Results for “charavault”

Trains, evaluates, exports, and runs inference for Visual ChangeNet models used in AOI defect detection, comparing image pairs for PASS/NO_PASS classification or change-segmentation masks.

Enables visual instruction tuning and image-based conversations using open-source vision-language models. Supports multi-turn image chat, visual question answering, and image understanding tasks.

Hunt for threats in Windows Event Logs using Chainsaw, a fast Rust-based forensic tool that runs Sigma rules, keyword searches, and artifact analysis offline.

Build and operate a Havoc C2 framework for authorized red-team engagements, including team server deployment, evasive Demon agent generation, and post-exploitation.

Secure-by-default environment variable management for Claude Code sessions.

Manages environment variables and secrets in Claude Code sessions without exposing values, using Varlock for validation, masking, and secure command execution.

Runs the open-source LLaVA vision-language model for image understanding, captioning, visual question answering, and multi-turn image conversations, including setup, inference, and training guidance.

Solve a user-specified web task code-as-action style by driving a local Playwright browser through one bash command at a time, saving screenshots and an action log into `final_runs/run_id/`, and visually verifying the result. Use when the user asks to automate a web task (search, filter, form-fill, multi-step flow, data extraction) and wants reusable scripts plus screenshot evidence rather than a one-shot answer.

Requires node, and AISA_API_KEY. Uses the supplied AISA_API_KEY to send requests to https://api.aisa.one. Native-first ClawHub plugin for `aisa-tavily`. Ships the packaged AIsa skill with an `openclaw.plugin.json` manifest and a Claude-compatible bundle fallback. Search the web and extract public page content through AIsa's Tavily-backed API relay. Use when: the user needs open-web research, source discovery, current news lookup, or public URL content extraction. Supports concise result sets, deeper research, and news-focused queries.

Use when the agent needs to drive a browser through the Microsoft Playwright CLI (`playwright-cli`) for navigation, form interactions, screenshots, recordings, data extraction, session management, or debugging without loading a full MCP browser. It trains the agent on the CLI commands, snapshots, and session/config habits that make Playwright CLI reliable for scripted browsing.

Secure-by-default environment variable management for Claude Code sessions.

Secure-by-default environment variable management for Claude Code sessions.

Secure and powerful Playwright browser automation for testing websites, checking deploys, taking screenshots, filling forms, validating login flows, responsive QA, deploy QA, accessibility smoke checks, and browser-based verification. Use when Nick asks to test a page, verify a deployment, automate browser interactions, capture screenshots, inspect console errors, check mobile/desktop rendering, or run real Chromium-based browser checks.

Deploy and operate CAPEv2 sandbox for automated malware analysis with behavioral monitoring, payload extraction, configuration parsing, and anti-evasion capabilities.

Manage environment variables securely by validating schemas, masking sensitive values, and preventing secret exposure in logs or agent context.

Requires python3, and AISA_API_KEY. Uses the supplied AISA_API_KEY to send requests to https://api.aisa.one. Native-first ClawHub plugin for `tavily-extract`. Ships the packaged AIsa skill with an `openclaw.plugin.json` manifest and a Claude-compatible bundle fallback. Extract clean, readable content from one or more URLs using Tavily Extract via AIsa API. Useful for reading full articles without visiting the page. Use when: the user needs web search, research, source discovery, or content extraction.

Prevent Kubernetes hallucinations by diagnosing and fixing failure modes: insecure workload defaults, resource starvation, network exposure, privilege sprawl, fragile rollouts, and API drift. Use when generating, reviewing, refactoring, or migrating manifests, Helm charts, Kustomize overlays, cluster policies, and platform-specific Kubernetes work for EKS, GKE, AKS, OpenShift, GitOps controllers, or observability stacks.

Benchmarks large audio-language models against adversarial audio attacks using the CAA dataset, computing WER, ROUGE-L, cosine similarity, and coherence scores to assess robustness in conversational settings.

VS-Enhanced Theoretical Framework Architect with Critique & Visualization Full VS 5-Phase process: Modal theory avoidance, Long-tail exploration, differentiated framework presentation Absorbed A3 (Devil's Advocate) critique and A6 (Conceptual Framework Visualizer) capabilities Use when: building theoretical foundations, designing conceptual models, deriving hypotheses, critiquing frameworks, visualizing models Triggers: theoretical framework, 이론적 프레임워크, conceptual model, 개념적 모형, hypothesis derivation, critique, devil's advocate, 반론, visualization, diagram

旗木卡卡西（少年漫）认知与表达框架（压缩蒸馏）：迟到的老师、写轮眼悬念、慵懒靠谱 触发：火影忍者 等。虚构；非暴力教唆

Audits and iteratively fixes chat-based AI user interfaces against production best practices drawn from Claude, ChatGPT, and modern conversational AI, covering layout, rendering, input, responsiveness, scrolling, streaming, and accessibility.

Large Language and Vision Assistant. Enables visual instruction tuning and image-based conversations. Combines CLIP vision encoder with Vicuna/LLaMA language models. Supports multi-turn image chat, visual question answering, and instruction following. Use for vision-language chatbots or image understanding tasks. Best for conversational image analysis.

Large Language and Vision Assistant. Enables visual instruction tuning and image-based conversations. Combines CLIP vision encoder with Vicuna/LLaMA language models. Supports multi-turn image chat, visual question answering, and instruction following. Use for vision-language chatbots or image understanding tasks. Best for conversational image analysis.

Refreshes the local OWASP Cheat Sheet Series cache for the current project's language, checking GitHub for updates and fetching changed sheets.

Routes short slash commands to Claude Code relay sessions, including starting, stopping, and tailing sessions, and forwarding messages in relay mode.

Operates Laravel applications in production, covering Horizon, queues, scheduler, Octane, Redis, Supervisor, PHP-FPM, cache, and deployment with safety gates for destructive commands.

Drafts Right of First Refusal and Co-Sale Agreements for venture-backed and closely-held companies. Establishes ROFR mechanics, tag-along/co-sale rights, transfer restrictions, and permitted transfer carve-outs aligned with NVCA standards. Use when drafting ROFR agreements, co-sale agreements, tag-along rights, share transfer restrictions, or investor protective provisions in venture capital, private equity, or startup financing transactions.

Requires python3, and AISA_API_KEY. Uses the supplied AISA_API_KEY to send requests to https://api.aisa.one. Native-first ClawHub plugin for `openclaw-search`. Ships the packaged AIsa skill with an `openclaw.plugin.json` manifest and a Claude-compatible bundle fallback. Intelligent search for agents. Multi-source retrieval with confidence scoring - web, academic, and Tavily in one unified API. Use when: the user needs web search, research, source discovery, or content extraction.

Analyse experiment results, run validity checks (SRM, exposure parity, data integrity, novelty/primacy), interpret causally, make a ship/iterate/kill decision against the pre-declared rule, and append to cumulative learnings. Forces honest readouts — strips significance claims from underpowered or peek-violating tests; never lets directional results masquerade as causal wins. Load when results exist, or when the user says "read out this experiment", "analyse the test", "did the test win", "interpret the results", "what did we learn", "ship or kill", or when the experimentation orchestrator routes here.

Manages environment variables securely by validating against a schema, masking sensitive values, and injecting validated secrets into commands without exposing them.

Secure-by-default environment variable management for Claude Code sessions.

Covers MariaDB-specific behavior of the Connector/C++ sql:: API, including driver and connection setup, 1-based indexes, placeholder syntax, ResultSet iteration, raw pointer ownership, SQLString, autocommit, and exception handling.

Manages SurrealDB schemas as desired-state .surql files, with sync for disposable databases and reviewed rollouts for shared or production environments, plus seeding and declarative testing.

Use when calculating thermodynamics of RNA-RNA interactions, including accessibility and binding energy predictions for RNA duplex formation.

Provides a concise overview of CVS Health's history, business model, competitive moat, and key metrics.