Develop applications using the Docyrus API with @docyrus/api-client and @docyrus/signin libraries. Use when building apps that authenticate with Docyrus OAuth2 (PKCE, iframe, client credentials, device code), make REST API calls to Docyrus data source endpoints, construct query payloads with filters, aggregations, formulas, pivots, and child queries, or integrate with external connectors (discover connectors, send requests through provider auth, run actions). Triggers on tasks involving Docyrus API integration, @docyrus/api-client usage, @docyrus/signin authentication, data source query building, Docyrus REST endpoint consumption, connector discovery, or external provider requests.
Autonomous incident detection, root-cause analysis, and self-healing for Linux/Docker production environments. Activate when the user mentions: server down, high CPU, memory leak, disk full, service crash, deployment failure, alert firing, on-call page, or any infrastructure emergency. Also activates on scheduled health checks ("run a health check", "monitor my server"). Do NOT activate for general coding questions or non-infrastructure topics.
Expert in Elixir, Phoenix Framework, and OTP. Specializes in building concurrent, fault-tolerant, and real-time applications using the BEAM. Use when building Elixir applications, working with Phoenix, implementing GenServers, or designing distributed systems on the BEAM.
Use this skill when the user wants Codex to hand off a task to GitHub Copilot CLI LongRun for unattended execution, prompt generation, status checks, or resuming previous long-running missions. Trigger on requests mentioning longrun, Copilot CLI long tasks, resumable missions, or asking Codex to launch Copilot as the execution backend.
Review Markdown documents using the MRSF (Sidemark) sidecar format. Use when asked to review, comment on, or provide feedback on Markdown files. Adds structured, anchored review comments via the MRSF MCP server.
HealthClaw Guardrails (healthclaw.io) — FHIR agent guardrails for secure clinical data access via MCP. Supports FHIR R4 US Core v9 (stable) and R6 ballot3 (experimental). Use when: (1) Reading patient data through MCP with automatic PHI redaction, (2) Writing clinical resources with two-phase propose/commit and step-up auth, (3) Proxying requests to real FHIR servers (HAPI, SMART Health IT, Epic), (4) Auditing AI agent access to healthcare data, (5) Evaluating R6 Permission resources for access control decisions. 12 MCP tools with guardrail enforcement.
Deploy a OpenClaw bot with Discord integration on a Vultr server.
Configure Deep Agent backends (StateBackend, FilesystemBackend, StoreBackend, LocalShellBackend, CompositeBackend, Sandboxes). Use when choosing storage, configuring file access, or setting up persistent state.
Audit web applications and codebases for the most common and dangerous security vulnerabilities — especially those introduced by AI-assisted ("vibe coded") development. Use this skill whenever the user asks to review code for security issues, harden an app, audit an API, check for vulnerabilities, or secure a project. Also trigger when the user mentions terms like "security review", "pentest checklist", "harden my app", "is my code secure", "fix security holes", "OWASP", "SQL injection", "XSS", "vibe code security", or shares backend/frontend code and asks if anything looks wrong. Even if the user just says "review my code" without mentioning security, consider triggering this skill — security is always relevant. --- # Vibe-Code Security Audit Systematic security audit for web applications, with special attention to vulnerabilities that AI code-generation tools introduce most frequently.
Use this skill when the user wants Codex to hand off a task to GitHub Copilot CLI LongRun for unattended execution, prompt generation, status checks, or resuming previous long-running missions. Trigger on requests mentioning longrun, Copilot CLI long tasks, resumable missions, or asking Codex to launch Copilot as the execution backend.
Build production-ready REST APIs with versioning, documentation, and rate limiting. Use when the user wants to create API endpoints, build a REST API, add API resources, or generate OpenAPI documentation. Triggers: "build api", "create endpoint", "api resource", "rest api", "api documentation", "swagger", "json api", "graphql".
Kills a process listening on a specific port. Use this skill when a server fails to start because a port is already in use (e.g., EADDRINUSE) or when explicitly asked to free up a port.
