Iuliandita Skills

· Handle git branches, commits, remotes, conflicts, hooks, signing, releases, PR/MR workflows. Triggers: 'git', 'commit', 'branch', 'merge', 'rebase', 'tag', 'push', 'PR', 'MR', 'gh', 'glab'.

· Build/review MCP servers, clients, tools, resources, OAuth. Triggers: 'mcp', 'model context protocol', 'mcp server', 'mcp client', 'fastmcp', '@modelcontextprotocol/server', '@modelcontextprotocol/sdk'. Not HTTP APIs (backend-api).

· Build/review AI apps: LLMs, RAG, embeddings, agents, evals, local inference. Triggers: 'llm', 'rag', 'embedding', 'openai sdk', 'agent loop', 'fine-tune', 'ollama', 'vllm'. Not for MCP (use mcp).

· Write/review CI/CD for GitHub Actions, GitLab, Forgejo/Gitea, Woodpecker. Triggers: 'ci/cd', 'pipeline', 'github actions', 'gitlab ci', 'runner', 'renovate', 'trivy'. Not for git workflows (use git).

· Browse/scrape web pages with Lightpanda, Playwright MCP, agent-browser, or fetch. Triggers: 'browse', 'scrape', 'headless', 'open url', 'read website', 'fill form', 'crawl'. Not for E2E tests (use testing).

· Write/review Dockerfiles, Compose, OCI/Podman/BuildKit builds, signing, hardening. Triggers: 'docker', 'dockerfile', 'podman', 'buildkit', 'buildah', 'skopeo', 'containerd'. Not for K8s manifests (use kubernetes).

· Write/review Ansible playbooks, roles, inventories, Vault, Molecule, AWX/AAP. Triggers: 'ansible', 'playbook', 'ansible role', 'ansible inventory', 'group_vars', 'ansible-lint'.

· Compress the current session into a handoff doc another agent continues from. Triggers: 'handoff', 'hand off', 'context handoff', 'fresh session', 'AFK run'. Not for idea capture (use roadmap) or full dev workflow (use dev-cycle).

· Capture, track, and prioritize ideas in gitignored ROADMAP.md. Triggers: 'roadmap', 'ideas', 'feature ideas', 'competitive analysis', 'what should I build', 'feature backlog'. Not for project management or code review.

· Write/debug tests: unit, integration, E2E, TDD, mocks, fixtures, a11y, perf. Triggers: 'test', 'test spec', 'TDD', 'playwright', 'vitest', 'jest', 'pytest', 'coverage', 'flaky'. Not for security tests (use security-audit).

· Administer Arch/CachyOS: pacman, AUR, systemd, boot, desktop, GPU, gaming. Triggers: 'arch linux', 'cachyos', 'endeavouros', 'manjaro', 'pacman', 'paru', 'mkinitcpio', 'hyprland'. Not for Debian/Fedora/NixOS.

· Audit app i18n/l10n: hardcoded strings, locale catalogs, translations, fallback gaps. Triggers: 'i18n', 'internationalization', 'localization', 'locale', 'translate app', 'multilingual', 'add language', 'hardcoded strings', 'next-intl'.

· Handle authorized privesc, CTFs, post-exploitation on Linux, containers, K8s. Triggers: 'privesc', 'CTF', 'pentest', 'post-exploitation', 'container escape', 'SUID', 'GTFOBins'. Not for hardening (use security-audit).

· Hunt novel vulnerabilities via reversing, patch diffs, fuzzing, and PoCs. Triggers: 'zero-day', '0-day', 'vulnerability research', 'CVE variant analysis', 'patch diffing', 'n-day variant', 'fuzz', 'exploit dev'. Not SAST: security-audit.

· Audit AI-generated code slop: hallucinated APIs, over-abstraction, duplicate code, test theater, noisy comments. Triggers: 'slop', 'AI-generated code', 'cleanup', 'overengineered'. Not for prose (use anti-ai-prose).

· Configure/tune/migrate PostgreSQL, MongoDB, MySQL/MariaDB, MSSQL. Triggers: 'database', 'postgres', 'mysql', 'mongodb', 'database schema', 'database migration', 'pgbouncer', 'EXPLAIN'. Not for HTTP APIs (use backend-api).

· Run dev workflow: branch, implement, lint/test, review, docs, PR, merge, release. Triggers: 'start working', 'kick off', 'wrap up', 'ship this', 'ready to ship'. Not for single git ops (use git).

· Administer NixOS/Nix: flakes, home-manager, nix-darwin, generations, overlays, disko. Triggers: 'nixos', 'nix', 'flake', 'home-manager', 'configuration.nix', 'nixos-rebuild'. Not for other distros.

· Write/review Terraform/OpenTofu HCL, modules, state, policy-as-code. Triggers: 'terraform', 'opentofu', 'hcl', 'tfvars', 'tfstate', 'tflint', 'terragrunt', 'checkov', 'CDKTF'. Not for Kubernetes manifests (use kubernetes).

· Run exhaustive 5-wave repo audits, persist findings, and generate phased tasks. Triggers: 'deep audit', 'comprehensive audit', 'full audit', 'mega review', 'deep review', 'audit report'. For quick sweeps, use full-review.

· Grill a plan before building: clarify the decision tree, then attack it. Triggers: 'grill me', 'deep grill', 'stress-test this plan', 'poke holes', 'what did I miss'. Not for existing code (code-review) or decision red-team (jekyll-hyde).

· Administer Kali: apt, branches, metapackages, images, live USB persistence, NetHunter, wireless/GPU. Triggers: 'kali', 'kali rolling', 'kali snapshot', 'kali-tweaks', 'nethunter'.

· Write/review Kubernetes manifests, Helm, Kustomize, Gateway API, ArgoCD, sealed secrets. Triggers: 'kubernetes', 'k8s', 'helm', 'kubectl', 'kubernetes deployment', 'pod', 'ingress', 'gateway api'.

· Configure/troubleshoot Linux networking: DNS, proxies, VPNs, VLANs, nftables, routing. Triggers: 'dns', 'reverse proxy', 'vpn', 'wireguard', 'tailscale', 'vlan', 'nftables', 'bgp', 'ospf', 'frrouting'. Not OPNsense: firewall-appliance.

· Design/review HTTP APIs for FastAPI, Express, NestJS: REST, OpenAPI, pagination, OAuth/JWT. Triggers: 'fastapi', 'express', 'nestjs', 'openapi', 'pagination', 'idempotency', 'rest api', 'endpoint'. Not for schemas (use databases).

· Review code for correctness: bugs, edge cases, races, leaks, regressions. Triggers: 'review this code', 'code review', 'find bugs', 'check this diff', 'sanity check'. Not for style/slop (anti-slop) or vulnerabilities (security-audit).

· Run 4 parallel audits: code-review, anti-slop, security-audit, update-docs. Triggers: 'full review', 'four-lens review', 'full repository review', 'code security docs audit', 'review before merge'. For deep coverage, use deep-audit.

· Review product, engineering, design, and business decisions with Jekyll/Hyde lenses. Triggers: 'jekyll', 'hyde', 'decision review', 'strategy review', 'red-team', 'dark pattern'.

· Administer RHEL/Fedora/CentOS/Rocky/Alma/Amazon Linux: dnf, yum, SELinux, firewalld, dracut. Triggers: 'rhel', 'fedora', 'centos stream', 'rocky', 'dnf', 'selinux'. Not for other distros.

· Sweep docs after changes: README, changelog, API, runbooks. Triggers: 'update docs', 'refresh docs', 'sync docs', 'docs drift', 'merged PR', 'release cut', 'version bump', 'update changelog'. Not for PR text (use git).

· Triage a live incident to localize an unknown failing layer, then route. Triggers: incident, outage, triage, production down, crashloop, 502. Not for known-component debugging (systematic-debugging) or repo audits (deep-audit).

· Route user requests to the right installed skill with minimal loading. Triggers: 'which skill', 'skill routing', 'choose skill', 'route this request', 'skill match'. Not for creating or editing skills (use skill-creator).

· Administer Synology DSM over SSH: volumes, btrfs, packages, snapshots, crash recovery. Triggers: 'synology', 'dsm', 'diskstation', '/volume1', 'synopkg', 'volume crashed'. Not for desktop Linux distros or their btrfs setups.

· Strip AI tells from prose in docs, PRs, emails, and your own replies. Filters every response once loaded; full audit on request. Triggers: 'unslop', 'ai writing', 'sounds like chatgpt', 'llm voice'. Not for code (use anti-slop).

· Audit read-only code slimming: dead/superseded code, unused files, duplicates, wrappers, inert try/catch, copy-per-element functions. Triggers: 'slim codebase', 'dead code', 'unused files', 'dedupe'. Not for bugs or broad reviews.

· Administer Debian/Ubuntu/Mint/Pop: apt, dpkg, PPAs, snaps, systemd, GRUB, HWE, desktop. Triggers: 'debian', 'ubuntu', 'mint', 'popos', 'apt', 'dpkg', 'ppa'. Not for Arch/Fedora/NixOS.

· Instrument and audit observability: metrics, traces, logs, alerts, SLOs, dashboards. Triggers: observability, metrics, tracing, prometheus, opentelemetry, grafana, slo. Not for live diagnostics (cluster-health) or manifests (kubernetes).

· Create/review skills: frontmatter, triggers, overlaps, collection consistency, retrospective updates. Triggers: 'skill creator', 'new skill', 'skill audit', 'skill review', 'update skill library'.

· Improve skill collections or a named skill with iterative scoring, lint checks, behavioral tests, peer review. Triggers: 'skill refiner', 'improve skills', 'quality sweep', 'batch improve', 'skill loop', 'target 99%'.

· Check Kubernetes cluster health with read-only diagnostics. Triggers: 'cluster health', 'health check', 'cluster status', 'diagnostics', 'post-maintenance', 'node status'. Not for manifests/IaC (use kubernetes).

· Write/debug shell commands, scripts, dotfiles, completions for zsh, bash, POSIX sh, fish. Triggers: 'shell', 'shell script', '.zshrc', '.bashrc', 'alias', 'shell completion', 'trap'. Not for CI blocks (use ci-cd).

· Write Claude Code routine prompts for schedules, APIs, and GitHub events. Triggers: 'routine', 'claude routine', 'scheduled claude task', 'unattended claude', '/schedule', '/fire'. Not one-off prompts: prompt-generator.

· Audit code security: OWASP, credentials, auth, access control, supply chain, hardening. Triggers: 'security audit', 'vulnerability scan', 'secret scan', 'OWASP', 'auth review'. Not for offensive work (use lockpick).

· Create/troubleshoot VMs and hypervisors: Proxmox, QEMU/KVM, libvirt, XCP-ng, VMware/vSphere. Triggers: 'proxmox', 'qemu', 'kvm', 'libvirt', 'virsh', 'vm', 'hypervisor', 'xcp-ng', 'vmware', 'esxi'. Not for containers (use docker).

· Build/critique frontend UIs with taste, rejecting AI design tells. Mobile-first, touch-aware, dark+light. Triggers: 'frontend', 'ui', 'ux', 'css', 'tailwind', 'landing page', 'ui design review'. Not for code logic (code-review).

· Manage OPNsense/pfSense via SSH: pfctl, pf rules, CARP, CrowdSec, pfBlockerNG. Triggers: 'opnsense', 'pfsense', 'pfctl', 'CARP', 'configctl'. Not for Linux firewalls.