OXI-717

@oxi-717 source repo

17 skills
0 followers
6 hours ago last updated

▌
Agent Teams · oxi-717
Use when facing complex tasks needing parallel collaboration between multiple agents with shared state, coordination, and direct inter-agent communication. Triggers on "создай команду", "agent team", "параллельная работа агентов", "team of agents"

0
installs
▌
Team Review · oxi-717 bundle
Use when the user invokes /team-review, team-review, asks for the team-based code review workflow, wants multi-pass or multi-agent review, or wants the review → fix → build/test → re-review loop. Supports Codex by using native subagents only when the user explicitly asks for the multi-agent/team review behavior; otherwise run the same reviewer roles locally.

0
installs
▌
Cc Analytics · oxi-717
Use when user asks for Claude Code usage stats, weekly analytics, project activity summary, or wants to see what projects were worked on. Triggers on "аналитика", "статистика claude", "cc stats", "weekly report", "что делал"

0
installs
▌
Security Hardening · oxi-717 bundle
Comprehensive security audit and hardening checklist for VPS servers, WordPress sites, and Next.js applications. Covers SSH hardening, firewall configuration, fail2ban, CrowdSec, kernel sysctl, Docker security, SSL/TLS, WAF, OWASP Top 10, headers, secrets management, backups, and incident response. Use this skill whenever the user mentions security, hardening, securing a server, защита сервера, обезопасить VPS, security audit, security checklist, or asks about SSH, firewall, fail2ban, ports, brute force, DDoS, WAF, SSL certificates, security headers, or any topic related to protecting servers, websites, or web applications from attacks — even if they don't explicitly say 'security'.

0
installs
▌
Statusline Setup · oxi-717
Use when user asks to set up, configure, or troubleshoot the Claude Code statusline. Triggers: "setup statusline", "fix statusline", "statusline not working", "show usage limits", "context percentage". NOT for general status questions.

0
installs
▌
Deep Interview · oxi-717 bundle
Focused clarification interview for vague tasks. Asks questions one at a time, explores codebase for context, outputs structured brief for planning/execution. Triggers: "interview", "clarify task", "deep interview", "define requirements", "scope this out", "what exactly do you need", "let's clarify", "gather requirements"

0
installs
▌
Infocompressor · oxi-717 bundle
Use when the user needs to compress, condense, or summarize lengthy content while preserving ALL critical details. Triggers: "compress this", "make it shorter but keep everything", "create a cheat sheet", "dense summary", "reference format", "compact version", "information-dense". NOT for casual summaries—only when user explicitly wants maximum density with zero data loss.

0
installs
▌
Context Handoff · oxi-717
Use when user asks about context handoff, preserving context across compaction, restoring session state, or mentions HANDOFF.md. Also activates automatically after compact/clear when additionalContext contains "CONTEXT RESTORED FROM PRE-COMPACTION HANDOFF". Triggers: "handoff", "save context", "preserve context", "restore after compact", "context lost", "session continuity". NOT for general text compression—use infocompressor for that.

0
installs
▌
Setup My Context · oxi-717 bundle
Build a personal or team Claude Code/Codex working structure through an interview: workspace, AGENTS.md, rules, memory habits, delegation, and delivery pipeline. Triggers on setup my context, set up AGENTS.md, собери структуру Claude Code, настрой рабочую директорию, создай правила для агентов, L0-L4 runbooks.

0
installs
▌
Openrouter Setup · oxi-717 bundle
Configure OpenRouter as an OpenAI-compatible endpoint (OPENROUTER_API_KEY in env, never in code) for waitlist-gated models: moonshotai/kimi-k3, deepseek/deepseek-v4, z-ai/glm-*

0
installs
▌
Research Ensemble · oxi-717 bundle
Multi-agent adversarial research with Exa AI. Two levels: standard (3-5 agents, 30-60 min) and deep (10-15 agents, full ensemble with 3 cycles). Triggers: "research X", "исследуй", "deep research", "find out about", "compare options for", "deep dive into", "gather information on", "write a report about", "проанализируй", "разберись в", "investigate", "analyze topic", "сравни варианты", "изучи тему"

0
installs
▌
Ctx Init · oxi-717 bundle
Initialize AGENTS.md + CLAUDE.md + rules/ in a code repo (fresh mode). Triggers on "/ctx-init", "init context", "scaffold AGENTS.md", or when user asks to set up project context in a new repo.

0
installs
▌
Ctx Lint · oxi-717 bundle
Validate @-imports across all ctx AGENTS.md files. Finds broken links, missing end markers. Supports auto-fix for trivial issues. Triggers on "/ctx-lint", "validate imports", "check AGENTS.md", "what broke in context".

0
installs
▌
Pentest · oxi-717 bundle
Outside-in black-box security audit of a running web application. Use when the user asks to check a web app / Telegram mini app for vulnerabilities, find security issues, audit an app from the outside, do a pentest / security review of a deployed app. Keywords: pentest, проверь на уязвимости, security audit, найди дыры, vulnerability scan, mini app audit, Telegram mini app, vercel app security, Next.js security, Supabase RLS check. Produces a human-readable report, an evidence log, and per-finding fix files that a coding agent can consume. Four aggression levels L0-L3. NOT for load testing (use loadtest instead) and NOT for hardening the user's own server (use security-hardening instead).

0
installs
▌
Loadtest · oxi-717 bundle
Lightweight HTTP load testing with Locust. Use when the user asks to run a load test / stress test / нагрузочное тестирование / check RPS a web app can handle / measure latency under load / simulate N users. Generates a Locustfile from a template, runs the test for a bounded duration, outputs JSON stats + a markdown report with p50/p95/p99 latency, error rate, and per-endpoint breakdown. Trigger keywords: load test, loadtest, нагрузка, нагрузочное тестирование, stress test, simulate N users, RPS, requests per second, locust. NOT for security probing (use pentest instead) and NOT for real traffic simulation at production scale (link to the distributed JMeter setup for that).

0
installs
▌
Notebooklm · oxi-717 bundle
Use this skill to query your Google NotebookLM notebooks directly from Claude Code for source-grounded, citation-backed answers from Gemini. Browser automation, library management, persistent auth. Drastically reduced hallucinations through document-only responses.

0
installs
▌
Screencast · oxi-717
Records a screencast/demo video of a web-app flow (browser chrome, address bar, synthetic cursor, click ripples, narration captions). Use when the user asks to record a demo, capture a walkthrough, make a product video / screencast / демо-ролик, записать видео-демо, снять прохождение или работу приложения, сделать скринкаст. Reconnoiters the live flow via Playwright MCP, generates a declarative YAML scenario, renders mp4 to ./screencast/. NOT for screenshots (use webapp-testing), load testing (loadtest), or security testing (pentest).

0
installs

17 published skills