Claude Skills by jscraik

Use when authoring or reviewing TypeScript code that requires strict type safety, explicit module contracts, and predictable runtime boundaries.

Build shared project vocabulary, glossary terms, aliases, prompt translations, domain-grill interviews, and agent instruction links when wording is fuzzy or overloaded.

Audit unused functions, dead exports, orphaned modules, stale imports, unreachable code, and tech-debt cleanup candidates with evidence-backed removal guidance. Use when unused code, dead code, remove unused imports, stale-code checks, or scoped cleanup evidence are needed.

Create, repair, and validate uv Python project setup. Use when initializing Python apps or libraries, managing uv dependencies, virtual environments, or CI-ready uv workflows.

Install, repair, and validate Vale prose linting. Use when users need Vale config, style sync, docs lint gates, or broken Vale workflow diagnosis.

Review and validate completion claims. Use when you are about to say work is complete, fixed, passing, pushed, or ready for review.

Create and review YAML files with safe indentation, schema-aware structure, and low-surprise serialization. Use when editing YAML config or workflow files.

Plan, implement, and validate backend service changes. Use when patching or adding backend features in an existing API, data, auth, worker, or service codebase.

Create and validate implementation-grade CLI specifications when command trees, JSON contracts, dry-run plans, errors, or agent-ready behavior need a binding spec.

Design and validate MCP server tools when standard integrations need schemas, safe auth, resources, prompts, and Inspector-ready verification.

Build safe Oak Curriculum API learning flows. Use this skill when Oak endpoints, curriculum maps, or child-facing Apps SDK guidance are needed.

Create, render, and validate Mermaid diagrams when users need Mermaid source converted into SVG, PNG, HTML previews, or polished diagram assets.

Create or update an Obsidian-friendly local markdown knowledge base. Use when the user wants LLM-maintained notes, wikilinks/backlinks, frontmatter, citations, local attachments, vault cleanup, or reusable research synthesis.

Draft evidence-backed release notes and changelog entries. Use this skill when PR notes, GitHub releases, or npm handoff need traceability.

Download, transcribe, inspect, summarize, or convert video and audio sources. Use when the user wants transcripts, subtitles, audio extraction, or media downloads from a video source.

Create self-contained HTML visual explainers from technical material. Use this skill when diagrams, matrices, timelines, or browser artifacts beat plain text.

Generate, review, and refine high-retention technical YouTube hooks, outlines, and scripts. Use when the user wants video scripting tailored to a topic, audience, runtime, and evidence-bound claims.

Audit, validate, and troubleshoot Agentation integrations in frontend apps. Use when annotations, MCP registration, endpoint sync, webhook delivery, or watch mode readiness are failing.

Audit UI implementation quality when frontend work needs accessibility, responsiveness, theming, performance, and anti-slop guardrails.

Search, compare, and extract SVG icons from Iconify collections. Use when the user needs production-ready UI icons, icon family consistency, or exact SVG markup.

Govern and validate design-system changes. Use when tokens, typography, spacing, iconography, themes, or style aliases need repository-grounded evidence.

Audit, fix, and validate accessibility issues. Use when adding or reviewing controls, forms, dialogs, keyboard behavior, focus management, ARIA labels, color contrast, or WCAG compliance.

Audit, fix, and validate HTML metadata. Use when shipping pages that need titles, descriptions, canonical URLs, Open Graph tags, Twitter cards, favicons, JSON-LD, or robots directives.

Design or implement production-ready frontend screens and components. Use this skill when UI build, redesign, accessibility, layout, or state coverage is needed.

Generate route-aware Open Graph image workflows from existing web apps. Use this skill when route-specific social preview assets need refresh or creation.

Build and audit polished interaction refinements for existing React or Tauri UI when motion, accessibility, reduced-motion, and browser-verified behavior need focused improvement.

Review, triage, and validate visual regression diffs. Use when the user wants snapshot-change analysis, layout regression evidence, Storybook diffs, Playwright screenshots, or Argos review.

Automate Atlas on macOS when users explicitly ask to control Atlas tabs, bookmarks, history, or desktop browser state.

Analyze, review, and plan architecture alternatives through a structured interview. Use when the user needs tradeoffs surfaced before implementation or a Linear decision note instead of an ADR.

Analyze, deepen, and validate an existing doc or topic through a structured interview. Use when refining PRDs, Linear tickets, notes, or draft specs before planning or execution.

Analyze underspecified requests with a short decision interview. Use this skill when guessing would risk the wrong plan.

Plan, diagnose, and validate 1Password CLI workflows. Use when tasks need op CLI sign-in, secret references, op run, op inject, item reads, env injection, or service-account secret access.

Audit, review, and harden Better Auth integrations. Use when the user wants Better Auth security review, config debugging, provider hardening, session checks, or operational risk guidance.

Create, migrate, or validate Better Auth implementation work. Use when the user wants Better Auth added or changed in code, including OAuth, passkeys, 2FA, magic links, or org flows.

Run, audit, and design authorized Recon Workbench workflows when scoped target interrogation needs evidence artifacts, redaction, validation, and safe reporting.

Analyze git-history security ownership when sensitive files, CODEOWNERS coverage, bus factor, contributor concentration, and remediation evidence need mapping.

Run CodeRabbit CLI review for staged, committed, or all changes when users request risk-focused feedback or an implementation-review-fix loop.