Sigma Digital's engineering playbook — review skills covering API design, code review, database schema and migrations, documentation, frontend accessibility, GitHub Actions, incident postmortems, web performance, web security, and web SRE.
Reviews code changes for defects, design issues, and codebase coherence using a severity-ordered rubric and Conventional Comments. Use this whenever the user asks for a code review, a PR review, a pre-PR self-review, or wants feedback on a diff or branch — even when they only say 'review this' or 'look at this PR'.
Reviews REST and GraphQL API designs for contract quality, error shape, idempotency, versioning, pagination, and backwards-compatibility risk. Use this whenever the user is designing a new API, modifying an existing endpoint, reviewing an OpenAPI or GraphQL schema diff, or asks for an API design review — even if they don't explicitly mention 'the API design playbook'.
Reviews relational database work — schema design for new tables and relationships, online-safe migrations (locks, backfills, expand/contract, rollback), and query/index performance under load. Postgres-biased with explicit MySQL and SQLite call-outs. Use this whenever the user is reviewing a migration file, designing a new table, debugging a slow query, asking about indexes, or modifying schema — even if they don't say 'database review'.
Reviews technical documentation for clarity, accuracy, structure, and agent-readability while preserving the author's voice. Use this whenever the user is reviewing a README, design doc, runbook, ADR, contributor guide, or any markdown documentation — or asks for feedback on docs — even if they don't say 'documentation review'.
Reviews web frontends for WCAG 2.2 Level AA accessibility — semantic HTML, ARIA, keyboard interaction, screen reader experience, color contrast, forms, motion, and internationalization. Use this whenever the user is reviewing a UI component, building a form, auditing a page for a11y, asks about ARIA or screen readers, or asks for an accessibility review — even if they don't explicitly mention WCAG.
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.
Guides, prompts, and technical reference material for the engineering team at Sigma Digital.
This repo is the canonical home for how we build, review, and operate software. It pairs human-readable playbooks (the principles, checklists, and procedures we follow) with matching prompts (the LLM-ready versions of those playbooks, designed to run reviews and audits with an AI assistant).
The playbooks and prompts in this repo are also packaged as a Claude Code plugin. Skills auto-activate when you ask Claude to do relevant work — for example, "review this PR for security issues" will fire the web-security skill automatically.
/plugin marketplace add sigmadigitalza/engineering-playbook
/plugin install sigma-engineering@sigma-engineering-playbook
/reload-plugins
The same skills work with GitHub Copilot — copy any folder from plugins/sigma-engineering/skills/ into your repo's .github/skills/ directory, or into ~/.copilot/skills/ for personal scope. The SKILL.md format is a cross-vendor open standard.
docs/playbooksLong-form guides describing how we approach a discipline, what "good" looks like, and the specific checks and procedures we run.
| Playbook | What it covers |
|---|---|
| API design review | REST and GraphQL contract design, error shape, idempotency, versioning, and backwards-compatibility risk. |
| Code review | Sigma's posture, severity-ordered rubric, and Conventional Comments convention for PR review and pre-PR self-review. |
| Database review | Schema design, online-safe migrations, and query/index performance review for relational databases. |
| Documentation review | Standards and checks for technical documentation quality, structure, and accuracy. |
| Frontend accessibility review | WCAG 2.2 AA review of web frontends — semantic HTML, ARIA, keyboard, screen reader, contrast, forms, motion, i18n. |
| GitHub Actions review | Workflow design, security, and reliability practices for CI/CD pipelines. |
| Incident postmortem | Blameless postmortem template, drafting and review rubric for post-incident reviews. |
| Web performance | Core Web Vitals audit, lab-vs-field discipline, and quick-win optimisations for web applications. |
| Web security | Threat model, hardening checklist, and review procedure for web applications. |
| Web SRE | Reliability, observability, and incident-response practices for web services. |
docs/promptsEach playbook has a paired prompt designed to be handed to an LLM (Claude, ChatGPT, etc.) to run the review autonomously against a codebase, PR, or artefact.
npx claudepluginhub sigmadigitalza/engineering-playbook --plugin sigma-engineeringComprehensive 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.
v9.44.1 — Patch release for Gemini environment/version detection and qwen auth gating. Run /octo:setup.
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.
A growing collection of Claude-compatible academic workflow bundles. Covers scientific figures, manuscript writing and polishing, reviewer assessment, citation retrieval, data availability, paper reading, literature search, response letters, paper-to-PPTX conversion, and evidence-grounded Chinese invention patent drafting. Rules are organized as reusable skill folders with explicit workflows and quality checks.
Harness-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
UI/UX design intelligence. 67 styles, 161 palettes, 57 font pairings, 25 charts, 15 stacks (React, Next.js, Vue, Svelte, Astro, SwiftUI, React Native, Flutter, Tailwind, shadcn/ui, Nuxt, Jetpack Compose). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, mobile app. Elements: button, modal, navbar, sidebar, card, table, form, chart. Styles: glassmorphism, claymorphism, minimalism, brutalism, neumorphism, bento grid, dark mode, responsive, skeuomorphism, flat design. Topics: color palette, accessibility, animation, layout, typography, font pairing, spacing, hover, shadow, gradient.