Каталог навыков агентов

EU AI Act (Regulation (EU) 2024/1689) compliance advisor — risk classification across all four tiers, all 9 prohibited p...

EU AI Act (Regulation (EU) 2024/1689) compliance advisor — risk classification across all four tiers, all 8 prohibited p...

Build a preliminary, evidence-based EU AI Act readiness assessment across AI-system inventory, territorial scope, operat...

EU AI Act (Regulation (EU) 2024/1689) operational compliance for compliance teams. Three Article-level decisions: (1) Wh...

Guides EU Code of Conduct adherence under GDPR Articles 40-41 including EDPB approval requirements, monitoring body accr...

面向 (EU) 2024/2847 号法规的欧盟网络弹性法案（CRA）专家顾问——对在欧盟销售的所有含数字元素产品（PDE）的强制性网络安全和漏洞处理要求。使用本技能进行差距分析、产品分类（默认 / 第一类 / 第二类）、合格评定路线选择、...

Expert EU Cyber Resilience Act (CRA) advisor for Regulation (EU) 2024/2847 — mandatory cybersecurity and vulnerability h...

Practitioner skill for advising on EU Regulation 2023/2854 (Data Act). Covers Chapters II-VII (IoT data access, mandator...

Für EU Electronic Communications Code Router: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Schnittstellenkarte m...

Scans EU funding databases (Horizon Europe, ERDF, Digital Europe,Innovation Fund) to identify grant opportunities matchi...

Access EU law. Search and retrieve Directives, Regulations, Treaties and CJEU case law from EUR-Lex.

Provide actionable guidance for software under EU MDR, focusing on classification (Rule 11), technical documentation exp...

Assess a named organisation's role in a Horizon Europe or LIFE proposal. Cover leadership, major contributions, partner...

Works out which EU regulations apply to a system, process, vendor, or organization (EU AI Act, NIS2, DORA, GDPR), classi...

Einordnung von Wirtschaftstätigkeiten nach der Taxonomie-VO (EU) 2020/852 – Taxonomiefähigkeit und Taxonomiekonformität...

Prüft die Voraussetzungen des Vorabentscheidungsersuchens nach Art. 267 AEUV: Vorlagebefugnis und -pflicht, CILFIT-Ausna...

Manage Eufy Security (HomeBase S380 + SoloCam S340/E340) from the `eufy` CLI—capture snapshots, forward alarms to the Tu...

Drafts enforceable End-User License Agreements for software licensors across desktop, mobile, SaaS, and cloud models. Co...

Euler EVK vaults, borrowing, liquidation, risk, EVC authorization, oracle pricing and periphery integration.

This skill should be used when the user asks about "oracle", "EulerRouter", "price feed", "Chainlink", "Uniswap TWAP", "...

This skill should be used when the user asks about "Perspective", "vault validation", "Lens", "Swapper", "SwapVerifier",...

Write a eulogy or obituary for someone you loved when you're grieving and the words won't come — a true, warm piece that...

Help someone write a eulogy — the hardest writing most people ever do, at the worst possible time. Use when someone must...

Expert skill for building high-performance EUR/CAD forex trading bots with IBKR integration, advanced strategies, news a...

Capture technical breakthroughs and transform them into actionable, reusable documentation. Use this skill when the user...

Trigger word — when the user types "eureka" after finishing a piece of work, review the just-completed changes and surfa...

Complete Eureka V6.1 Context Engineering suite with observability, structured output, and hybrid memory

Beihilfenrecht und Vergaberecht prüfen wenn staatliche Foerderung oder öffentlicher Auftrag in Frage steht. Art. 107 108...

Klagemoglichkeiten vor dem EuGH und EuG einordnen und Zulassigkeitsvoraussetzungen prüfen. Art. 263 265 268 340 AEUV Nic...

Einstiegspunkt für Europarechtsmandate: Rechtsgebiet bestimmen relevante Normen identifizieren Bearbeitungsroute festleg...

Verhandlung vor EU-Behoerde oder nationalem Gericht mit EU-Rechtsbezug simulieren und Argumentation testen. Art. 267 AEU...

Vorabentscheidungsersuchen nach Art. 267 AEUV vorbereiten oder Vorlagepflicht eines nationalen Gerichts prüfen. Art. 267...

Use when picking software for EU customers, GDPR-driven replacements, digital-sovereignty contexts, or when user asks fo...

Use this skill to search life-science literature through Europe PMC when you need publication metadata oriented toward b...

Europe PMC RESTful Web Service 多源文献聚合检索原子 skill。一次调用同时召回 PubMed + PMC + AGRICOLA + CABI + 预印本(bioRxiv / medRxiv / ChemRx...

Guide a veterinary team through a compassionate end-of-life conversation with a pet owner — quality-of-life assessment,...

Phase 1 of the Gaia evidence verification pipeline. Use this skill whenever you need to gather, consolidate, or refresh...

Skippable Phase 0 of the Gaia evidence verification pipeline. Use only on declared need for higher-quality Stage-2 evide...

Top-level orchestrator for the Gaia Skill Tree evidence verification pipeline. Run this when you want to do a full evide...

Broad, pre-curation evidence reconnaissance for a declared Gaia skill, intake batch, upstream repository, or proposed ge...

Compare an EV against a comparable gas car on total cost — upfront gap after incentives, energy vs fuel per year, mainte...

Use when working on EVADE game UI, creating screens, styling components, or making visual decisions. Apply for any React...

Evaluate and rank agent results by metric or LLM judge for an AgentHub session.

EvalKit is a conversational evaluation framework for AI agents that guides you through creating robust evaluations using...

Evaluate and rank agent results by metric or LLM judge for an AgentHub session. Use when the user runs /hub:eval or asks...

Generate a complete Langfuse evaluation pipeline: auto-detect app type, create datasets, LLM-as-judge evaluators, scorin...

Test harness for the Signal Prospecting Kit v4.1. Runs deterministic checks and rubric-based grading against all 6 skill...

Use this skill to run an honest session-process evaluation (Standard v1, aiat-llm-eval/1.0) — score the last completed o...

View and manage the evaluation harness — session metrics, baselines, trend analysis, and regression detection. The feedb...

Quality and performance evaluation with baseline comparison. Sub-modes: correctness, performance, quality, regression. O...

Rank finished AgentHub agents by metric or judge. Use when asked which agent won.

Evaluate LLM outputs systematically — benchmarks, automated metrics, human preference, and regression tracking

Evaluate everything the PA agent manages — tasks, skills, PA network health, billing, calendar connections, and memory q...

Capture task quality signals and log them to agent memory to build a feedback loop. Use at the end of each implemented t...

Evaluate a local skill with the terum-skills CLI — hygiene, trigger evals and execution cases against a baseline, billed...

Score a review agent (Rex/Hakim/Tariq) against a labeled PR corpus — ground-truth defect-set overlap, never a prose rubr...

Analyze evaluation baseline results, identify failure patterns, and generate actionable insights. Use after running eval...

Audit an existing evaluation workflow and produce severity-ranked findings with concrete next actions. Use when inheriti...

This skill should be used when the user mentions "llm eval", "evaluation", "promptfoo", "deepeval", "regression test", "...

Carefully evaluate and grade the Ramco ERP "Brain" chatbot's answers against the ground-truth question bank (BrainEvals-...

Use when designing or improving Lev eval packs, inline FlowMind evaluation policy, owner-local runtime scenarios, assura...

Internal /ace:run step — Method reference for calibrating -eval rubrics against ground truth.

Use to generate high-signal evaluation cases for PonyBunny changes, including success paths, failure modes, edge cases,...

Write deterministic, code-based evaluator functions for an AI product. Use this skill whenever you need to write evaluat...

Compares the eval scores of two plugin folders, such as a plugin and a variant of it. Use when the user wants to know wh...

Configure content eval settings. Use when: adjusting score thresholds, dimension weights, or auto-reject rules.

Evaluate content quality. Use when: scoring drafts, checking hallucinations, or assessing brand voice compliance.

[Beta] Creates permanent eval cases from promoted learnings and runs regression checks against them. Turns failures into...

[Beta] CI-only eval regression runner using gh-aw (GitHub Agentic Workflows). Runs all eval cases in .evals/ on a schedu...

Use when the user needs to design evaluation datasets, create test cases, stratify samples, generate adversarial example...

Audit whether a paper's EVALUATION DESIGN actually measures what it claims and whether its reporting is complete — the v...

Use this skill when building evaluation frameworks to measure LLM quality, safety, accuracy, or alignment including test...

Manage eval-driven development workflow

Manage eval-driven development workflow

Set up eval-based QA for Python LLM applications: instrument the app, build golden datasets, write and run eval tests, a...

Instrument Python LLM apps, build golden datasets, write eval-based tests, run them, and root-cause failures — covering...

Use to design the evals for a build before you build it, right after the Goal and Constraint Brief, and again to run the...

Use this to build or change an LLM feature the reliable way, by writing evals first and iterating against them, instead...

A safe calculator for mathematical expressions

Turn a validated wedge into the scope you can SCORE — a one-sentence job, 20 pass/fail golden cases drawn from real arte...

Framework for capturing, storing, and comparing AI evaluations to measure consistency and completeness.Use when: compari...

Traditional software metrics (accuracy, F1) fail to capture the quality of LLM outputs. Evaluation frameworks like Ragas...

Find AILANG vs Python eval gaps and improve prompts/language. Use when user says 'find eval gaps', 'analyze benchmark fa...

Turn observed run outputs into eval-spec Artifacts, paired Gates, and policy bindings. Use when creating or calibrating...

Entry point for eval work. Use when someone asks for help with evals in general, does not know where to start, asks "wha...

Formal evaluation framework for Antigravity Code sessions implementing eval-driven development (EDD) principles. Enforce...

Professional Eval Harness Expert skill. Integrate LLM API workflows, safe system prompt guidelines, and agentic workflow...

克劳德代码会话的正式评估框架，实施评估驱动开发（EDD）原则

Formal evaluation framework for LLM features implementing Evaluation-Driven Development (EDD) principles.

克劳德代码会话的正式评估框架，实施评估驱动开发（EDD）原则

Frozen evaluation harness that gates self-improvement with benchmarks, regressions, and human approval loops.

Use this skill when building, running, or reasoning about the project's evals — the layer that proves the benchmark *beh...

Claude Codeセッションの正式な評価フレームワークで、評価駆動開発（EDD）の原則を実装します

Formal evaluation framework for Claude Code sessions implementing eval-driven development (EDD) principles

Eval-driven development (EDD) framework for AI coding sessions — define capability and regression evals before coding, g...

Formal evaluation framework for OpenAI Codex sessions implementing eval-driven development (EDD) principles