a11y-audit
01Skill Claude Code
Run WCAG 2.2 Level AA accessibility audits against generated UI. Use when a story has ui:true or when asked to audit accessibility.
Heimdall is a lightweight, cross-platform hardware monitoring system with a real-time terminal dashboard.
This repository also configures its own agents. See what Heimdall tells them →
Skill Claude Code
Run WCAG 2.2 Level AA accessibility audits against generated UI. Use when a story has ui:true or when asked to audit accessibility.
Skill Claude Code
Generate a complete component file tree wired to design tokens with tests and Gherkin spec. Use when scaffolding a new UI component.
Skill Claude Code
Extract Gherkin scenarios from story markdown files into runnable .feature files and generate step definition stubs. Use when syncing stories to test suites.
Skill Claude Code
Read and write design tokens in W3C DTCG format (tokens.json) and emit CSS, Tailwind, and Mantine outputs. Use when modifying or generating design tokens.
Skill Claude Code
Apply Docker and Docker Compose best practices for containerising services. Use when writing or reviewing Dockerfiles and compose configs.
Skill Claude Code
Identify and annotate cloud cost implications of architectural decisions. Use when reviewing infrastructure changes or designing new services.
Skill Claude Code
Create, read, update, and link GitHub Issues as story artifacts throughout the story lifecycle. Use when managing issues for stories.
Skill Claude Code
Bootstrap and sync GitHub labels and milestones idempotently. Use when setting up a new repository or syncing label definitions.
Skill Claude Code
Manage GitHub Projects v2 board: add issues, update field values, and query board state. Use when managing project boards.
Skill Claude Code
Produce valid, consistently named Gherkin story files with correct IDs, timestamps, and tags. Use when writing or updating story files.
Skill Claude Code
Comprehensive gh CLI reference — issues, tasks, PRs, repos, branches, Actions, search, and project board. Use whenever interacting with GitHub.
Skill Claude Code
Remove AI-isms and artificial language patterns from text. Makes documentation, comments, commit messages, and prose sound more natural and human. Based on Wikipedia's "Signs of AI writing" patterns.
Skill Claude Code
Apply best practices for Jupyter notebooks: cell ordering, reproducibility, parameterisation. Use when working with .ipynb files.
Skill Claude Code
Audit code changes against Karpathy's 4 principles (Think Before Coding, Simplicity First, Surgical Changes, Goal-Driven Execution). Auto-called after Phase 5 IMPLEMENT; can also be invoked manually. Produces scored compliance report and blocks advancement if threshold not met.
Skill Claude Code
Apply Kubernetes and Kustomize patterns for deployments, services, and overlays. Use when writing or reviewing k8s manifests.
Skill Claude Code
Generate and validate Mermaid diagrams (component, sequence, ER, deployment, state machine) for features. Use when documenting architecture.
Skill Claude Code
Scaffold high-fidelity UI component mockups using the project UI stack consuming approved wireframes. Use when implementing approved wireframes.
Skill Claude Code
Universal dispatcher: run a named taffy workflow (.claude/taffy/ .yaml), a skill (/skill-name), or a sub-agent (@agent-name). Falls back to skills.sh registry when a skill is not found locally. Tracks all runs in .claude/state/maple.json so the maple TUI shows live progress.
Skill Claude Code
Use Playwright CLI for interactive browser exploration and snapshot-based interaction. Use when writing or running browser automation tests.
Skill Claude Code
Apply PostgreSQL schema, migration, and query patterns with idempotent SQL. Use when writing database schemas or migrations.
Skill Claude Code
Apply Redis data structure, caching, and pub/sub patterns. Use when integrating Redis into a service.
Skill Claude Code
Author and manage Architecture Decision Records (ADRs) in docs/specs/. Use when a significant architectural decision needs to be documented.
Skill Claude Code
Invoke the rubber duck reviewer for a second opinion. Use after planning, after complex multi-file implementations, or after writing tests. Produces a focused CRITICAL/WARN/INFO list and a APPROVE/REQUESTCHANGES verdict.
Skill Claude Code
Run ship-safe security and quality audit on the current project. Executes npx ship-safe audit . and reports findings by severity. Use before shipping any feature or PR.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: