Internal downstream skill for ctf-sandbox-orchestrator. CTF-sandbox workflow for queues, async workers, cron jobs, delayed tasks, retry behavior, worker-only config drift, and payload-to-side-effect chains. Use when the user asks to trace a queue payload, inspect async job execution, explain worker-only behavior, follow retries or dead-letter handling, or connect an enqueued item to a later file, cache, email, or privilege-bearing side effect. Use only after `$ctf-sandbox-orchestrator` has already established sandbox assumptions and routed here.

Internal downstream skill for ctf-sandbox-orchestrator. CTF-sandbox workflow for LSASS-resident secrets, Windows logon sessions, Kerberos ticket caches, DPAPI-backed material, SSP artifacts, and replayable credential extraction. Use when the user asks to inspect LSASS memory, recover tickets or logon sessions, trace DPAPI or SSP material, distinguish which credential artifacts are replayable, or connect host-resident credential material to an accepted pivot or privilege edge. Use only after `$ctf-sandbox-orchestrator` has already established sandbox assumptions and routed here.

Internal downstream skill for ctf-sandbox-orchestrator. CTF-sandbox workflow for GraphQL schemas, persisted queries, RPC manifests, generated clients, OpenAPI drift, hidden operations, and contract-to-handler mismatches. Use when the user asks to inspect GraphQL or RPC requests, compare client contracts to live handlers, recover hidden operations, trace generated clients, or explain how schema or contract drift produces the decisive behavior. Use only after `$ctf-sandbox-orchestrator` has already established sandbox assumptions and routed here.

Internal downstream skill for ctf-sandbox-orchestrator. CTF-sandbox workflow for firmware images, partition tables, boot chains, update packages, extracted filesystems, embedded configs, and device-facing trust boundaries. Use when the user asks to unpack firmware, map partition layout, inspect bootloader or init chains, recover update keys or credentials, trace config loading, or explain how a device surface reaches the decisive artifact. Use only after `$ctf-sandbox-orchestrator` has already established sandbox assumptions and routed here.

Internal downstream skill for ctf-sandbox-orchestrator. CTF-sandbox workflow for crypto, encoding, steganography, APK, IPA, and mobile trust-boundary challenges. Use when the user asks to decode a blob, recover a transform chain or key, inspect hidden media payloads, hook an APK or IPA signer, inspect app storage, or replay mobile request-signing logic. Use only after `$ctf-sandbox-orchestrator` has already established sandbox assumptions and routed here.

Manage matter workspaces — new, list, switch, close, or detach (practice-level). Use when working across multiple clients or matters in private practice and you need to create, list, switch, close, or detach the active matter so context from one engagement doesn't leak into another.

House cold-start for the litigation plugin — branches by role (in-house, firm associate, solo) and side (plaintiff, defense, both), captures risk calibration, landscape, and house style, and writes the practice profile CLAUDE.md. Use on a fresh install, when the user wants to set up or redo the practice profile, or to re-check available integrations.

Disable a community skill installed through the hub without removing its files. Use when the user wants to temporarily quiet a community skill ("disable [skill]"), stop its hooks from firing while keeping its config, or re-enable a previously disabled skill.

Check open leaves for deadline alerts and required decisions. Surfaces only the leaves that require an action and explains why — not a status board. Use weekly, or whenever the attorney needs to know which leaves have upcoming designation, certification, or exhaustion deadlines.

Update the status of an in-progress international expansion project — recalculates what is now unblocked, flags anything overdue, and surfaces the next priorities. Use when work has happened since the last session and the expansion tracker needs to reflect the current state.

House cold-start interview (request list + prior memo), or --new-deal for deal-specific context. Modular: identifies which practice areas apply (M&A, Board & Secretary, Public Company, Entity Management), then asks targeted questions for each active module and writes only the relevant sections to the plugin config. Use on fresh install, when CLAUDE.md still has [PLACEHOLDER] markers, when starting a new deal, or to re-check integrations or refresh a module.

Run the cold-start interview to learn your commercial contracts practice and write your team practice profile. Use on first use of the plugin, when `~/.claude/plugins/config/claude-for-legal/commercial-legal/CLAUDE.md` is missing or still contains template placeholders, or when the user says "set up the plugin", "configure commercial contracts", "onboard me", or "let's get started". This is the only skill that should run on a fresh install.

Train or fine-tune language and vision models using TRL (Transformer Reinforcement Learning) or Unsloth with Hugging Face Jobs infrastructure. Covers SFT, DPO, GRPO and reward modeling training methods, plus GGUF conversion for local deployment. Includes guidance on the TRL Jobs package, UV scripts with PEP 723 format, dataset preparation and validation, hardware selection, cost estimation, Trackio monitoring, Hub authentication, model selection/leaderboards and model persistence. Use for tasks involving cloud GPU training, GGUF conversion, or when users mention training on Hugging Face Jobs without local GPU setup.

Records research provenance as a post-task epilogue, scanning conversation history at the end of a coding or research session to extract decisions, experiments, dead ends, claims, heuristics, and pivots, and writing them into the ara/ directory with user-vs-AI provenance tags. Use as a session epilogue — never during execution — to maintain a faithful, auditable trace of how a research project actually evolved.

High-performance vector similarity search engine for RAG and semantic search. Use when building production RAG systems requiring fast nearest neighbor search, hybrid search with filtering, or scalable vector storage with Rust-powered performance.

Multi-agent orchestration framework for autonomous AI collaboration. Use when building teams of specialized agents working together on complex tasks, when you need role-based agent collaboration with memory, or for production workflows requiring sequential/hierarchical execution. Built without LangChain dependencies for lean, fast execution.

Optimizes LLM inference with NVIDIA TensorRT for maximum throughput and lowest latency. Use for production deployment on NVIDIA GPUs (A100/H100), when you need 10-100x faster inference than PyTorch, or for serving models with quantization (FP8/INT4), in-flight batching, and multi-GPU scaling.

Evaluates LLMs across 60+ academic benchmarks (MMLU, HumanEval, GSM8K, TruthfulQA, HellaSwag). Use when benchmarking model quality, comparing models, reporting academic results, or tracking training progress. Industry standard used by EleutherAI, HuggingFace, and major labs. Supports HuggingFace, vLLM, APIs.

Half-Quadratic Quantization for LLMs without calibration data. Use when quantizing models to 4/3/2-bit precision without needing calibration datasets, for fast quantization workflows, or when deploying with vLLM or HuggingFace Transformers.

High-performance RLHF framework with Ray+vLLM acceleration. Use for PPO, GRPO, RLOO, DPO training of large models (7B-70B+). Built on Ray, vLLM, ZeRO-3. 2× faster than DeepSpeedChat with distributed architecture and GPU resource sharing.