Results for “garak”
55 skillsRed Teaming Llms With Garak
Run NVIDIA garak probe suites against an LLM endpoint to test for jailbreaks, prompt injection, data leakage, and toxic generation, then interpret the hit-rate report for triage and reporting.
24.6k · bundle
Testing For System Prompt Leakage
Test LLM applications for system prompt leakage using manual payloads, garak, and Promptfoo to extract embedded secrets and routing logic.
24.6k · bundle
More results
Testing Prompt Injection In RAG Pipelines
Probe RAG applications for prompt injection via poisoned retrieved context and embedding manipulation.
24.6k · bundle
RAG
Build and debug Retrieval-Augmented Generation pipelines — chunking, embedding, retrieval, reranking
1 · bundle
Stakr Protocol
Interact with the Stakr protocol to create ERC-4626 vaults, add and modify multi-reward staking programs, and manage agent-owned vaults.
1.2k · bundle
Agent Agentic RAG
Expert en RAG agentique (retrieval multi-étapes, self-query, chunking adaptatif, tool-augmented generation)
6
Rpk Group
Manage Kafka consumer groups on Redpanda with rpk group: list, describe, seek, delete groups, and delete offsets.
6 · bundle
Giskard RAG
Giskard RAGET (RAG Evaluation Toolkit): automatic testset generation (simple / complex / distracting / conversational), component-level scoring (retriever / generator / rewriter), hallucination and bias tests, CI integration. Compared to RAGAS and DeepEval. USE WHEN: user mentions "Giskard", "RAGET", "Giskard RAG toolkit", "automatic testset generation", "component-level RAG scoring", "hallucination test Giskard" DO NOT USE FOR: general RAGAS usage - use `rag-evaluation`; Stanford ARES - use `ares-framework`; CI/CD wiring - use `continuous-evaluation`
28
Grok Designer
Delegates UI, UX, and visual design tasks to Grok 4.5 through a dedicated CLI, covering critique, art direction, HTML mockups, and SVG assets.
57 · bundle
Zarr Python
Store and process large N-dimensional arrays with chunking, compression, and parallel I/O, integrating with NumPy, Dask, and Xarray for cloud-native scientific computing.
30.2k · bundle
Jobbank Search
Make sure to use this skill whenever the user mentions anything related to job searching on Akademikernes Jobbank, jobbank.dk, or looking for academic or highly educated positions in Denmark — even if they don't mention jobbank.dk explicitly. Also invoke this skill for questions about Danish job listings, graduate trainee positions, Ph.d. jobs, or finding work in specific industries or regions in Denmark. Trigger phrases include: jobbank, akademikernes jobbank, jobs denmark, academic jobs denmark, find job denmark, highly educated jobs, graduate job denmark, trainee position denmark, ph.d. position denmark, postdoc denmark, studiejob, fuldtidsjob, deltidsjob, vikariat, freelance job, praktikplads, job søgning, jobsøgning, søg job, ledige stillinger, nye jobs, it jobs denmark, engineering jobs denmark, marketing jobs denmark, finance jobs denmark, healthcare jobs denmark, remote job denmark, fjernarbejde, job københavn, job aarhus, job odense, nyuddannede job, job til nyuddannede, international job denmark, jo
0 · bundle
Lark
Turns Lark collaboration noise into prioritized action by triaging chat, approvals, meetings, docs, spreadsheets, calendars, and email with a default read-only counselor mode.
32 · bundle
Agentic RAG
Agent-driven RAG patterns. Self-RAG, Corrective RAG (CRAG) with web fallback, Adaptive RAG with routing classifier, ReAct with retrieval tool, multi-hop retrieval, plan-and-execute, LangGraph state machines for RAG. USE WHEN: user mentions "agentic RAG", "Self-RAG", "Corrective RAG", "CRAG", "Adaptive RAG", "multi-hop retrieval", "LangGraph RAG", "ReAct RAG", "plan and execute RAG" DO NOT USE FOR: static retrieval pipelines - use `rag-architecture`; query rewriting only - use `query-transformations`; evaluation - use `rag-evaluation`
28
QA
Systematically QA test a web application and fix bugs found. (gstack)
0 · bundle
QA
Systematically QA test a web application and fix bugs found. (gstack)
0
Rtk
Install, initialize, verify, and troubleshoot RTK (Rust Token Killer) for AI coding agents. Use when you need to reduce shell-command token output, confirm that the correct `rtk` binary is installed, choose between Homebrew, install.sh, or Cargo installation, wire `rtk init` for Claude Code, Codex, Gemini CLI, Cursor, Copilot, Windsurf, Cline, or OpenCode, or use compact wrappers such as `rtk git status`, `rtk read`, `rtk grep`, `rtk test`, `rtk lint`, and `rtk gain`. Triggers on: rtk, rust token killer, token saver cli, rtk init, rtk gain, codex rtk, gemini rtk, opencode rtk, claude hook token reduction.
42 · bundle
Form 8k
Drafts SEC Form 8-K current reports with item-accurate narratives, exhibit indexing, and EDGAR-ready formatting. Use when a public company must disclose a reportable event (material agreement, acquisition, personnel change, Reg FD disclosure) or file a current report within four business days. Trigger on "Form 8-K", "current report", "8-K filing", "EDGAR", "Item 1.01", "Item 2.01", "Item 5.02", "Reg FD".
34
Ivx Om Grok Media
xAI Grok image and video generation guide covering authentication, endpoints, prompt structure, image editing, reference-image video, and async polling.
0 · bundle
Agent Platform RAG Engine Management
Manage and query Agent Platform RAG Engine Corpora and retrieve grounded contexts using the Google GenAI SDK.
14.4k
Gstack Upgrade
Upgrade gstack to the latest version. Detects global vs vendored install, runs the upgrade, and shows what's new. Use when asked to "upgrade gstack", "update gstack", or "get latest version". Voice triggers (speech-to-text aliases): "upgrade the tools", "update the tools", "gee stack upgrade", "g stack upgrade".
0
Prd
Generates a structured Product Requirements Document for the MÄÄK dating app, with clarifying questions, right-sized user stories, and verifiable acceptance criteria.
54 · bundle
Okrs
Apply the OKRs framework to structure analysis, guide decision-making, and improve outcomes in product research and strategic planning contexts.
2
Pair Agent
Pair a remote AI agent with your browser. One command generates a setup key and prints instructions the other agent can follow to connect. Works with OpenClaw, Hermes, Codex, Cursor, or any agent that can make HTTP requests. The remote agent gets its own tab with scoped access (read+write by default, admin on request). Use when asked to "pair agent", "connect agent", "share browser", "remote browser", "let another agent use my browser", or "give browser access". (gstack) Voice triggers (speech-to-text aliases): "pair agent", "connect agent", "share my browser", "remote browser access".
0
Guard
Full safety mode: destructive command warnings + directory-scoped edits. (gstack)
2 · bundle
Grill With Docs
Runs a relentless interview that sharpens a plan or design and creates docs (ADRs and glossary) along the way. Use when the user wants to stress-test a plan or design, or produce decision records.
580 · bundle
Slack Gif Creator
Create animated GIFs optimized for Slack with validators for size constraints and composable animation primitives.
66.9k · bundle
Okr
Generate OKR cascades from company strategy to team objectives. Usage: /okr generate <strategy>
6
Guard
Full safety mode: destructive command warnings + directory-scoped edits. (gstack)
0 · bundle
Pk Standup
Generate today's standup: what was done, what is in progress, what comes
0
LLM Security
Conduct authorized security assessments of LLM applications and AI agents, covering prompt injection, tool abuse, RAG exposure, memory poisoning, and model supply-chain risks.
12.8k · bundle
Copy Hooks
Gera e testa ganchos de abertura para posts, e-mails, anúncios e vídeos usando uma biblioteca de 9 padrões nomeados, adaptados por canal e público.
2
God Marduk
Trigger: project task list, task decomposition, phase planning, master orchestration, delivery governance. Scope: Project sequencing, task checklist creation, operating governance. Boundary: Excludes tactical code debugging.
1 · bundle
QA
Systematically QA test a web application and fix bugs found. Runs QA testing, then iteratively fixes bugs in source code, committing each fix atomically and re-verifying. Use when asked to "qa", "QA", "test this site", "find bugs", "test and fix", or "fix what's broken". Proactively suggest when the user says a feature is ready for testing or asks "does this work?". Three tiers: Quick (critical/high only), Standard (+ medium), Exhaustive (+ cosmetic). Produces before/after health scores, fix evidence, and a ship-readiness summary. For report-only mode, use /qa-only. (gstack) Voice triggers (speech-to-text aliases): "quality check", "test the app", "run QA".
0
Standup
Facilitates a read-only standup across git worktrees, branches, or PRs to compare changes and produce one consolidation plan.
· bundle
Delivery Status Brief
Create a clear project status brief with progress, risks, blockers, decisions, and next actions.
0
Blockrun
Use when user needs capabilities Claude lacks (image generation, real-time X/Twitter data) or explicitly requests external models ("blockrun", "use grok", "use gpt", "dall-e", "deepseek")
0