Results for “lockheed-martin”

Meta's 7-8B specialized moderation model for LLM input/output filtering. 6 safety categories - violence/hate, sexual content, weapons, substances, self-harm, criminal planning. 94-95% accuracy. Deploy with vLLM, HuggingFace, Sagemaker. Integrates with NeMo Guardrails.

Meta's 7-8B specialized moderation model for LLM input/output filtering. 6 safety categories - violence/hate, sexual content, weapons, substances, self-harm, criminal planning. 94-95% accuracy. Deploy with vLLM, HuggingFace, Sagemaker. Integrates with NeMo Guardrails.

Generates a comprehensive copilot-instructions.md file that guides GitHub Copilot to produce code consistent with project standards, architecture patterns, and exact technology versions by analyzing existing codebase patterns.

Generates a comprehensive README.md by analyzing project documentation files in .github/copilot and copilot-instructions.md.

Lint and format Python code for Megatron-LM using ruff, black, isort, pylint, and mypy, with commands for autoformatting and import ordering.

飞书邮箱 — draft, compose, send, reply, forward, read, and search emails; manage drafts, folders, labels, contacts, and attachments. Use when user mentions 起草邮件, 写一封邮件, 拟邮件, 草稿, 发通知邮件, 发送邮件, 发邮件, 回复邮件, 转发邮件, 查看邮件, 看邮件, 读邮件, 搜索邮件, 查邮件, 收件箱, 邮件会话, 编辑草稿, 管理草稿, 下载附件, 邮件文件夹, 邮件标签, 邮件联系人, 监听新邮件, draft, compose, send email, reply, forward, inbox, mail thread.

Detect prompt injections and jailbreak attempts in LLM applications using Meta's 86M parameter classifier. Filter user inputs, third-party data, and RAG documents with low latency and multilingual support.

Master advanced prompt engineering techniques to maximize LLM performance, reliability, and controllability in production. Use when optimizing prompts, improving LLM outputs, or designing production prompt templates.

飞书会议纪要（Note）直查：已知 note_id 时查询纪要详情、展示类型、关联文档 token，并读取 unified 原始逐字记录。当用户已持有 note_id，或从文档显式 vc-node-id 获得 note_id 时使用。不负责会议/日程/妙记定位、文档标题搜索或 Docx 正文读取。

Multi-agent autonomous startup system for Claude Code. Triggers on "Loki Mode". Orchestrates 100+ specialized agents across engineering, QA, DevOps, security, data/ML, business operations, marketing, HR, and customer success. Takes PRD to fully deployed, revenue-generating product with zero human intervention. Features Task tool for subagent dispatch, parallel code review with 3 specialized reviewers, severity-based issue triage, distributed task queue with dead letter handling, automatic deployment to cloud providers, A/B testing, customer feedback loops, incident response, circuit breakers, and self-healing. Handles rate limits via distributed state checkpoints and auto-resume with exponential backoff. Requires --dangerously-skip-permissions flag.

Track elapsed time from a set epoch with tamper-evident locking, supporting count-up, count-down, and count-between modes, milestones, and email notifications.

Multi-cloud orchestration for ML workloads with automatic cost optimization. Use when you need to run training or batch jobs across multiple clouds, leverage spot instances with auto-recovery, or optimize GPU costs across providers.

Push the LLM to reconsider, refine, and improve its recent output. Use when user asks for deeper critique or mentions a known deeper critique method, e.g. socratic, first principles, pre-mortem, red team.

Activation-aware weight quantization for 4-bit LLM compression with 3x speedup and minimal accuracy loss. Use when deploying large models (7B-70B) on limited GPU memory, when you need faster inference than GPTQ with better accuracy preservation, or for instruction-tuned and multimodal models. MLSys 2024 Best Paper Award winner.

LLM observability with Langfuse — tracing, evals, prompt management, cost tracking

Expert in designing effective prompts for LLM-powered applications. Masters prompt structure, context management, output formatting, and prompt evaluation. Use when: prompt engineering, system prompt, few-shot, chain of thought, prompt design.

Hunt for Mimikatz execution using command-line patterns, LSASS access signatures, binary indicators, and in-memory detection of known modules.

Imported skill tracing from langchain

Automate multi-turn adversarial conversations against LLM agents using Microsoft PyRIT, including Crescendo and Tree-of-Attacks-with-Pruning (TAP) attack chains with scorer feedback loops.

Build editorial/magazine/report webpages on a GENUINE Müller-Brockmann modular grid (International Typographic Style), not a decorative one. Encodes the discipline — columns + modules + baseline, grotesque type, flush-left ragged-right, restrained black/white/red — AND the front-end engineering that makes the grid load-bearing: one CSS-variable source of truth, a grid-toggle overlay that lives in the SAME content box as the content, subgrid 'bands' so every element snaps to a column line, an 8px baseline lock, and runtime optical alignment that puts display type's ink (not its box) on the line. Ships a scaffold generator and a Puppeteer harness that proves 0px adherence. Use when: building any editorial, magazine, report, or longform page that must read as rigorously grid-aligned, Swiss, International Typographic Style, or 'Müller-Brockmann'. Triggers: magazine spread, grid system, Swiss design, editorial layout, show the grid, grid overlay toggle, baseline grid, modular grid, 12-column layout, 瑞士网格, 版面网格.

Execute remote commands on Windows targets using WMI-based lateral movement techniques, including Impacket wmiexec.py, CrackMapExec, and native PowerShell WMI commands for red team engagements.

Graduate a proven pattern from auto-memory (MEMORY.md) to CLAUDE.md or .claude/rules/ for permanent enforcement.

Deploy Meta's LlamaGuard moderation model to filter LLM inputs and outputs across 6 safety categories using HuggingFace, vLLM, or FastAPI.

Fetch and analyze LangSmith execution traces to debug LangChain and LangGraph agents, investigate errors, and review tool calls and performance.

Expert prompt optimization system for the prompts INSIDE an AI product you are building — system prompts, LLM feature prompts, chatbot/agent instructions. Use when the user wants to write or improve a system prompt for an AI feature they're shipping, review/critique an LLM prompt, apply prompt-engineering techniques (chain-of-thought, few-shot, structured output, hard constraints) to a product prompt, or optimize cost/latency of a production prompt. Do NOT use this to clarify or structure the user's own vague request to Claude Code — that is `prompt-clarifier`'s job, not this skill's.

Builds a custom LWC lookup component with typeahead search via Apex SOSL/SOQL, debounce, keyboard navigation, and pill UI for cases where standard pickers fall short.

Push the LLM to reconsider, refine, and improve its recent output. Use when user asks for deeper critique or mentions a known deeper critique method, e.g. socratic, first principles, pre-mortem, red team.

Meta's 86M prompt injection and jailbreak detector. Filters malicious prompts and third-party data for LLM apps. 99%+ TPR, <1% FPR. Fast (<2ms GPU). Multilingual (8 languages). Deploy with HuggingFace or batch processing for RAG security.

Jailbreak API-served LLMs using G0DM0D3 techniques — Parseltongue input obfuscation (33 techniques), GODMODE CLASSIC system prompt templates, ULTRAPLINIAN multi-model racing, encoding escalation, and Hermes-native prefill/system prompt integration. Use when a user wants to bypass safety filters, jailbreak a model, or red-team model robustness.

Unified LLM Gateway - One API for 70+ AI models. Route to GPT, Claude, Gemini, Qwen, Deepseek, Grok and more with a single API key. Use when: the user needs model routing, provider setup, or Chinese LLM access guidance.

飞书妙记：搜索妙记、查看妙记基础信息、下载/上传音视频、读取或编辑妙记的产物内容、改标题、替换说话人/关键词、申请妙记查看/编辑权限。当给出minute_token、本地音视频文件，要查/改/转妙记产物，或用户明确要主动申请妙记权限时使用；本地音视频转纪要/逐字稿优先走本 skill，不要用 ffmpeg/whisper 本地转写。不负责：获取会议关联妙记，或仅按自然语言标题定位纪要

Computes the SQuAD metric using torchmetrics, given predictions and ground truth. Use when evaluating question-answering outputs with exact match and F1 scores.

Multi-agent autonomous startup system for Claude Code. Triggers on "Loki Mode". Orchestrates 100+ specialized agents across engineering, QA, DevOps, security, data/ML, business operations, marketing, HR, and customer success. Takes PRD to fully deployed, revenue-generating product with zero human intervention. Features Task tool for subagent dispatch, parallel code review with 3 specialized reviewers, severity-based issue triage, distributed task queue with dead letter handling, automatic deployment to cloud providers, A/B testing, customer feedback loops, incident response, circuit breakers, and self-healing. Handles rate limits via distributed state checkpoints and auto-resume with exponential backoff. Requires --dangerously-skip-permissions flag.

Guides using the lightning-record-picker base component for single-record selection in LWC, covering display-info, matching-info, graph-QL filters, and accessibility.

Multi-agent autonomous startup system for Claude Code. Triggers on "Loki Mode". Orchestrates 100+ specialized agents across engineering, QA, DevOps, security, data/ML, business operations, marketing, HR, and customer success. Takes PRD to fully deployed, revenue-generating product with zero human intervention. Features Task tool for subagent dispatch, parallel code review with 3 specialized reviewers, severity-based issue triage, distributed task queue with dead letter handling, automatic deployment to cloud providers, A/B testing, customer feedback loops, incident response, circuit breakers, and self-healing. Handles rate limits via distributed state checkpoints and auto-resume with exponential backoff. Requires --dangerously-skip-permissions flag.