EvilFreelancer

Turn any OpenAPI/Swagger API into CLI commands and call them. Search endpoints with BM25, check parameters, execute — no MCP server needed.

Generate secure MikroTik RouterOS v7 configurations from a plain-language description, or review and harden an existing /export. Use when the user asks to write, generate, build, audit, or harden a MikroTik / RouterOS config, firewall, NAT, PPPoE + RADIUS BNG, site-to-site WireGuard, hotspot captive portal, or ISP edge router. Always applies a security-hardening baseline, takes per-model port and interface names from devices/, and never invents IPs or secrets — it emits clearly marked placeholders plus a fill-in checklist.

Use when the user invokes /token-cost or asks for the floor / bedrock / self-cost / "real" price of LLM tokens on a self-hosted server — the physical lower bound from electricity plus hardware amortization, NOT the market API price. The skill measures power draw and generation speed ON the server (nvidia-smi, streaming benchmark) and asks for electricity tariff, hardware cost and amortization period, then prints cost per 1M input/output tokens. Triggers: "сколько на самом деле стоит токен", "цена самохоста", capacity and break-even planning.

Run when the user invokes /rpa-init or asks to onboard or warm up context on a repository. The agent studies code, reads documentation and test code, sets up the dev environment as the project expects, runs tests, and writes a short project report. No extra user brief is required.

Run when the user invokes /rpa-gen-rules or asks to create or refresh agent project rules (Cursor .mdc, Claude Code CLAUDE.md and .claude/rules). Infers from specs, docs, and code. Rules use a layered-cake model (implement inner layers with no dependencies first, then the next layer) and BDD-style delivery. Generated rules include a mandatory Rules Sync step so changes to one agent's tree are mirrored to every other agent's tree (Cursor <-> Claude <-> AGENTS.md) in the same commit. No separate user brief required.

Run when the user invokes /rpa-feat together with a clear feature description (for example issue text). BDD workflow: plan, failing tests, implementation, green tests, full suite, docs and examples, linter at the end. Will not work correctly without the user supplying what to build.

Run when the user invokes /rpa-bugfix together with a clear bug description (expected vs actual, reproduction). Reproduction test first, then fix, full test suite, short report. Will not work correctly without the bug details.