites-Internal and returns an <img> tag to paste into the body. Use whenever a screens

  • yalesites-migration-assessment

    Assess a public source website — starting with Drupal, including Drupal 7 — for migration onto the YaleSites platform, and produce a migration-path assessment: source-to-YaleSites content type and component mapping, the things that will not carry over cleanly with a suggested handling for each, an e

  • onboard

    Walk a non-technical product or content person through setting up their Mac or Windows computer so the `ticket` skill works, from a blank machine to a green check. Claude runs the checks and installs, explains each step in plain words, and stops only where the person must act (a browser login, an or

  • yalesites-pr-feedback

    The human half of YaleSites PR review, and the only way a PR reaches an approved state. Use whenever the user asks to review, look at, check, approve, or give feedback on a PR, even without the words 'PR feedback' explicitly, e.g. 'can you check PR 1288', 'review this PR', 'is this one ready to merg

  • rc-domino-hunt

    Hunt a YaleSites release candidate for the edge cases and domino effects that PR-level testing never looked at: cross-PR collisions, shared component, token, and contrib-patch changes rippling into blocks nobody tested, new validation landing on old real content, and filter, theme, color, and layout

  • yalesites-release-prep

    End-to-end release prep workflow for YaleSites. Covers: drafting GitHub release notes, writing supplementary documentation for the featured new feature, drafting the release email communication, updating the Current Issues & Fixes page on yalesites.yale.edu, adding Release Testing Steps to GitHub is

  • reviewer-profile

    Builds or updates the personal reviewer profile that tells the pr-feedback skill what a given person actually reviews, so a design reviewer stops getting asked to rule on code and a developer stops getting asked to rule on UI copy. Use when someone wants to set up, see, change, or reset how PR revie

  • router

    Run the YaleSites router: hand each feature phase (UX, Design, Development, QA, Visual regression, Docs) to its next owner when the phase before it finishes, and post a brief of who owes what: open `needs-decision` and `follow-up` items grouped by person with their due dates, plus In progress ticket

  • ticket-sync

    Check whether a GitHub issue still matches how the work actually turned out, and either edit it or comment on it to catch it up. Use standalone when someone asks 'does this ticket need updating,' 'is the ticket still accurate,' 'sync the ticket to the PR,' or 'does the epic need to reflect this.' Al

  • ticket

    Create and groom GitHub issues for the YaleSites backlog, including scoping multi-ticket epics. Use when creating a new issue, filling out an existing stub ticket, reviewing a ticket for completeness, or preparing issues for an upcoming sprint or grooming session. Also use when the user wants to cre

  • yalesites-ux-research

    User experience research context for the YaleSites platform. Use when evaluating feature requests, scoping tickets, making product decisions, advising editors or site builders, or assessing whether a proposed change serves the platform's users well. Contains the six current user archetypes, top pain

  • yalesites-design-pass

    Run an agentic first design pass on a YaleSites UX or Design phase ticket (a `<Feature>: UX` or `<Feature>: Design` child in yalesites-org/YaleSites-Internal), so the reviewer reviews and signs off on drafts instead of starting from a blank page. Three rounds, each on a local review board: round 1 s

  • yalesites-docs-board

    Take a batch of YaleSites docs tickets from ticket to built draft in one pass: match each ticket against the full yalesites.yale.edu sitemap, screenshot the live page it changes, draft the change, and show every ticket on a local side-by-side board (live page on the left, proposed blocks on the righ

  • yalesites-page-build

    Build a drafted page on yalesites.yale.edu in a visible Playwright browser: create an unpublished page, or stage a forward draft revision of a published one, assemble it in Layout Builder, and verify it before handing it back. Use when the user asks to build, stage, create, or put a page draft on th

  • yalesites-web-content

    Draft web content for the YaleSites website (yalesites.yale.edu): user guide pages, resource pages, release documentation, and knowledge base updates. Use this skill whenever the task is to write, draft, revise, or update a page that will live on yalesites.yale.edu, including when the request only n

View source on GitHub

More from yalesites-org/yalesites-claude-plugins

All 4 plugins →

Day-to-day Git, pull-request, GitHub-issue, and Drupal development skills for YaleSites developers — look up/plan issues, conventional commits, cross-repo branch management, PR description and creation, Drupal coding conventions, and running PHPUnit tests in the YaleSites Lando environment.

8 skills

0

yalesites

claude

Deep expertise on the YaleSites Drupal platform: Layout Builder, blocks, Views, content types, menus, taxonomy, accessibility, editorial workflow, and training resources. Includes the yalesites-portfolio skill with measured block adoption, config trends, exemplar sites and page patterns from a crawl of the live portfolio (known gaps: Gallery unreviewed, 5 sites without data).

2 skills

0

Security tooling for YaleSites projects — currently supply-chain auditing (malicious-package detection via live OSV.dev and GitHub malware advisories), distinct from ordinary CVE scanning.

1 skill

0

Similar plugins

superpowers

claudecodex

Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques

15 skills · hooks

obra/superpowers 316,836

context7

claudecodex

Up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your coding agent's context.

1 MCP server

upstash/context7 64,709

Build powerful, stateful CLI interfaces for any GUI application using the cli-anything harness methodology.

5 commands

HKUDS/CLI-Anything 58,665

Automates browser interactions for web testing, form filling, screenshots, and data extraction

12 skills

vercel-labs/agent-browser 50,373

Use Alibaba Open Code Review from local Codex.

2 skills

alibaba/open-code-review 50,068

slidev

claude

Claude Code skill for creating and presenting Slidev slidedecks

1 skill

slidevjs/slidev 49,452

Maintain yalesites-product?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex plugins4 plugins