3.2.0 — 🚪 Same Skills, New Doors

This release skips straight from 2.0.0 to 3.2.0 — 3.0.0 and 3.1.0 happened in plugin.json but never got their own GitHub release, so this is where everyone catches up in one hop. Bring a snack.

Breaking Changes (carried over from the unreleased 3.0.0)

• Five skills lost their standalone installability: daily-planning-ritual, setting-up-a-project, writing-product-specs, writing-user-stories, and writing-verification-plans each shipped a duplicate .claude-plugin/plugin.json next to their marketplace entry, which let them be installed on their own — inconsistent with every other skill in the library. Those manifests are gone; all five are now reachable only through the claude-code-skills bundle.

What's New

• Codex CLI and Cursor can now read every skill natively. All skills are symlinked under .agents/skills/ — the shared open-standard path those tools already look for — plus new Codex/Cursor plugin manifests for both the full bundle and project-foundations. Nothing is duplicated; skills/ stays the one canonical copy, everyone else just gets a window into it.
• working-on-an-issue went hands-off. No more approval gates before the PR — the PR is now the single review checkpoint. Adds a budgeted recon step that stops once the change is located, a verification plan written before the implementation plan, sizing off-ramps to issue-decomposition/requirement-elicitation, and a verification-failure path through systematic-debugging.
• setting-up-a-project now flags the GitHub Actions Node 20 deprecation, steering generated workflows (and CLAUDE.md) away from the deprecated runtime before it bites you in CI.

Docs

• Landing page, skills index, and install instructions refreshed across the site and project-foundations bundle to match the multi-tool install paths.
• Site title updated.

Housekeeping

• Added an internal GitHub Actions workflow to sync issues into project board 13.

Full Changelog: 2.0.0...3.2.0

2.0.0 — 🪦 RIP summoning-the-user: A Eulogy in Semver

This one's a major version bump, which around here means "we killed a couple of skills and made everyone else go to therapy." 29 skills went under the knife. Two didn't make it. The rest came out more self-aware.

Breaking Changes

• summoning-the-user is dead. It has been removed from the marketplace entirely. It served bravely, in the sense that it existed.
• user-story-template has been absorbed into writing-user-stories — the INVEST checklist and Given-When-Then acceptance criteria now live there. If you had this installed standalone, update your plugin list; it's not coming back as its own thing.
• Marketplace and bundle plugins jump to 2.0.0 (claude-code-skills, project-foundations) to reflect the removals above. 26 individually published skills bump to 1.1.0 for the refinements below (additive, non-breaking).

What's New

• project-foundations bundle — a curated plugin bundling eight skills (setup, issue decomposition, user stories, verification plans, and the architecture/dependency/Mermaid diagram trio) for taking a project from "idea" to "diagrammed plan," single-sourced via symlinks so nothing is duplicated.
• sgai-goal — new skill for composing GOAL.md files for SGAI-driven repos.
• idea-to-design and roughly 20 other skills imported from the old LLPM collection, covering planning, stakeholder tracking, at-risk detection, FAQ generation, and more.
• Individual skill installation — every skill can now be installed on its own instead of forcing the whole collection on you.

Under the Hood: The Skill Review Overhaul

Every one of the 29 skills got audited against skill-authoring best practices, because apparently we'd been winging it. Highlights:

• Stripped unsupported frontmatter fields (instructions, tags) from 16 skills and folded their trigger phrases into actual discoverable "Use when..." descriptions.
• Every skill that fetches GitHub or external data now states its tool prerequisites (gh CLI, MCP connectors) with concrete setup commands, instead of silently failing and letting you guess why.
• Replaced leftover references to a defunct LLPM notes system and phantom claude.ai artifacts with real file conventions (docs/stakeholders/, requirements-<project>.md).
• Fixed broken cross-references (britt/*, obra/*), a name mismatch in daily planning, and a scan tool in project-analysis that was, to put it gently, fictional.
• Bundled TDD.rules.md directly into setting-up-a-project instead of fetching it from main at runtime.
• Restored the architecture-diagramming skill's CRITICAL Mermaid syntax section (no-parentheses, matching-brackets) after it got accidentally collapsed to a one-liner — this guards against a real GitHub rendering bug, so it's staying emphatic.

Fixes

• Root plugin.json was pinned to 1.3.0 while the marketplace entry said otherwise; since plugin.json wins at install time, this was silently freezing users on an older version. Fixed, and claude plugin validate . --strict now passes.
• Corrected the documented install syntax everywhere (README + 28 skill pages): it's /plugin install <name>@britt, not /plugin install britt/<name>. The owner/repo form only works for marketplace add.

Docs

• Documentation site synced with the overhaul: new pages for sgai-goal and project-foundations, both linked from the homepage, bundle-install instructions documented, and drift fixed across 19 skill pages that had gone stale.
• Added semantic-release commit examples (fix/feat/perf/breaking) to the contributing docs, because someone asked "what does a breaking change commit actually look like" one too many times.

Full Changelog: 1.1.0...2.0.0

1.1.0 Trust but verify

New Skills

setting-up-a-project

A project bootstrapping skill that helps Claude author a well-structured CLAUDE.md file before writing any code. This skill guides you through:

• Defining project purpose - Name, problem statement, and approach
• Configuring tech stack - Language, runtime, package manager, testing framework, linting, and build tools with sensible defaults per language
• Establishing development practices - Mandatory TDD rules, git branching strategy, and commit discipline

The core principle: A well-configured project prevents rework and ensures consistency, helping Claude Code avoid doom loops where code is written, broken, and rewritten repeatedly.

writing-verification-plans

A skill for creating acceptance testing procedures that validate your project works in real-world scenarios. Key features:

• Real-world verification - Uses actual systems, never mocks or fakes
• Structured scenarios - Clear prerequisites, steps, and success criteria
• Automatic execution - Runs after completing any task
• Detailed logging - Documents exactly what was tested and observed

This skill integrates with setting-up-a-project and summoning-the-user for a complete development workflow.

Installing

Add the marketplace (if not already added)

  /plugin marketplace add britt/claude-code-skills

Your mom and I are so proud...

What's New

• There's a release that exists 🍾
• Plugin marketplace support - Install skills directly with /plugin commands
• Reorganized documentation - Clearer installation instructions for Claude Code and Claude.ai
• Three ways to install:
  • Claude Code plugin marketplace (recommended)
  • Claude Code manual installation
  • Claude.ai via project knowledge

Quick Start

Add the marketplace

/plugin marketplace add britt/claude-code-skills

Install a skill

/plugin install summoning-the-user

Available Skills

Skill	Description
daily-planning-ritual	Interactive daily planning across work and personal life
summoning-the-user	Gets your attention when Claude needs input in the background
writing-product-specs	Write comprehensive product specifications
writing-user-stories	Write properly formatted user stories

Claude.ai Users

Download the zip files below and upload them to your project's knowledge section.