Results for “inspect-ai”

Prevents AI-introduced regressions with sandbox-mode API testing, automated bug-check workflows, and patterns that catch blind spots where the same model writes and reviews code.

Enhances plain-language requests into structured, reviewable prompts and inspects a self-hosted MCP gateway with provider-free defaults.

Runs independent AI CLI reviewers over phase plans and merges their feedback into a REVIEWS.md file.

Use when building, fixing, polishing, or comparing any terminal UI — ratatui/crossterm REPLs, agent CLI chrome — or when a TUI shows a frozen spinner, dead keys, duplicated responses, stale cells, flicker, resume failures on dangling tool_use, or when you need side-by-side screenshots against reference CLIs.

Analyze images using Azure AI Vision SDK for Java, enabling captioning, OCR, object detection, tagging, and smart cropping.

Analyze images using Azure AI Vision SDK: generate captions, tags, detect objects, extract text (OCR), detect people, and suggest smart crops.

Pre-install security scanner for AI agent skills. 7.5% of 14,706 skills are malicious. Audit before you trust.

Scan and audit AI agent skills for security risks before installation, producing a PASS/WARN/FAIL verdict with findings and remediation guidance.

Security audit and vulnerability scanner for AI agent skills before installation. Use when: (1) evaluating a skill from an untrusted source, (2) auditing a skill directory or git repo URL for malicious code, (3) pre-install security gate for Claude Code plugins, OpenClaw skills, or Codex skills, (4) scanning Python scripts for dangerous patterns like os.system, eval, subprocess, network exfiltration, (5) detecting prompt injection in SKILL.md files, (6) checking dependency supply chain risks, (7) verifying file system access stays within skill boundaries. Triggers: "audit this skill", "is this skill safe", "scan skill for security", "check skill before install", "skill security check", "skill vulnerability scan".

Run a PDCA quality audit on LLM/AI features: traces, prompts, costs, evals, grounding, hallucination. Use for "audit LLM quality", "check Langfuse", "audit prompts", "check AI quality", "audit AI costs", "check traces". Jailbreak/OWASP LLM → audit-llm-security. Token caps → plan-llm-cost-guardrails.

Use this skill for search indexing, embeddings, RAG chunking, freshness, retrieval evaluation, source citations. Trigger when the task involves ai engineering work related to Search Indexing RAG, implementation, audits, debugging, strategy, or validation.

Inspect and adjust the agent's runtime state, including model, context window, iteration limits, token usage, workspace configuration, subagent status, and request routing metadata.

Inspect screenshots, photos, diagrams, image paths, and image URLs when the task depends on visible content. Use when the prompt lacks actual image content, native inspection fails, or the user requests inspect_image; prefer the MCP tool, then the installed CLI.

Professional code review with auto CHANGELOG generation, integrated with Codex AI

Automate Replicate AI model operations: run predictions, upload files, inspect model schemas, list versions, and manage prediction history via the Composio MCP integration.

Use Heroku Managed Inference and Agents with the current Heroku AI workflow. Use when the agent needs to install or inspect the Heroku AI CLI plugin, provision Heroku inference access on the current standard plan, review the latest Managed Inference model catalog, attach model resources, make test inference calls, or review Heroku-managed AI model operations.

CUDA kernel development, debugging, and performance optimization for Claude Code. Use when writing, debugging, or optimizing CUDA code, GPU kernels, or parallel algorithms. Covers non-interactive profiling with nsys/ncu, debugging with cuda-gdb/compute-sanitizer, binary inspection with cuobjdump, and performance analysis workflows. Triggers on CUDA, GPU programming, kernel optimization, nsys, ncu, cuda-gdb, compute-sanitizer, PTX, GPU profiling, parallel performance.