「eval」の検索結果

AI context assessment — evaluating problem malleability, mapping structural rigidity versus flexibility, analyzing transformation pressure, and estimating capacity to adapt. Use when a complex task feels stuck and it is unclear whether to push through or pivot, before a significant approach change to assess whether the current reasoning structure can support it, when accumulated workarounds suggest the underlying approach may be wrong, or as a periodic structural health check during extended multi-step 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。

Comprehensive primary skill for agents working with Weights & Biases. Covers both the W&B SDK (training runs, metrics, artifacts, sweeps) and the Weave SDK (GenAI traces, evaluations, scorers). Includes helper libraries, gotcha tables, and data analysis patterns. Use this skill whenever the user asks about W&B runs, Weave traces, evaluations, training metrics, loss curves, model comparisons, or any Weights & Biases data — even if they don't say "W&B" explicitly.

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。

Optimize a pydantic-ai agent's instructions, tool descriptions, output type, and signature inputs using the gepa CLI. Trigger when the user asks to "optimize this agent", "improve tool descriptions", iterate on prompts driven by eval failures, or otherwise improve a pydantic-ai agent against a dataset. Operates in the user's repo with full filesystem access — YOU are the reflection model; the gepa CLI handles minibatches, evaluation, and Pareto bookkeeping.

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。

Fix silent incorrect results in RFDB Datalog queries that share a variable between two edge atoms on opposite ends (e.g. self-join patterns like `edge(M, C, "T1"), edge(C, M, "T2")`). Use when: (1) a Datalog rule returns rows that look structurally wrong (e.g. a self-loop rule reports hits but pinning M to each reported id refutes the edge existence), (2) Cypher `MATCH (m)-[:R1]->(c)-[:R2]->(m)` returns the same bogus rows (engine-level bug, not Datalog-specific), (3) results change when you bind one variable explicitly vs. leave it free. Root cause: hash- join fast path in `eval_edge_hash_join` / `eval_incoming_hash_join` unconditionally rebinds the non-key Term::Var without checking whether the variable is already bound in the current row.

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 evaluation frameworks for agent systems. Use when testing agent performance, validating context engineering choices, or measuring improvements over time.

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。

Deep Single-Candidate Scoring — evaluate one candidate across 5 dimensions (skills match, experience relevance, culture fit signals, growth potential, red flags) with final 0-100 score and hire/no-hire signal

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。

Analiza textos aplicando pensamiento crítico — el marco de los 8 elementos del pensamiento y los estándares intelectuales universales de Richard Paul y Linda Elder — y detecta las falacias lógicas graves presentes. Úsala siempre que el usuario comparta un texto (pegado o en un archivo) y pida analizarlo críticamente, detectar falacias, evaluar argumentos, identificar sesgos, o preguntas como "¿qué problemas tiene este argumento?", "¿es sólido este razonamiento?", "analiza esto", "dame una crítica". También actívala cuando el usuario comparta un artículo de opinión, un post, un discurso, un ensayo o cualquier texto argumentativo y quiera evaluar su calidad argumentativa.

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。

Show a team skill's eval history — committed receipts per version and this machine's local runs — as a Markdown board from the terum-skills CLI, without fetching. Use when the user asks how a shared skill scored, which version passed, or what its receipts say.

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。

Drive the terum-skills CLI from a Claude Code or Codex session: run any verb with --format md and show its board — inspect the Library or the team Marketplace, search, fetch with sync, validate or fix a local skill, install the latest version into Global or an added project, publish a local skill as an immutable version, manage the eval queue — and prepare the verbs that belong in a terminal (project setup, skill move/copy/rename/delete, prune, reconcile, machine uninstall, team administration). Use when the user wants to manage, evaluate, publish or install skills and no narrower terum-skills skill fits.

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 analyzing an existing TypeScript or JavaScript codebase to decide where and how to introduce Inngest. Covers repository discovery, framework and package detection, finding durability gaps in HTTP handlers, webhooks, cron jobs, queues, long-running jobs, AI agents, Agent Evals, polling loops, eval loops, and side-effect-heavy code, then producing and implementing an incremental integration 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。

Entry point for rafter. Invoke when a sub-skill is unclear, or when the task needs `rafter run` (remote SAST+SCA), `rafter secrets` (local secrets-only), `rafter audit`, policy checks, or command-risk evaluation. Scope by security surface, not task label: engage when the diff touches auth, credentials/secrets/tokens, untrusted input, SQL, shell/exec, file paths, deserialization, crypto, network endpoints, data deletion, or dependencies; for research/experimental/local-only code with none of that, a quick surface check is enough. When such surface IS present and no rafter skill or CLI call has been made, invoke this before handing the task off — an un-evaluated "done" on genuine security surface is not done.

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 evaluating VCSDD grading dimensions during adversarial review. Provides concrete evaluation checklists for each of the 5 dimensions and convergence signal detection.

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。

Perform critical Rust code reviews covering correctness, edition 2024 compliance, error handling, API design, async pitfalls, and dependency hygiene. ALWAYS use this skill when the user wants to review, audit, or critically evaluate Rust code — whether that's a PR diff, a specific crate or module, a cross-cutting concern like error handling, or the whole codebase. This includes requests to "review my changes", "check this code", "audit for best practices", "look for issues", "what's wrong with this", or "flag anything that could bite us". Use it even when the user doesn't say "review" explicitly but is asking you to find problems, inconsistencies, or anti-patterns in existing Rust code. Do NOT use for requests to write, fix, refactor, test, explain, or implement code — only for evaluating existing code.

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 validating, benchmarking, or monitoring LLM application performance. Keywords: RAG evaluation, LLM-as-a-judge, CI/CD gating, trajectory scoring, test suites, prompt 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。

Use when building self-correcting retrieval systems for AI agents. Keywords: RAG, retrieval, Corrective RAG, Self-RAG, query decomposition, reranking, hallucination, grounding.

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。

Master context engineering for AI agent systems. Use when designing agent architectures, debugging context failures, optimizing token usage, implementing memory systems, building multi-agent coordination, evaluating agent performance, or developing LLM-powered pipelines. Covers context fundamentals, degradation patterns, optimization techniques (compaction, masking, caching), compression strategies, memory architectures, multi-agent patterns, LLM-as-Judge evaluation, tool design, and project development.

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。

Create AI agents and workflows using Microsoft Agent Framework SDK. Supports single-agent and multi-agent workflow patterns. USE FOR: create agent, build agent, scaffold agent, new agent, agent framework, workflow pattern, multi-agent, MCP tools, create workflow. DO NOT USE FOR: deploying agents (use agent/deploy), evaluating agents (use agent/evaluate), Azure AI Foundry agents without Agent Framework SDK.

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。

Memory is the cornerstone of intelligent agents. Without it, every interaction starts from zero. This skill covers the architecture of agent memory: short-term (context window), long-term (vector stores), and the cognitive architectures that organize them. Key insight: Memory isn't just storage - it's retrieval. A million stored facts mean nothing if you can't find the right one. Chunking, embedding, and retrieval strategies determine whether your agent remembers or forgets. The field is fragm

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。

Provides guidance for automatically evolving and optimizing AI agents across any domain using LLM-driven evolution algorithms. Use when building self-improving agents, optimizing agent prompts and skills against benchmarks, or implementing automated agent evaluation loops.

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。

Assesses a research paper outline (.qmd file) against structured criteria from Kosuke Imai's empirical research guide. Evaluates the abstract and section outline for: research question clarity, stated contributions, hypotheses and testable implications, data description, planned results and inferential approach, and robustness checks. Detects causal papers from the abstract and conditionally assesses identification strategy only when causal framing is present. Produces a structured markdown report with PASS/PARTIAL/FAIL assessments and actionable suggestions. Use when asked to assess, evaluate, review, or check a paper outline, abstract-and-outline, or research plan in a .qmd file.

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。

"Apply pragmatist philosophy (Peirce, James, Dewey) to frame knowledge as instrumental for action, evaluate ideas by their practical consequences, and conduct inquiry as problem-solving. Use this skill when the user needs to bridge theory and practice, evaluate competing theories by their usefulness, employ abductive reasoning to generate hypotheses, or when they ask 'which theory is more useful here', 'how do I move from abstract ideas to actionable knowledge', or 'what practical difference does this distinction make'.".

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。

"Apply the Efficient Market Hypothesis (Fama, 1970) to evaluate information incorporation in asset prices across weak, semi-strong, and strong forms. Use this skill when the user needs to assess market efficiency, determine if a trading strategy can generate abnormal returns, evaluate event studies, or when they ask 'can technical analysis work', 'does the market already know this', or 'is this anomaly exploitable'.".

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 unit economics to evaluate per-unit profitability and business model scalability. Use this skill when the user needs to assess whether each transaction, customer, or product unit is profitable, evaluate startup viability, or optimize contribution margins — even if they say 'does our business model work', 'what's our margin per order', or 'can we scale profitably'.".

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。

"Calculate and analyze Customer Acquisition Cost (CAC) and Customer Lifetime Value (LTV) to evaluate unit economics and marketing efficiency. Use this skill when the user needs to assess whether their customer acquisition is profitable, optimize marketing spend allocation, or evaluate business model viability — even if they say 'are we spending too much on ads', 'what's each customer worth', or 'is our growth sustainable'.".

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。