Results for “ai-blind-spots”

OpenAI API skill. Use when working with OpenAI for assistants, audio, batches. Covers 148 endpoints.

Audit a codebase, UI, or copy for machine-generated tells across prose, visual/UI, code, and structure/IA, then produce a phased de-slop burndown. Use when the user says "feels AI-generated", "looks like AI slop", "reads like ChatGPT", "feels generic/soulless", or wants an authenticity/voice pass before launch.

Build a comprehensive catalog of API endpoints including documented, undocumented, shadow, zombie, and deprecated APIs using passive traffic analysis, active scanning, DNS enumeration, JavaScript analysis, and cloud resource inventory.

Discover and inventory undocumented API endpoints by comparing live traffic against OpenAPI specs, scanning code repositories, and analyzing cloud configurations.

Executes Binance Spot API requests, including authenticated order management, with support for testnet and mainnet.

Design metacognitive checkpoints that prevent AI-assisted learning from bypassing genuine understanding. Use when students use AI tools and may overestimate their own comprehension.

Segment any object in images using points, boxes, or masks as prompts, or automatically generate all object masks with zero-shot transfer.

Debug and optimize AI agents by analyzing reasoning traces, context degradation, tool confusion, instruction drift, repeated task failures, and performance regressions.

AI 原生的潜在客户情报和外联流水线。用 agent 驱动的信号评分、共同关系人排名、暖场路径发现、来源语音建模和多渠道外联（邮件、LinkedIn、X），替代 Apollo、Clay 和 ZoomInfo。在用户想找到、评估并联系高价值联系人时使用。

Discover and install complementary skills from the inference.sh registry to expand AI agent capabilities.

Audits codebases, pages, or documents for AI-generated design and copy tells, then proposes surgical fixes for user approval.

NBA Stats API skill. Use when working with NBA Stats for playerdashptshots, leagueleaders, playerdashptreb. Covers 91 endpoints.

Registers an AI agent on inbed.ai as a blob-flexible dating profile, discovers matches, swipes, chats, and manages relationships via the platform's REST API.

Autonomous AI agent platform for building and deploying continuous agents. Use when creating visual workflow agents, deploying persistent autonomous agents, or building complex multi-step AI automation systems.

Autonomous AI agent platform for building and deploying continuous agents. Use when creating visual workflow agents, deploying persistent autonomous agents, or building complex multi-step AI automation systems.

Adds observability and debugging for AI-assisted application workflows using Sentry.

Runs a bounded spec-build-review development loop with explicit scope, stop conditions, and human approval gates for risky or ambiguous work.

Build comprehensive AI-native brand asset systems that maintain consistency across all AI-generated content. Train AI tools on brand guidelines, create reusable prompt libraries, and manage visual/voice assets at scale. Use when ", " mentioned.

Mistral AI API skill. Use when working with Mistral AI for models, conversations, agents. Covers 71 endpoints.

AI-native lead intelligence and outreach pipeline. Replaces Apollo, Clay, and ZoomInfo with agent-powered signal scoring, mutual ranking, warm path discovery, source-derived voice modeling, and channel-specific outreach across email, LinkedIn, and X. Use when the user wants to find, qualify, and reach high-value contacts.

Deepgram API Specification API skill. Use when working with Deepgram API Specification for agent, auth, listen. Covers 39 endpoints.

AI Safety Specialist IA — Expert en sécurité IA (alignment, guardrails, filtrage de contenu, test de biais, red teaming)

Systematically extract hidden system prompts, core directives, and invisible context intentionally concealed within Large Language Model (LLM) applications. This skill utilizes targeted linguistic engineering and boundary manipulation to bypass prompt opacity.

Banking interface for AI bots and automation.

Diagnose and mitigate context degradation patterns including lost-in-middle failures, context poisoning, distraction, confusion, and clash in AI agent systems.

Analyze text and images for harmful content using Azure AI Content Safety SDK for Java. Supports hate, violence, sexual content, and self-harm detection with blocklist management.

Analyzes prompts for safety, bias, security vulnerabilities, and effectiveness, providing detailed improvement recommendations with frameworks, testing methodologies, and educational content.

Automates the full DEFT AOI improvement loop for NVIDIA TAO VisualChangeNet / ChangeNet PCB inspection models, including baseline evaluation, RCA, synthetic defect generation, data mining, retraining, and deployment gating until KPI targets are met.

Implements a continual learning loop for AI coding agents using hooks, two-tier memory (global and local), and automatic pattern detection to persist and apply learnings across sessions.

Manage Arize AI integrations that store LLM provider credentials for evaluators and other features. Supports creating, reading, updating, and deleting integrations with providers like OpenAI, Anthropic, Azure OpenAI, AWS Bedrock, Vertex AI, Gemini, and NVIDIA NIM.

seven API skill. Use when working with seven for analytics, balance, contacts. Covers 51 endpoints.

Turns product ideas into structured specs for AI tools or stakeholder review, with quick feature specs and full project scopes.

Design privacy-aware observability for AI agents using traces, spans, structured events, metrics, cost attribution, dashboards, alerts, and investigation workflows. Use when instrumenting an agent, debugging intermittent tool or model failures, defining service-level objectives, analyzing latency or spend, auditing agent decisions, or preparing production monitoring.

Clean AI-generated code slop with a regression-safe, deletion-first workflow and optional reviewer-only mode

Botify API skill. Use when working with Botify for analyses, projects. Covers 26 endpoints.