Dev & Coding

A practical WCAG 2.2 AA toolkit for news and academic sites: alt text rules, accessible charts, keyboard patterns, and automated axe-core audits.

Teaches Claude to create, fork, and share Ghost managed PostgreSQL databases via CLI or MCP for agent workflows.

A skill documenting the `.claude/plugin-name.local.md` convention for storing and reading per-project Claude Code plugin configuration.

A reference skill for wiring MCP servers (stdio, SSE, HTTP, WebSocket) into Claude Code plugins, covering config, auth, and debugging.

Audits existing Rust code for soundness, error handling, API design, and idiom, then produces a prioritized review report with cited rules and minimal fixes.

Terminal-first browser control with playwright-cli — navigate, fill forms, screenshot, mock networks, trace, and generate Playwright tests.

Production-tested Playwright guidance for writing, debugging and scaling E2E, API, component, visual and accessibility test suites.

Drive all of Azure DevOps — work items, PRs, pipelines, wikis, test plans, policies — through natural language in Claude Code.

Diagnoses your LaTeX toolchain, installs only the missing packages, and gives the exact compile pipeline for your project.

A skill for designing type-safe @ConfigurationProperties binding, validation, profiles and secret handling in Spring Boot 3.

Turns any technical decision into a complete Nygard-format ADR with context, options, consequences and review triggers (Spanish edition).

Turns raw API specs, endpoint notes, or Postman collections into polished developer-facing reference documentation.

A collaborative Q&A workflow that turns a rough idea into an approved, committed design spec before any code is written.

Runs and safely fixes lint/format issues with Ruff for Python and Biome for JavaScript/TypeScript.

Scans a repo for nine kinds of technical debt and produces a prioritized, effort-estimated cleanup report with optional safe auto-fixes.

Read an AST-derived code graph as plain files to instantly answer structural questions like "what calls X?" and "what breaks if I change this?".

Query an AST-derived code graph as virtual files to answer structural questions like "what calls X?" and "what breaks if I change this?".

A read-only skill that audits an agent's context against four places — system prompt, tools, history, tail — and ranks fixes by tokens saved per turn.

Turns a vague task into a machine-checkable definition of done, writes goal-test.sh, and optionally wraps a headless agent in a bounded retry loop.

Audits a pipeline for bounded decisions that don't need a frontier model and proposes rule / classifier / small-model gates with fail-closed escalation.