nbiish

Post-quantum cryptography secrets management system for protecting API keys, tokens, and private data.

Expert instructions to implement and verify ML-DSA-65 post-quantum cryptographic signatures and agentic workflow security.

Enterprise-grade codebase intelligence via a TWO-LAYER knowledge graph. Use GitNexus (MCP-native, AST-precise, call-graph aware) as the always-on operational layer for code call-chains, blast-radius, and rename. Use Graphify (multimodal, code+docs+papers+video+image) as the on-demand semantic enrichment layer for cross-document reasoning, PR triage, and visual deliverables. Trigger on: "how does X work", "what calls Y", "what breaks if I change Z", "show me the architecture", "ingest this paper/RFC", "triage my PRs", "client briefing", "merge-order risk", "find dead code", "explain this symbol", "find god nodes", or any codebase question. Skips guessing, fast-paths through cached graphs.

Multi-tool coding skill integrating gstack (Claude Code skills), claude (Claude Code), and mini-live (mini-swe-agent with Live-SWE-agent config). Use when spawning Claude Code sessions for coding work, running security audits, code reviews, QA testing URLs, building features end-to-end, or planning before building. Also configures and orchestrates sub-agents to maximize utilization of all AI subscriptions and APIs. For MCP-equipped sub-agent dispatch with provider fallback, pair with pi-mini-orchestrator skill.

Multi-agent orchestration via fixed claude→mini rotation with scoped MCP tools and provider fallback chains. Every dispatch gets exactly the MCP servers it needs, a provider chain that auto-recovers from API failures, and its own git worktree for filesystem isolation. Use when dispatching subagent tasks, running parallel coding work across subscriptions, or orchestrating complex multi-step code changes.

Enhances and hardens markdown documents through two independent pipelines — (1) fusing external knowledge bases into a target document via multi-agent orchestration, and (2) recursively optimizing documents for multi-model LLM effectiveness using a split→optimize→review→merge architecture.

Extracts structured markdown knowledge bases from YouTube videos by combining spoken transcripts with sequential visual frames via a Vision-Language Model (VLM). Use this when you need to turn a video into a deep, searchable knowledge document.

Modern Prompting & Context Engineering Framework. Includes techniques like OOReDAct, Chain-of-Thought, Chain-of-Draft, ReAct, and more for advanced LLM steering.

Multi-expert advisory council. Dispatches sub-agents that each inherit a distinct expert identity and append their analysis to a single shared deliberation document. Use for any decision, analysis, or question that benefits from multiple expert perspectives: investment, risk, strategy, growth, valuation, or general advisory.

LLM & Agentic AI Security Skill. Domain knowledge for securing probabilistic AI components, including prompt injection defense, RAG security, and MCP hardening.

Modern Prompting & Context Engineering Framework. Includes techniques like OOReDAct, Chain-of-Thought, Chain-of-Draft, ReAct, and more for advanced LLM steering.

Multi-agent orchestration via fixed-order rotation across equal CLI coding agents (Gemini, Claude, OpenCode, mini, pi, kilo, crush). Use when dispatching subagent tasks, running parallel agent work, or orchestrating code changes across multiple tools. Implements YOLO mode (non-interactive) execution with automatic fallback on failure and git worktree isolation per subagent.

Creates a subagent to autonomously find books, leaks, and other content via Google Dorks and WebSearch. Invoke when user wants to research a topic, find leaks, or expand the knowledge base.

Extracts W5 (Who, What, Where, When, Why) from any video URL or webpage and automatically updates the Obsidian Knowledge Graph. Invoke when user provides a new URL or asks to process media.

Expert instructions to implement and verify ML-DSA-65 post-quantum cryptographic signatures and agentic workflow security.

Post-quantum cryptography secrets management system for protecting API keys, tokens, and private data. Includes the 10 browser_secrets_* MCP tools (betterbrowsermcp v0.7.0+ rotates v0.8.0+), the append-only audit log at ~/.config/pqc-secrets/audit.log, and the PQC Rust binary (ML-KEM-768 + AES-256-GCM).

Diagnose missing files in git worktrees — when a file exists in the main worktree but not in a linked worktree, check .gitignore

Integrate ML-KEM-768 + AES-256-GCM key persistence into a Node.js server via a Python UV inline script

Debug silent JS failures from template literal backslash escaping when embedding JS strings in server-rendered HTML

Enables YOLO Mode to iteratively plan, implement, verify, and converge on a completed coding outcome.

Enables YOLO mode with Text-to-Speech feedback via tts-cli (or YOLO_TTS_COMMAND override).

Post-quantum cryptography secrets management system for protecting API keys, tokens, and private data.

Expert instructions to implement and verify ML-DSA-65 post-quantum cryptographic signatures and agentic workflow security.

Multi-expert advisory council. Dispatches sub-agents that each inherit a distinct expert identity and append their analysis to a single shared deliberation document. Use for any decision, analysis, or question that benefits from multiple expert perspectives: investment, risk, strategy, growth, valuation, or general advisory.

Multi-tool coding skill integrating gstack (Claude Code skills), pi (pi-coding-agent), and mini (mini-swe-agent). Use when spawning Claude Code sessions for coding work, running security audits, code reviews, QA testing URLs, building features end-to-end, or planning before building. Also configures and orchestrates pi and mini to maximize utilization of all AI subscriptions and APIs. For MCP-equipped sub-agent dispatch with provider fallback, pair with pi-mini-orchestrator skill.

Hugging Face ML Intern CLI (`ml-intern`) — an agent that turns natural-language goals into end-to-end ML workflows using the HF ecosystem. Use when: the user wants to research papers/datasets, fine-tune models, run ML experiments, publish artifacts to HF Hub, or perform any multi-step ML engineering task. Combines research, code generation, sandbox execution, and Hub publishing. Use with `hf` CLI for deterministic repo/space/job operations.

Date-stamped iterative goal execution across 6 passes (ITERATION 0 through 5). Use when the user says ">doU" or "run doU", asks for iterative refinement with tracking, wants to execute a prompt through multiple progressive passes, or needs a goal file with iteration history. Triggers on any request involving iterative execution with date-stamped goal files.