「eval」の検索結果

Conduct expert heuristic evaluations using Nielsen's heuristics and domain-specific criteria.

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。

Audits any developer documentation site across 33 checks in 7 categories and produces a scored report (out of 100) with Pass / Warn / Fail status per check. Use this skill whenever a user provides a docs URL and asks to audit it, review it, score it, check its quality, or evaluate it for AI discoverability, SEO, structure, content, or completeness. Also trigger when the user says "run a docs audit", "audit these docs", "check this documentation", "how good are the docs for X", or pastes a docs URL with any evaluative intent. Always use this skill — do not attempt a freeform docs review without following this structured workflow.

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。

Applies the epidemiological and aging research frameworks of Tamara B. Harris (epidemiologist, National Institutes of Health). Use this skill whenever analyzing health metrics in older populations, designing longitudinal studies, evaluating body composition (muscle quality vs. mass), assessing dementia risk factors, or interpreting paradoxical risk factors in geriatrics. Trigger this skill when the user asks about aging, longevity, functional decline, socioeconomic health disparities, or when evaluating clinical trial data where reverse causation or subgroup stratification might skew results.

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。

This skill channels the reasoning of Walter C. Willett, nutrition epidemiologist at Harvard University. Use this skill whenever you are asked to evaluate diets, give nutritional advice, critique food policy, or discuss the environmental impact of food systems. Trigger this skill for topics like macronutrient quality (fats vs. carbs), plant-based diets, the health impacts of red meat or dairy, seed oils, epidemiological methodology, and planetary health. Apply his frameworks to shift focus from macronutrient quantity to quality, evaluate foods using the 'Compared to what?' rule, and prioritize public health over personalized nutrition fads.

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。

Applies the rigorous deontological ethics, transcendental idealism, and political philosophy of Immanuel Kant (18th-century German philosopher, Critique of Pure Reason). Reach for this skill whenever the user is facing moral dilemmas, questions of duty, truth-telling, evaluating the limits of human knowledge, balancing civic obedience with free speech, or designing systems for global governance and peace. Use this skill to evaluate actions based on universalizability and human dignity rather than consequences, even if the user doesn't explicitly name Kant.

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。

Applies the philosophical frameworks of Martha Nussbaum (American philosopher, capabilities approach, University of Chicago) to evaluate justice, human welfare, and ethical dilemmas. Use this skill whenever the user is discussing measuring societal well-being, educational curricula, animal rights, the role of emotions (like anger or disgust) in law and public life, or navigating human vulnerability and tragedy. Reach for this skill whenever evaluating policy impacts, responding to injustice, or questioning purely economic metrics like GDP. It shifts the focus to what people are actually able to do and be.

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 agent and skill behavior or routing.

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。

Suede AI blunt A-F ship grade for a code change across correctness, security and permissions, data and state, domain truth, UX and release behavior, tests and verification, and deploy readiness, with Instant-F triggers and evidence-based grade caps on auth, payment, migration, and public-API surfaces. Use when asked to grade this, give it a letter, is this an A, how ready is this to ship, or should this merge: when the caller wants the verdict without a findings list. NOT FOR: findings, evidence, and fix briefs (use suede-code-review, or suede-code for findings plus grade); enforcing the verdict in CI (use suede-ci-gate); eval coverage for AI behavior (use suede-ai-eval).

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。

Suede AI CI and branch-protection wiring for any repo and any stack: path-aware jobs, a single aggregator required check that cannot deadlock, lockfile hygiene, runtime pinning from the repo, and the exact branch-protection settings. Use when asked to set up CI, protect main, make CI block a bad merge, fix a required check that hangs pending forever, or repair duplicate or misfiring pipelines. Detects the repo's real apps, package managers, and runtime versions first; emits workflow files and settings, never pushes or flips protection itself. NOT FOR: reviewing or grading the change the gate is failing on (use suede-code); designing the AI eval cases to wire in (use suede-ai-eval); branch and worktree hygiene (a private Suede Labs companion, not in this pack).

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。

Suede-owned operations-architecture discipline that fixes the shape of a system before anyone builds it: entity schema first, exactly one write path per entity, every unit of work routed to a deterministic automation, an AI agent, or a human decision, every existing tool marked absorb, keep, or kill, and the build sequenced into phases whose completion is proved by a command. Use when scoping an automation or agent build, deciding whether a workflow needs a model at all, consolidating a sprawling tool stack, designing the data model under a workflow, choosing a migration path off an old system, or ordering a build so nothing lands on a moving foundation. NOT FOR: executing a planned multi-file repo change (use suede-graph-flo-xr); coordinating parallel builders with file ownership (use suede-agent-teams); lead lifecycle, scoring, and CRM routing rules (use suede-revops); proving agent output quality against an eval set (use suede-ai-eval); reviewing the finished diff (use suede-code-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。

Use when the user wants to work on a Claude Code skill file (SKILL.md): writing one from scratch, testing whether an existing one works well, running evals or benchmarks, improving its instructions, or fixing why it isn't triggering. Triggers on: 'make a skill for X', 'test this skill', 'run evals on my SKILL.md', 'touch-skill', sharing a SKILL.md and asking if it's ready to ship. The key signal is intent to create, validate, or improve a skill — not just mention one. Do NOT trigger for general Claude Code questions, hook debugging, or CLAUDE.md configuration.

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 GraphRAG retrieval pipelines on Neo4j using the neo4j-graphrag Python package (v1.22.0+). Covers retriever selection (VectorRetriever, HybridRetriever, VectorCypherRetriever, HybridCypherRetriever, Text2CypherRetriever, ToolsRetriever), external vector DB retrievers (Weaviate, Pinecone, Qdrant), retrieval_query Cypher fragments, query_params, filters, GraphRAG pipeline wiring (GraphRAG + LLM + prompt), all LLM providers (OpenAI, Anthropic, Gemini/VertexAI, Bedrock, Cohere, Mistral, Ollama), embedder setup, index creation, token usage tracking, Cypher 25 SEARCH clause, and LangChain/LlamaIndex integration. Does NOT handle KG construction — use neo4j-document-import-skill. Does NOT handle plain vector search — use neo4j-vector-index-skill. Does NOT handle GDS analytics — use neo4j-gds-skill. Does NOT handle agent memory — use neo4j-agent-memory-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。

Manages Neo4j Aura Agents via the v2beta1 REST API — create, list, get, update, delete, and invoke Aura agents backed by an AuraDB instance. Use when configuring Aura Agent tools (CypherTemplate, SimilaritySearch, Text2Cypher), setting system prompts, deploying agents to REST or MCP endpoints, invoking agents with natural language queries, or generating evaluation datasets (max 50 questions) for the Aura Agent evaluation feature. Covers OAuth2 auth, organization/project scoping, tool parameter schemas, and InvokeAgentResponse format. Does NOT cover AuraDB instance provisioning — use neo4j-aura-provisioning-skill. Does NOT cover vector index creation — use neo4j-vector-index-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。

Use when training, tuning, comparing or evaluating a model — choosing the cross-validation scheme, baselines, tuning inside CV, thresholds and calibration, per-slice metrics, feature importance and error 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。

Used to invoke the PXMeter tool for rigorous quality assessment of biomolecular structure prediction models (e.g., proteins, nucleic acids, small molecules). This skill covers single-sample CIF evaluations and large-scale dataset benchmarks, providing rich result parsing support. Trigger this skill when the user asks to "run PXMeter", "compare PDB/CIF evaluation results of different tools", "check benchmark scores", or asks "how accurate is the structure generated by the model".

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 technologies and competitive developments against Genesis architecture

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 content for personal relevance to the user using the user model

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 and runs reproducible evaluations for AI agents, prompts, tools, skills, and model-backed workflows using realistic datasets, isolated baselines, objective assertions, rubric grading, trajectory analysis, cost/latency tracking, and regression comparison. Use when measuring agent quality, optimizing skill triggering, comparing prompts or models, or gating an AI feature release. Not for ordinary deterministic unit tests.

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。

Builds local-first note vault retrieval for Obsidian, markdown notebooks, and NotebookLM-adjacent exports. Use when packaging notes into LLM-ready context.

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 LLM, agent, responsible-AI, and multimodal evals. Use when measuring quality, fairness, grounding, safety, or judge reliability. Not for test harnesses (qa-agent-testing).

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。

Batch query TikTok product detail data, including multi-period sales and GMV (1d/7d/15d/30d/60d/90d/cumulative), live sales and live GMV, promoting video and creator data, views, price, rating, review count, commission rate, and delisted/fully-managed status. Supports batch retrieval by product ID or TikTok Shop product URL. Trigger when users mention TikTok product detail, batch query TikTok products, TikTok product sales analysis, TikTok product GMV, TikTok live sales, TikTok influencer sales data, TikTok product price rating, batch get TikTok product info, Nexscope product detail, TikTok product detail, batch product lookup, TikTok sales analysis, TikTok GMV, TikTok live sales, TikTok influencer data. Even if the user does not explicitly mention "Nexscope", trigger this skill whenever their need involves batch retrieval of detailed TikTok product sales and marketing data by product ID or product URL.

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。

Query patent simple bibliographic (catalog) data from the Nexscope patent database. Triggered when users mention patent bibliographic information queries, patent basic info retrieval, patent catalog data, patent publication details, searching by patent number for inventors, patent applicant information, patent abstract retrieval, patent classification codes (IPC/CPC), patent citation queries, or any request to search for structured metadata by patent ID or publication number, patent brief bibliography, patent basic info, patent number lookup, patent abstract, Nexscope, or patent metadata. Even if the user does not explicitly mention "Nexscope" or "bibliographic info," this skill should be triggered whenever their need involves querying core bibliographic fields of specific patents.

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 Nexscope market list capability to filter Amazon niche markets by category dimensions, supporting market size, competition, top concentration, seller structure, new product share, price/rating/margin ranges, and many other criteria for discovering viable markets and evaluating product selection directions. Trigger when the user mentions Amazon market research, niche category research, market opportunity screening, market concentration analysis, new product opportunities, market selection, Nexscope market research, category market research. Even if the user does not explicitly mention "Nexscope", if the need is to screen and evaluate Amazon markets by category dimensions, this skill should also be triggered.

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 a lesson opening that activates prior knowledge and connects previous learning to today's content. Use when planning lesson starters, retrieval openers, or advance organisers.

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。