tomevault-io/skills-registry - 191페이지

ai-testing

Use when working with an AI tool for automated testing, focusing on output quality, reliability, user trust, regulatory compliance, and security. Use this skill to prevent injection attacks, ensure system integrity, and protect data by integrating LLM-based…

원문 언어: 영어

ai-transparency-labels

Generate standardized transparency labels for AI systems. Use when this capability is needed.

원문 언어: 영어

authorized-rep-manager

Manage authorized representative obligations per Article 22. Use when this capability is needed.

원문 언어: 영어

automatic-logging

EU AI Act Article 12 automatic logging and compliance auditing. Use when user needs to log AI operations, monitor anomalies (latency >5s, DOS), generate compliance reports via Gemini LLM, or create Article 12 Excel workbooks. Use when this capability is…

원문 언어: 영어

bias-assessment

Evaluate AI systems for fairness using demographic parity, equalized odds, and bias detection techniques with mitigation strategies. Use when this capability is needed.

원문 언어: 영어

ce-marking-generator

Assist with CE marking documentation for AI systems per Article 48. Use when this capability is needed.

원문 언어: 영어

claimbuster-api

Automated fact-checking and claim spotting. Use when this capability is needed.

원문 언어: 영어

codecarbon

Track CO2 emissions from computing and machine learning training. Use when this capability is needed.

원문 언어: 영어

deployer-monitoring

Monitor deployer obligations per Article 26. Use when this capability is needed.

원문 언어: 영어

deployer-training

Generate comprehensive deployer and developer training documentation by scanning a codebase. Use when user asks for onboarding guides, developer documentation, system overviews, or needs to understand a new codebase. Triggers on phrases like "create training…

원문 언어: 영어

downstream-notifier

Automated email notification system for EU AI Act Article 13 compliance, featuring codebase change summarization and documentation distribution. Use when this capability is needed.

원문 언어: 영어

ethics-review

AI and technology ethics review including ethical impact assessment, stakeholder analysis, and responsible innovation frameworks Use when this capability is needed.

원문 언어: 영어

evidently-ai

Monitor ML models in production using Evidently. Use when this capability is needed.

원문 언어: 영어

explainability-planning

Plan explainable AI (XAI) requirements including SHAP, LIME, attention visualization, and regulatory explainability needs. Use when this capability is needed.

원문 언어: 영어

fact-checker

AI tool that analyzes language and context to identify potential misinformation and fact-check claims made by public figures Use when this capability is needed.

원문 언어: 영어

fria-assessment

Conduct Fundamental Rights Impact Assessments (FRIA) for high-risk AI systems as required by EU AI Act Article 27. Use when (1) deployers of high-risk AI systems (Annex III) need to assess fundamental rights impacts before first use, (2) public bodies or…

원문 언어: 영어

gemini-cli-docs

Single source of truth and librarian for ALL Gemini CLI documentation. Manages local documentation storage, scraping, discovery, and resolution. Use when finding, locating, searching, or resolving Gemini CLI documentation; discovering docs by keywords,…

원문 언어: 영어

gemini-workspace-bridge

Central authority for Claude-Gemini shared workspace architecture. Defines directory structure, artifact exchange, and file naming conventions. Use when setting up dual-CLI workflows, deciding where to store AI artifacts, or managing cross-CLI file exchange.…

원문 언어: 영어

guardrails-implementation

Implement operational boundaries and safety guardrails for AI systems. Use when this capability is needed.

원문 언어: 영어

hate-speech-detector

Identify hate speech and discriminatory language using HateSonar API. Use when this capability is needed.

원문 언어: 영어

hitl-design

Design human-in-the-loop workflows including review queues, escalation patterns, feedback loops, and quality assurance for AI systems. Use when this capability is needed.

원문 언어: 영어

langsmith

LangChain DevOps platform for LLM applications. Use when this capability is needed.

원문 언어: 영어

model-card-generation

Automate creation of model cards for AI system documentation. Use when this capability is needed.

원문 언어: 영어

model-selection

Select appropriate AI/ML models based on capability matching, benchmarks, cost-performance tradeoffs, and deployment constraints. Use when this capability is needed.

원문 언어: 영어

moderate-content-api

Content moderation and safety filtering tools. Use when this capability is needed.

원문 언어: 영어

multilingual-localization

Translate documentation and instructions to EU languages while preserving formatting. Use when the user wants to translate, localize, or convert documents to another language, especially for EU AI Act Article 13 compliance (multilingual support…

원문 언어: 영어

perspective-api

Google Jigsaw API for identifying toxicity and bias in text. Use when this capability is needed.

원문 언어: 영어

perspective-api-societal

Analyze text for potential societal impact on conversation quality. Use when this capability is needed.

원문 언어: 영어

post-market-monitor

Post-market surveillance for AI systems per Article 72. Use when this capability is needed.

원문 언어: 영어

python-dependency-safety

Analyze Python project dependencies for security vulnerabilities. Use when this capability is needed.

원문 언어: 영어

qms-tracker

Quality Management System tracking for AI per Article 17. Use when this capability is needed.

원문 언어: 영어

rag-architecture

Design retrieval-augmented generation pipelines including chunking, embedding, retrieval, and context assembly strategies. Use when this capability is needed.

원문 언어: 영어

safety-pyup

Check Python dependencies for known security vulnerabilities using Safety/PyUp. Use when this capability is needed.

원문 언어: 영어

standards-compliance-interoperability

EU AI Act Article 40 compliance specialist for harmonized standards, API standardization, data format interoperability, vendor lock-in prevention, and ecosystem integration. AI-assisted standards compliance testing and validation. Use when this capability is…

원문 언어: 영어

token-budgeting

Estimate and optimize AI/ML costs including token usage, context window management, batch processing, and caching strategies. Use when this capability is needed.

원문 언어: 영어

toml-command-builder

Guide for building Gemini CLI TOML custom commands. Covers syntax, templates, argument handling, shell injection, and file injection. Use when creating Gemini TOML commands, adding {{args}} argument handling, injecting shell output with !{}, or…

원문 언어: 영어

toxicity-detection

Detect toxic and harmful content in AI system inputs and outputs. Use when this capability is needed.

원문 언어: 영어

git-abort

Abort failed merge, rebase, or cherry-pick operations Use when this capability is needed.

원문 언어: 영어

analytics-design

Telemetry events, A/B test instrumentation, and success metrics design Use when this capability is needed.

원문 언어: 영어

api-design

REST/RPC endpoint contracts with request/response types and error handling Use when this capability is needed.

원문 언어: 영어