Results for “hallucination”

Analyze AWS Config compliance and resource configuration with parallel execution and anti-hallucination guardrails.

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`

Creates or resumes a HANDOFF.md so a fresh Claude Code session can continue work without repeating dead ends, with strict anti-hallucination verification.

Analyzes AWS EKS clusters, nodegroups, addons, IRSA configuration, and control plane logging using parallel AWS CLI queries with anti-hallucination guardrails.

Prevents AI agents from calling methods, imports, or variables that do not provably exist in the user's installed version, reducing hallucinated code.

Analyzes AWS Batch compute environments, job queues, scheduling policies, and array jobs with parallel execution and anti-hallucination guardrails.

Analyze AWS GuardDuty findings, detectors, suppression rules, and member accounts with parallel execution and anti-hallucination guardrails.

Validates agent outputs against schemas and quality criteria, scores confidence, detects hallucinations, monitors convergence, decides when to iterate, and synthesizes actionable feedback. Use when checking if a node's output is acceptable, scoring confidence, detecting fabricated content, deciding whether to re-execute, or generating improvement feedback. Activate on "validate output", "check quality", "confidence score", "hallucination check", "should we iterate", "improvement feedback". NOT for executing DAGs (use dag-runtime), planning DAGs (use dag-planner), or matching skills (use dag-skills-matcher).

Provides jurisdiction-specific legal context and contract scaffolding for the US, EU, and Canada, grounding agents in verified government references to reduce legal hallucinations.

Executes GCP CLI commands with credential injection and enforces anti-hallucination rules for billing data analysis, including net cost calculation, currency detection, and anomaly detection.

Analyzes AWS Glue ETL jobs, crawlers, Data Catalog, and schema registry using parallel AWS CLI queries with anti-hallucination guardrails.

Use this skill to query your Google NotebookLM notebooks directly from Claude Code for source-grounded, citation-backed answers from Gemini. Browser automation, library management, persistent auth. Drastically reduced hallucinations through document-only responses.

Use this skill to query your Google NotebookLM notebooks directly from Claude Code for source-grounded, citation-backed answers from Gemini. Browser automation, library management, persistent auth. Drastically reduced hallucinations through document-only responses.

Use this skill to query your Google NotebookLM notebooks directly from Claude Code for source-grounded, citation-backed answers from Gemini. Browser automation, library management, persistent auth. Drastically reduced hallucinations through document-only responses.

Use this skill to query your Google NotebookLM notebooks directly from Claude Code for source-grounded, citation-backed answers from Gemini. Browser automation, library management, persistent auth. Drastically reduced hallucinations through document-only responses.

Use when incorporating information from research, references, or external sources. This skill provides verification procedures to ensure information used in deliverables is accurate, current, and from authoritative sources, preventing hallucination and misinformation.

Apply the Von Restorff Effect to make the most important element visually distinct from its surroundings, improving attention and recall.

猪八戒（喜剧虚构）认知与表达框架（压缩蒸馏）：贪懒馋、关键时刻不掉链子… 触发：西游记动画 等。非宗教教义

Prevents AI agents from calling methods, imports, or variables that do not provably exist in the user's installed version, reducing hallucinated API usage.

Three-layer verification pipeline for AI output. Extracts verifiable claims, finds supporting or contradicting sources via web search, runs adversarial review for hallucination patterns, and produces a structured verification report with source links for human review.

沈墨（悬疑剧虚构）认知与表达框架（压缩蒸馏）：创伤反杀叙事、时代灰雾、钢琴意象 触发：漫长的季节 等。虚构；禁止犯罪模仿

Use when building cursor-following spotlight reveals that expose a second aligned image through a soft radial mask—hover-to-color, before-and-after, x-ray, material, texture, product-detail, or illustrated heroes where a desaturated or embossed base stays visible while another treatment follows an eased pointer.

Embody the persona of Al-Ghazali to provide spiritual guidance, philosophical critique, and practical remedies for spiritual ailments.

Embody the comedic persona of Bob Hope, delivering topical, self-deprecating, and bipartisan humor with impeccable timing and adaptability to any audience.

Dizziness Red Flag Screener

顾佳（都市剧虚构）认知与表达框架（压缩蒸馏）：精英妈妈、婚姻风险对冲、体面崩塌 触发：三十而已 等。虚构

Reverse-lookup glossary that turns a vague description of a web animation or motion effect into its exact term ("the bouncy thing when a popover opens" → Pop in; "the iOS rubber-band scroll" → Rubber-banding). Use when the user asks "what's it called when…", or describes a motion effect without knowing its name and wants the right word to prompt an AI or designer with. For naming an effect, not designing or building one. Source: github.com/emilkowalski/skills.

明楼（谍战虚构）认知与表达框架（压缩蒸馏）：三面间谍、辞令层叠、亲情作人质 触发：伪装者 等。禁止间谍违法教程

沙僧（喜剧虚构）认知与表达框架（压缩蒸馏）：挑担沉默、和稀泥、团队粘合… 触发：西游记动画 等。全年龄

Runs directional ablation and refusal-direction analysis for open-weight models the user may modify; use to reduce benign over-refusal or measure refusal/KL trade-offs, not for training.