1,272 件 ・ 関連度順
概要と使いどころ
A meta-skill that understands task requirements, dynamically selects appropriate skills, tracks successful skill combinations using agent-memory-mcp, and prevents skill overuse for simple tasks.
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。
Testing and benchmarking LLM agents including behavioral testing, capability assessment, reliability metrics, and production monitoring—where even top agents achieve less than 50% on real-world benchmarks
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。
Remove refusal behaviors from open-weight LLMs using OBLITERATUS — mechanistic interpretability techniques (diff-in-means, SVD, whitened SVD, LEACE, SAE decomposition, etc.) to excise guardrails while preserving reasoning. 9 CLI methods, 28 analysis modules, 116 model presets across 5 compute tiers, tournament evaluation, and telemetry-driven recommendations. Use when a user wants to uncensor, abliterate, or remove refusal from an LLM.
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 when the user requests to review, analyze, critique, or summarize academic papers, research articles, preprints, or scientific publications. Supports comprehensive structured reviews covering methodology assessment, contribution evaluation, literature positioning, and constructive feedback generation. Trigger on queries involving paper URLs, uploaded PDFs, arXiv links, or requests like "review this paper", "analyze this research", "summarize this study", or "write a peer review".
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, test, and debug Hermes Agent RL environments for Atropos training. Covers the HermesAgentBaseEnv interface, reward functions, agent loop integration, evaluation with tools, wandb logging, and the three CLI modes (serve/process/evaluate). Use when creating, reviewing, or fixing RL environments in the hermes-agent 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。
Comprehensive ad account analysis across all major platforms (Google, Meta Comprehensive paid advertising audit and optimization for any business type. Performs full multi-platform audits (Google Ads, Meta Ads, LinkedIn Ads, TikTok Ads, Microsoft Ads), single-platform deep analysis, conversion tracking health checks, creative quality assessment, budget allocation optimization, bidding strategy evaluation, and compliance verification. Industry detection for SaaS, e-commerce, local service, B2B enterprise, info products, mobile app, real estate, healthcare, finance, and agency. Triggers on: "ads", "PPC", "paid advertising", "Google Ads", "Meta Ads", "Facebook Ads", "LinkedIn Ads", "TikTok Ads", "Microsoft Ads", "Bing Ads", "ad audit", "campaign audit", "ROAS", "conversion tracking", "creative fatigue", "bid strategy".
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。
Strategic advisor for Evvo Labs business decisions. Use when Vince asks for strategic advice, business opinions, market entry decisions, pricing strategy, product prioritization, resource allocation, partnership evaluation, competitive positioning, or any question about what Evvo should do next. Applies 5 frameworks: VRIO (competitive advantage), Value Stick (pricing/margin), Blue Ocean (market positioning), McKinsey Horizons (resource allocation), Strategy Diamond (initiative planning). Always read references/evvo-strategy.md before advising.
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。
Guardian Angel gives AI agents a moral conscience rooted in Thomistic virtue ethics. Rather than relying solely on rule lists, it cultivates stable virtuous dispositions— prudence, justice, fortitude, temperance—that guide every interaction. The foundation is caritas: willing the good of the person you serve. From this flow the cardinal virtues as practical habits of right action and sound judgment. v3.0 introduced virtue-based disposition as the primary evaluation layer, providing deeper coherence than checklists alone. The agent's character becomes the safeguard. v3.1 adds: Plugin enforcement layer with before_tool_call hooks, approval workflows for ambiguous cases, and protections for sensitive infrastructure 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。
Conduct exhaustive multi-source investigation with methodology tracking, source evaluation, and iterative depth.
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。
Structured, multi-dimensional company investment research framework for AI agents and human analysts. Provides a 10-part checklist (moat, tech, market, customers, growth, financials, geography, governance, valuation, recommendation) to turn scattered info into a consistent, high-quality investment memo. | 面向 AI Agent 与人工分析师的公司投研框架，用 10 大维度系统梳理商业模式、护城河、成长与估值，快速产出结构化投研报告。
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。
INVOKE THIS SKILL when optimizing, improving, or debugging LLM prompts using production trace data, evaluations, and annotations. Covers extracting prompts from spans, gathering performance signal, and running a data-driven optimization loop using the ax CLI.
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。
Patterns and techniques for evaluating and improving AI agent outputs. Use this skill when: - Implementing self-critique and reflection loops - Building evaluator-optimizer pipelines for quality-critical generation - Creating test-driven code refinement workflows - Designing rubric-based or LLM-as-judge evaluation systems - Adding iterative improvement to agent outputs (code, reports, analysis) - Measuring and improving agent response quality
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。
INVOKE THIS SKILL when creating, running, or analyzing Arize experiments. Covers experiment CRUD, exporting runs, comparing results, and evaluation workflows using the ax CLI.
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 accretion/dilution (merger) models in Excel — pro-forma P&L, synergies, financing mix, EPS impact. Pairs with excel-author. Use for M&A pitches, board materials, or deal evaluation.
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。
Generate AI design contract (AI-SPEC.md) for phases that involve building AI systems — framework selection, implementation guidance from official docs, and evaluation strategy
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。
Retroactively audit an executed AI phase's evaluation coverage — scores each eval dimension as COVERED/PARTIAL/MISSING and produces an actionable EVAL-REVIEW.md with remediation plan
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。
Designs retrieval-augmented generation pipelines for document-based AI assistants. Includes chunking strategies, metadata schemas, retrieval algorithms, reranking, and evaluation plans. Use when building "RAG systems", "document search", "semantic search", or "knowledge bases".
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。
Target discovery methodology for finding high-quality npm/PyPI/GitHub packages to audit for vulnerabilities, with evaluation criteria and search strategies.
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。
Decision tree analysis for complex decision-making across all domains. Use when user needs to evaluate multiple options with uncertain outcomes, assess risk/reward scenarios, or structure choices systematically. Applicable to business, investment, personal decisions, operations, career choices, product strategy, and any situation requiring structured evaluation. Triggers include decision tree, should I, what if, evaluate options, compare alternatives, risk analysis.
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。
Architectural decision-making framework. Requirements analysis, trade-off evaluation, ADR documentation. Use when making architecture decisions or analyzing system design.
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。
Complete inventory management, demand forecasting, supplier evaluation, and supply chain optimization for businesses of any size. From stockroom to strategy.
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。
Design dashboards for migrations and runtimes. Use for authority drift, verifier status, burn-down, runtime health, or pain panels. NOT for vanity analytics, ad hoc charts, or duplicate reporting.
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。
Facilitate idea generation sessions that actually produce diverse, useful options instead of degenerating into the first plausible answer. Use for product ideation, feature exploration, problem-reframing, naming, design alternatives, strategic option-generation, or any task where the failure mode is "we picked the obvious thing too fast." Covers solo and group sessions, divergence/convergence discipline, technique selection (SCAMPER, Crazy Eights, How Might We, 6-3-5 Brainwriting, Reverse Brainstorming, Worst Possible Idea, Random Stimulus), facilitation moves for handling dominant voices and groupthink, and structured convergence to a shortlist with rationale. Outputs a session artifact with options generated, evaluation, shortlist, and the rejected-but-interesting list.
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。
Architecture and systems design for agents that retain bounded state across sessions. Covers durable event history, owned state, derived memory, retrieval indexes, framework evaluation, recovery, deletion, and rebuild behavior. Uses constructed implementation examples and workload calibration rather than universal vendor, latency, similarity, retention, or cost claims. Activate on: "always-on agent", "persistent agent architecture", "episodic memory system", "agent memory design", "long-running agent", "stateful agent", "agent that remembers", "MemGPT architecture", "Letta deployment", "/always-on-agent-architecture". NOT for: choosing what data to feed the agent (use always-on-agent-inputs), brainstorming applications (use always-on-agent-applications), safety and privacy concerns (use always-on-agent-safety), general agentic patterns (use agentic-patterns).
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。