4,137 件 ・ 関連度順
概要と使いどころ
Evaluate LLM agents and tool-using workflows—task success, tool accuracy, latency/cost, safety, and regression suites. Use when shipping agent features, comparing prompts/models, or debugging agent failures.
日本語の概要は準備中です。原文の説明を表示しています。
Auto-activates during requirements analysis to evaluate technical stack compatibility, recommend appropriate technologies, and assess performance implications.
日本語の概要は準備中です。原文の説明を表示しています。
Evaluate and tier suppliers using a weighted scorecard per SCOR DS Supplier Management practices. Score Quality, Delivery, Cost, Responsiveness, and Sustainability. Classify suppliers as Strategic, Preferred, Approved, or Conditional. Use during vendor reviews or procurement decisions.
日本語の概要は準備中です。原文の説明を表示しています。
Assess organizational training needs using ADDIE methodology and Kirkpatrick's 4-Level evaluation framework. Maps performance gaps to learning objectives using Bloom's taxonomy. Use when planning L&D budgets, designing training programs, or evaluating training effectiveness.
日本語の概要は準備中です。原文の説明を表示しています。
Build structured vendor/tool evaluation matrices with weighted scoring, TCO analysis, and recommendation memos. Covers criteria definition, deal-breaker identification, and negotiation points. Use when selecting SaaS tools, evaluating technology vendors, or making build-vs-buy decisions.
日本語の概要は準備中です。原文の説明を表示しています。
AI and LLM red-teaming skill for evaluating prompt injection, jailbreak, data exfiltration, tool abuse, agent hijack, RAG poisoning, model denial of service, and unsafe tool-use chains in Gemini, Claude, GPT, and open-weight models. Use to build evaluation harnesses, attack corpora, defensive guardrails, and red-team reports for AI systems you own or are authorized to test.
日本語の概要は準備中です。原文の説明を表示しています。
Test Retrieval-Augmented Generation (RAG) systems for data poisoning, prompt injection via retrieved documents, and data exfiltration through manipulated context windows. Use this skill when assessing RAG-based chatbots, knowledge bases, enterprise AI assistants, or any system that augments LLM responses with external document retrieval. Covers document injection, embedding manipulation, knowledge base poisoning, and cross-document inference attacks.
日本語の概要は準備中です。原文の説明を表示しています。
Triage the Gaia issue backlog and skill-batch intake queue. Use this skill when someone asks to: "triage issues", "clean up the issue tracker", "review the backlog", "close stale issues", "process the intake queue", "review skill-batches", "evaluate draft skill proposals", "approve or reject pending skills", "is this issue still valid?", "what's clogging the backlog?", "run a triage pass", or /gaia-triage. Covers two workstreams: (1) GitHub issue lifecycle — identifying resolved, stale, or need-more-info issues and acting on them via gh CLI; (2) skill-batch intake — evaluating draft proposals in registry-for-review/skill-batches/ and routing them toward promotion or rejection. This is the gatekeeping step before new skills enter the canonical registry; and (3) a cross-repo triage sweep — sizing, P0-P4 prioritization, umbrella/epic synthesis, and assignment across every gaia-research org repo, on the one headquarters tracker.
日本語の概要は準備中です。原文の説明を表示しています。
Split documents for retrieval effectively — fixed, semantic, structural, and hierarchical chunking with overlap tuning. Use when RAG retrieval quality depends on how documents are divided.
日本語の概要は準備中です。原文の説明を表示しています。
Evaluate AI agents rigorously — task benchmarks, success criteria, failure taxonomy, cost/latency tracking, and regression testing. Use when you need to know whether an agent actually works, not whether it demos well.
日本語の概要は準備中です。原文の説明を表示しています。
Audit whether all score-deciding logic in sgl-eval is vendored from NeMo-Skills, or whether some has crept into SE code. Use when the user asks "are we vendoring enough", "review vendor coverage", "audit vendoring", "is our vendoring complete", or before a release.
日本語の概要は準備中です。原文の説明を表示しています。
Upgrade the vendored NeMo-Skills slice to a newer upstream commit. Use when the user asks to "bump vendored", "sync NeMo-Skills", "update vendored sha", "upgrade NS", or wants to pull a specific upstream fix. Inside the sgl-eval repo.
日本語の概要は準備中です。原文の説明を表示しています。
Set up LLM-as-judge evaluation for ORC workflows
日本語の概要は準備中です。原文の説明を表示しています。
Assess the scientific integrity and trustworthiness of publications before relying on their findings. Use this skill whenever evaluating a paper for a workflow, citing a study, building an analysis on published methods, or when a user asks about the reliability of a study. Checks for formal retractions, corrections, expressions of concern, and — critically — informal contradictions where subsequent studies failed to reproduce key findings. Integrates with PubMed, bioRxiv, and Consensus to provide a trust assessment. Use this skill for ANY publication evaluation, retraction checking, author reliability assessment, or when a user says "can I trust this paper", "is this study reliable", "has this been refuted", or "check this publication".
日本語の概要は準備中です。原文の説明を表示しています。
Analyze catastrophe modeling systems for natural disaster exposure, PML estimation, and reinsurance optimization. Use when: 'assess cat model', 'evaluate disaster exposure', 'review PML calculations', 'audit reinsurance program', 'check exposure data quality', 'analyze hurricane/earthquake risk models', 'evaluate Oasis or RMS setup'.
日本語の概要は準備中です。原文の説明を表示しています。
Build a weighted decision matrix to evaluate options. Use when the user says "decision matrix", "compare options", "weighted scoring", "which option should we choose", "evaluate alternatives", "Wiegers priority matrix", "force field analysis", "decision table", "trade-off analysis", "option comparison" - even if they don't explicitly say "decision matrix".
日本語の概要は準備中です。原文の説明を表示しています。
Author, validate, test, and deploy YARA-L 2.0 detection rules and evaluate end-to-end detection coverage gaps in Google SecOps. Use when writing new detection rules, tuning existing rules, validating syntax, testing logic against historical telemetry, or evaluating detection coverage against threat intelligence blogs, CVE disclosures, and Threat Detection Opportunities (TDOs) using synthetic UDM events and long-running coverage analysis. Don't use for alert triage (use secops-triage), deep forensic event reconstruction on infected hosts (use secops-investigate), or case management operations (use secops-cases).
日本語の概要は準備中です。原文の説明を表示しています。
Use this skill to manage Google Cloud Workload Manager evaluations, rules, scanned resources, and validation results by using public client libraries and the REST API. Use when you need to inspect workload best-practice rules, create and run evaluations for Google Cloud general best practices, SAP, SQL Server, or custom organizational rules, review violations, export results to BigQuery, or automate Workload Manager through client libraries because no service-specific public CLI or MCP server is available. Don't use for general Google Compute Engine instance management, VPC configuration, or standard IAM auditing.
日本語の概要は準備中です。原文の説明を表示しています。
Automates the end-to-end detection engineering workflow in Google SecOps using MCP tools. Use when fetching threat intelligence from blogs, generating Threat Detection Opportunities (TDOs), simulating attacker behavior with synthetic UDM events, evaluating rule coverage, generating new YARA-L 2.0 rules to close coverage gaps, and with user approval, deploy them to SecOps. Don't use when asked to perform threat hunting actions, and SOC investigative actions.
日本語の概要は準備中です。原文の説明を表示しています。
Deploy open models or custom weights from Model Garden to Agent Platform endpoints, check the status of an in-progress deployment operation, or clean up resources by undeploying models and deleting endpoints. Use when asked to actively deploy a model, list the Model Garden CATALOG of available models, check if a specific model is deployable (`gcloud ai model-garden models list-deployment-config`), query deployment cost, troubleshoot deployment errors (like quota limits), or undeploy/clean up endpoints. Also use when copying and deploying a 1P Tuned Model. Don't use for pure listing/discovery questions of the form "is X deployed?", "list my endpoints", or "which regions have models running?" — for those use `agent-platform-endpoint-management`. Don't use for public Vertex AI deployments (use the `vertex-deploy` skill) or for running model evaluations (use the `agent-platform-eval-flywheel` skill).
日本語の概要は準備中です。原文の説明を表示しています。
Turn Caveman's exact report-only repository observations into an operator-chosen optimization candidate with a paired baseline/candidate evaluation. Use when the user asks to inspect an optimization observation, evaluate a candidate change, or act on the current Caveman optimization report. Require a logged-in Caveman CLI connection and explicit approval; never infer money or actuation from a profile.
日本語の概要は準備中です。原文の説明を表示しています。
Router for the 53 SfSkills `agentforce` skill packages. Agentforce and Einstein: agents, topics, actions, prompt templates, grounding, guardrails, evaluation and production readiness. Use when the request mentions Agentforce, agent topic, agent action, prompt builder, Einstein, Trust Layer, grounding, RAG, guardrails, agent evaluation, prompt injection. Finds and opens the exact skill package to read; it does not contain the guidance itself.
日本語の概要は準備中です。原文の説明を表示しています。
Scholar of medieval philosophy covering Aquinas, Scotus, Ockham, and the synthesis of Aristotelian philosophy with Christian theology
日本語の概要は準備中です。原文の説明を表示しています。
Semantic vector search with moflo — RAG over your own documents, similarity matching, context-aware retrieval via HNSW (node:sqlite-backed). Use when building retrieval layers for chat, search, or context-assembly.
日本語の概要は準備中です。原文の説明を表示しています。