shadcn/ui done right. Component customization, form patterns with React Hook Form + Zod, theming, accessibility, and composition patterns your AI agent should follow.
★not rated 0 7mo agoA
tokens not measured
originalMIT
Injects live local time + timezone into every prompt so Claude never says 'tonight' in the morning. Stamps every response with [HH:MM AM/PM TZ]. Zero config, zero dependencies beyond jq.
★not rated 0 4mo agoA
tokens not measured
originalMIT
Swipe to apply for jobs using the Worklittle MCP app, and search over 4 million jobs with filters like visa status, distance, and salary, and connect your Worklittle account to save jobs you love.
★not rated 0 29d agoA
tokens not measured
originalMIT
Use Magic Patterns (magicpatterns.com) from your coding agent: prototype ideas, generate UI inspiration, upload local UI, and integrate Magic Patterns designs into your codebase.
★not rated 0 1mo agoA
tokens not measured
originalMIT
Server operations over SSH — health checks, container/service control, log tailing, config edits, Postgres introspection, and declarative deploys — driven through a single compiled CLI that never lets the agent see a password, private key, host, user, or port.
★not rated 0 2mo agoA
tokens not measured
originalMIT
Static security audit skill for web application codebases: stack triage, checklist-driven scan, and a PASS/FAIL/MANUAL-REVIEW report with file:line evidence and remediation code.
★not rated 0 20d agoA
tokens not measured
originalMIT
Interrogates recently shipped work with seven socratic questions, forcing evidence-backed answers about confidence, blind spots, decay, and unstated assumptions.
★not rated 0 20d agoA
tokens not measured
originalMIT
Claude Code adapter for the shared Windows Dev Agent runtime: truth-preserving Windows discovery, host-owned approval, capability routing, package setup, isolation, and ecosystem cleanup.
★not rated 0 23d agoA
tokens not measured
originalMIT
Local, on-demand maintenance skills for SvelteKit + TypeScript repos: security, performance, refactoring, accessibility, and test-coverage scanners that each fix one issue per run and leave the diff for review.
★not rated 0 20d agoA
tokens not measured
originalMIT
A skill that activates a rigorous research collaborator mode: flags confidence levels, prevents hallucinations, cites sources, and surfaces assumptions.
★not rated 0 20d agoA
tokens not measured
originalMIT
Reviews how a Claude Code session was conducted rather than what it shipped — classifies its shape, scores the run, flags where the context window went, and turns recurring cost into wire-ins for the skills it used or a named lever on the environment that caused it.
★not rated 0
changed todayA
tokens not measured
originalMIT