Engineering workflows end-to-end: spec → stacked PRs → review → ship. Includes the original Anthropic skills (standups, code review, architecture, incident response, docs) plus an extended workflow layer (TDD with red-green-refactor, disciplined diagnosis, careful-review, security-review, deploy-checklist, stacked-PR shipping with safe git hooks). 34 skills total.
Create or evaluate an architecture decision record (ADR). Use when choosing between technologies (e.g., Kafka vs SQS), documenting a design decision with trade-offs and consequences, reviewing a system design proposal, or designing a new component from requirements and constraints.
Re-read the code you just wrote (and anything else you modified) with fresh eyes and look hard for bugs, errors, awkward design, dead code, or things that will confuse the next reader. Then fix what you find. Use after a batch of edits, when the user says "careful review", "look it over again", "give it another pass", or before opening a PR.
Review code changes for security, performance, and correctness. Trigger with a PR URL or diff, "review this before I merge", "is this code safe?", or when checking a change for N+1 queries, injection risks, missing edge cases, or error handling gaps.
Run an OpenAI Codex code review on the current branch's changes against a base, extract findings, fix confirmed P0/P1 issues, and commit. Useful after a batch of work for a structured second opinion before shipping.
Structured debugging session — reproduce, isolate, diagnose, and fix. Trigger with an error message or stack trace, "this works in staging but not prod", "something broke after the deploy", or when behavior diverges from expected and the cause isn't obvious.
External network access
Connects to servers outside your machine
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
AI specialists for every role at your company.
Sales preps calls. Engineers ship PRs. Finance closes the month. Marketing ships campaigns. Each role gets Claude tuned to their work and connected to their real tools (HubSpot, Slack, Snowflake, Notion, Linear).
pace.tools · Cookbook · Docs · Catalog
Pace is a curated bundle of AI agents you install into Cowork (the Claude desktop app) or Claude Code (the CLI). One agent per role, each one fluent in that role's vocabulary and connected to the SaaS tools the team already uses.
/pace router for the commands that are specific to your
company. /pace teach captures how your team actually works once;
everything else builds on it.For front-end code-level design, Pace defers to impeccable; the installer offers to bring it.
Open Cowork → Plugins → Add marketplace → paste:
GoldenBerry-SO/Pace
Then install whichever plugin matches your role: sales, marketing,
engineering, data, finance, ...
claude plugin marketplace add GoldenBerry-SO/Pace
claude plugin install sales@pace
Or use the guided picker:
npx pace-tools install
Just describe what you need. The skills auto-trigger from natural language; you don't need to remember commands.
Prep me for the Acme call tomorrow.
> sales / call-prep fires, pulls HubSpot history + recent news, drafts the brief.
Write a SQL query for monthly active users by plan tier, last 6 months.
> data / write-query takes over, drafts the query, runs it against Snowflake if connected.
Review this PR. Look for real bugs first.
> engineering / code-review takes the PR, reads the diff, posts comments.
For your team's own commands, use the /pace router:
/pace teach # one-time: capture how your company works
/pace standup # then: anything you've authored as a /pace:* command
The engineering plugin includes 34 engineering skills. Beyond the obvious
review/test/diagnose ones, there's a disciplined stacked-PR
workflow: spec → implement → review → topr → next. See
the engineering cookbook
for the deep-dive.
pace.tools/
├── skill/ ← the /pace router (your team's commands)
├── plugins/ ← the 50-plugin catalog
│ ├── sales/ ← Anthropic-authored, imported verbatim
│ ├── engineering/ ← Anthropic + PiXeL16/skills + authored
│ ├── ...
│ └── partner-built/ ← Apollo, Common Room, Slack, etc.
├── .claude-plugin/
│ └── marketplace.json ← registers all 50 plugins
├── site/ ← pace.tools (Astro)
├── cli/ ← npx pace-tools CLI
└── NOTICE.md ← full attribution
Pace is open source, fork it, rename the router, write commands specific to your operation. We also help companies adopt Pace end-to-end: install + connector setup, command authoring tuned to your team's workflows, training, and ongoing enablement.
Talk to GoldenBerry · About GoldenBerry
See NOTICE.md for full attribution. Apache 2.0 throughout.
Company-wide skills for AI coding agents. One router (/pace), many commands across engineering, product, ops, marketing. Built on the same install tech as impeccable.
Search across all of your company's tools in one place. Find anything across email, chat, documents, and wikis without switching between apps.
Manage tasks, plan your day, and build up memory of important context about your work. Syncs with your calendar, email, and chat to keep everything organized and on track.
Create, customize, and manage plugins tailored to your organization's tools and workflows. Configure MCP servers, adjust plugin behavior, and adapt templates to match how your team works.
Company-wide skills for AI coding agents. One router (/pace), many commands across engineering, product, ops, marketing. Built on the same install tech as impeccable.
npx claudepluginhub goldenberry-so/pace --plugin engineeringHarness-native ECC operator layer - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
Upstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Upstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.
Reliable automation, in-depth debugging, and performance analysis in Chrome using Chrome DevTools and Puppeteer
Comprehensive feature development workflow with specialized agents for codebase exploration, architecture design, and quality review