/skills
Reusable capabilities for AI coding agents, installable with a single command.
npx skills add agustinusnathaniel/skillsPlugin installation for Claude Code, Codex, and ZCode
Install the whole collection as a plugin, or use the picker above to select individual skills.
Claude Code
/plugin marketplace add agustinusnathaniel/skills
/plugin install agustinusnathaniel-skills@agustinusnathaniel-skillsCodex CLI
codex plugin marketplace add agustinusnathaniel/skills
codex plugin add agustinusnathaniel-skills@agustinusnathaniel-skillsZCode
Open Settings → Plugins → Create → Add marketplace. Enter agustinusnathaniel/skills, then install agustinusnathaniel-skills.
Software Engineering
Skills for admin panels, webhooks, hydration, configuration, CI, calculations, client trust, testing, pruning, and tool adoption.
/admin-panel-engineering
Use when building admin panels, backoffice apps, or internal tools: permission-gated pages and menus, login and logout, tenant scoping, list pages, exports, and audit trails. Includes Ant Design, Filament, and SWR references.
/architecture-decision-framework
Use when comparing consequential architecture or implementation approaches, selecting technology, or revisiting a design after changed constraints or feedback.
/bulk-import-engineering
Use when planning, building, or auditing data import and export: bulk file imports with validation previews and safe recovery, backup and restore, and JSON, CSV, or spreadsheet import and export in offline-first apps.
/calculation-correctness
Use when implementing or reviewing code that computes money, dates, units, counters, or derived metrics, so totals stay correct across retries, timezones, partial payments, and row edits.
/client-trust-boundary
Use when exposing environment variables or API keys to a web or mobile client, calling Firebase, Supabase, or Convex from the client, or gating features by role in the UI.
/codebase-dossier
Invoke by name to write an evidence-cited dossier of a codebase or a family of related repos: purpose, architecture, operations, history, decisions, and sharp edges.
/config-drift
Use when changing environment variables, build or header config, service workers, hosting config, or CI, and when a setting seems to have no effect. Checks the value the running system actually uses.
/github-actions-authoring
Use when writing or debugging GitHub Actions workflows and reusable workflows: timeouts, caching, gates that actually fail, least-privilege permissions, and inputs that work for every caller.
/hydration-safe-state
Use when debugging hydration mismatches or theme flashes, or when prerendered or server-rendered pages read localStorage, cookies, sessions, or the viewer's time and locale.
/mobile-app-shell
Use when building a React Native or Expo app shell: environments and release channels, remote config and forced updates, token refresh, push notifications and deep links, and web views.
/prune-codebase
Use when substantially reducing code and supporting tests, documentation, configuration, and tooling while preserving intended behavior and useful rationale, including leftovers from starter templates and forks.
/release-notes
Use when writing or reviewing changelogs and release notes for end users, developers, or maintainers, with every entry checked against what actually shipped.
/test-strategy
Use when choosing the smallest meaningful test boundary, planning failure-first coverage, or requiring repeatable E2E evidence for complex features. Prefers real storage over mocks, and includes behavior checks for forms, uploads, and permission-gated reports.
/tool-evaluation-and-adoption
Vet an open-source tool before adopting it. Use when asked to evaluate, switch to, or install a tool, library, or package, including a platform that client work will be built on. When it replaces a tool, the old one is removed everywhere.
/url-state
Use when putting filters, pagination, or share links in the URL, or when a shared link crashes, opens the wrong view, or leaks the sender's state.
/webhook-integration
Use when handling payment or other provider webhooks, settlement and reconciliation, partner APIs with rate limits, queue retries, or scheduled sync jobs, so replays and partial failures stay recoverable.
Automation
Recurring improvement loops that run without per-cycle direction.
/autonomous-improvement-loop
Compound small improvements on a recurring schedule without per-cycle direction. Use when running unattended improvement cycles over one repo or a portfolio. Learns per-target rules from merged and closed deliveries.
Research
Deep domain research via canonical authorities and frameworks.
/domain-research
Use when researching how to build or run something, or synthesizing knowledge across domains through canonical authorities and frameworks. Track source roles and provenance so conclusions retain their basis.
No skills found matching your search.