「rl」の検索結果

Enhancement overlay — version the WHOLE deployable LLM-app artifact as one bundle: prompts + compiled programs + model snapshot pins + retrieval config + eval-set version, versioned together so a deploy is reproducible and rollback is atomic. Activate when preparing to deploy an LLM app, when asking "what exactly is running in prod right now?", when a deploy must be reproducible months later, or when an incident needs a clean rollback. The core reframe: an LLM app artifact is NOT an ML model — it is a manifest over many independently-mutable parts, not one weights file. Do NOT activate for one-off prompt edits with no deploy, for a single-component demo, or where a vendor owns the whole prompt lifecycle. For versioning ONE compiled prompt use [[agentsop-per-model-artifacts]]; for the CI comparison mechanism use [[agentsop-regression-gate]]. Search keywords: prompt versioning, reproducible deploy, what is running in prod, rollback LLM app, model pinning, prompt registry, version prompts and config.

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。

ENHANCE overlay on [[dspy]] — the upfront rubric for choosing a reasoning SHAPE (Predict / ChainOfThought / ReAct / ProgramOfThought) BEFORE you write a prompt or pick an optimizer. The local `dspy` skill lists the modules but never surfaces the *selection criterion*: reasoning shape is chosen by task structure, not by reflexively defaulting to CoT. Activate every time a new LM-calling node/step is added to a pipeline. Do NOT activate for one-shot prompts, optimizer/teleprompter choice (that is the dspy SOP's job), or non-LM control flow. Search keywords: chain of thought vs ReAct, when to use CoT, reasoning type, ReAct vs CoT vs PoT, which dspy module, predict vs chain of thought.

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。

Security-first SOP for multi-tenant RAG systems. Activate when a calling agent is building, reviewing, or debugging any retrieval pipeline whose vector store is shared across more than one user, organisation, workspace, customer, or permission scope. Encodes the single non-negotiable rule — **filter at the vector store query, never after retrieval / never after rerank** — together with the per-vendor query-time filter APIs (Pinecone namespaces + `$eq`/`$in`, Weaviate `multiTenancyConfig` + tenant handle, Qdrant `is_tenant` payload index + `Filter.must`, Chroma `where`, pgvector RLS), and the cross-framework adapters (LlamaIndex `MetadataFilters`, LangChain `filter=` dict). Frame the work as preventing CVE-2024-41892 / EchoLeak / Slack-AI-class cross-tenant leakage, not as "adding a filter for relevance".

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。

Enhancement-overlay skill — the DECISION + WIRING layer for LM observability that the single-backend skills [[langsmith]], [[phoenix]], [[mlflow]] do NOT cover. Each of those installs one backend; none of them help you DECIDE which backend fits your stack/scale/budget, nor give you a one-line autolog that turns it on fast. Use when starting any LM project, before the first deploy, or the moment someone asks "why did it do that?" and there are no traces to answer with. The skill picks a backend by stack (LangSmith for LangChain/LangGraph; Phoenix for OSS/local OpenTelemetry; MLflow for ML-shops already on MLflow; Langfuse for self-host), wires one-line autolog, verifies traces land, and adds eval hooks — instrumenting BEFORE you need it. Cross-links the first-debug-move skill [[agentsop-prompt-history-inspect]]. Do NOT activate to re-teach a backend you already chose (defer to its own skill), or for non-LM ML experiment tracking with no LLM calls (that is plain MLflow).

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。

Lifecycle SOP for **per-model prompt artifacts** — the compiled prompts, instructions, few-shot demos, edit-format pins, and embedding-bound indices that change behavior when the underlying LM, dataset, or framework version changes. Activate when adopting compiled prompts (DSPy, GEPA, BootstrapFewShot output), when supporting multiple LMs in production, when a provider deprecates a model snapshot, or when a framework deprecates a config surface (LlamaIndex `ServiceContext` → `Settings`, Aider edit-format defaults). Do NOT activate for one-off raw prompt edits or for truly model-agnostic system prompts that have been swap-tested. Search keywords: prompt portability, model swap, recompile prompt, model deprecation, prompt per model, prompt breaks on new model, version compiled prompts.

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 rubric for promoting a prose prompt into a typed DSPy Signature. This is an ENHANCE overlay on top of the [[dspy]] library skill: it does NOT teach DSPy syntax — it answers the coder-agent decision "when do I stop hand-writing a prompt string and declare it as a `dspy.Signature`, and how do I name/describe its fields so the optimizer and the calling code both get a clean contract." Activate when: a prompt string grows past ~50 lines; the LM output is consumed by code (parsed, branched on, stored) rather than read by a human; the same prompt is reused across >1 call site; or a teammate asks "should this be a Signature?". Do NOT activate for one-shot throwaway prompts, or for HOW-TO questions about DSPy modules /optimizers/compile — defer those to the [[dspy]] skill and the [[agentsop-dspy]] workflow skill. Search keywords: typed prompt, structured prompt, DSPy Signature, prompt as a function, prompt contract, when to formalize a prompt.

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。

Enhancement-overlay decision protocol for STREAMING the output of long-running LLM / agent runs from the *backend*, not just wiring a typing animation in the UI. Activates when a coder agent must stream final tokens to a chat client, surface intermediate agent steps (which tool, which node, partial reasoning), emit custom tool-progress events, choose a transport (SSE vs WebSocket), or decide what to do when the client disconnects mid-stream. The langchain / langgraph skills mention stream modes but stop at "you can stream"; this skill encodes *what to stream, over what transport, and how to fail safely*.

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。

Behavioral guardrails for LLM-assisted coding. Use when writing, reviewing, or refactoring code in any project to avoid overcomplication, keep changes surgical, surface assumptions early, and execute against verifiable success 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。

Review the symbol-notation section of a mathematical-modeling paper against the full paper. Check table coverage, symbol meanings, units, overloading, case and subscript consistency, first-use definitions, formula usage, and visible table formatting. Use for symbol-table diagnosis, not general paper 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。

Learn from public breach disclosures — extract the audit question each one implies and check your own stack. Capital One IMDS abuse, LastPass vault exfiltration, Okta Lapsus$, Snowflake credential reuse, MOVEit, SolarWinds, Equifax, Target POS, Codecov, Uber, Twilio — what would you check now if your boss said 'could that happen to us?' Use when the user mentions 'breach analysis,' 'lessons learned,' 'security postmortem,' 'breach patterns,' 'breach lessons,' 'has this happened to us,' 'apply breach lessons,' 'preempt breaches,' 'security retrospective,' 'real-world security incidents,' or wants to harden against known attacker playbooks.

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。

Audit iOS and Android mobile applications against OWASP MASVS / MASTG — insecure storage, weak crypto, certificate pinning, deeplinks, IPC, jailbreak/root detection, reverse-engineering resistance. Use when the user mentions 'mobile security,' 'iOS security,' 'Android security,' 'mobile audit,' 'mobile pentest,' 'MASVS,' 'MASTG,' 'certificate pinning,' 'jailbreak detection,' 'root detection,' 'deeplink,' 'URL scheme,' 'app transport security,' 'keychain,' 'keystore,' 'mobile reverse engineering,' or has a mobile app to 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。

数学建模竞赛解题全流程指导。覆盖国赛(CUMCM)和美赛(MCM/ICM)全部题型(A-F)，提供12种问题本质分析、95+场景模型决策矩阵、5本算法Cookbook、11本完整例题Playbook、22个Python+7个MATLAB可运行代码模板。与math-modeling-paper形成"解题→写作"配对。当用户提及建模思路、选什么模型、怎么建模、赛题求解、粘贴赛题文本、美赛/国赛题目分析、CVaR/NSGA-II/Monte Carlo/时间序列/ANOVA/灰色关联、网络流/图论/生态建模、模型命名/Memo/Letter/Our Work流程图时，使用此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。

API hardening for Express, FastAPI, and serverless. Use for rate limiting, CORS, input validation, API keys, or OWASP API Top 10.

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。

Scholarly writing and research compliance. Use for CRediT, preregistration, Plan S, Nelson Memo, preprints, ORCID, LLM disclosure.

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。

Kalshi daily and hourly range markets on crypto prices (BTC, ETH) and equity indices (S&P 500, Nasdaq-100) — bracket structure, Gaussian P(YES) modeling on price/vol, close-offset decision timing, longshot-sell edge with honest evidence bounds

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。

Reinforcement learning for trade execution optimization including order splitting, adaptive timing, and impact minimization

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。

[STUB] Options pricing models including Black-Scholes, binomial trees, Monte Carlo, implied volatility surfaces, and Greeks for crypto options

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。

Database schema patterns for InsForge including social graphs, e-commerce, content publishing, and multi-tenancy with RLS policies. Use when designing data models with relationships, foreign keys, or Row Level Security.

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。

Latch platform for bioinformatics workflows. Build pipelines with Latch SDK, @workflow/@task decorators, deploy serverless workflows, LatchFile/LatchDir, Nextflow/Snakemake integration.

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。

Choose optimal external AI models for code analysis, bug investigation, and architectural decisions. Use when consulting multiple LLMs via claudish, comparing model perspectives, or investigating complex Go/LSP/transpiler issues. Provides empirically validated model rankings (91/100 for MiniMax M2, 83/100 for Grok Code Fast) and proven consultation strategies based on real-world 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。

High-performance toolkit for genomic interval analysis in Rust with Python bindings. Use when working with genomic regions, BED files, coverage tracks, overlap detection, tokenization for ML models, or fragment analysis in computational genomics and machine learning applications.

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 and analyze SEC filings and financial statements using EdgarTools. Get company data, filings, XBRL financials, and perform multi-company 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。

This skill provides an advanced financial modeling suite with DCF analysis, sensitivity testing, Monte Carlo simulations, and scenario planning for investment decisions

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。

Enterprise-grade compliance architecture for SOC 2, HIPAA, GDPR, PCI-DSS. Provides compliance checklists, security controls, audit guidance, and regulatory requirements for serverless and cloud architectures. Activates for compliance, HIPAA, SOC2, SOC 2, GDPR, PCI-DSS, PCI DSS, regulatory, healthcare data, payment card, data protection, audit, security standards, regulated industry, BAA, business associate agreement, DPIA, data protection impact assessment.

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。