「cis」の検索結果

Decision protocol for the map-reduce / dynamic fan-out pattern in LM pipelines — "given list L, run f(item) for each item in parallel, then combine". Activates when the coder agent is about to process N items with N LM calls (per-doc summarize, per-query retrieve, per-candidate rank, parallel tool fan-out). Encodes the *when*, *how many at once*, *what to do when one fails*, and *how to reduce* — not the API of any single framework. Cross-framework: LangGraph `Send`, CrewAI parallel tasks / Flow, `asyncio.gather`, `ThreadPoolExecutor`, LlamaIndex batch retrieval.

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。

Split a multi-call LM workflow by cognitive load, not by accuracy: let one strong model make the few reasoning decisions and a cheap model do the many mechanical executions (Aider architect+editor, DSPy optimizer-LM vs task-LM, vLLM speculative draft+target, LangGraph supervisor+worker are the same shape). Use when designing or cost-optimizing a pipeline that calls an LM many times, when deciding which steps need a strong reasoner vs a cheap executor, or when adding an escalation valve for when the cheap tier degrades. Search keywords: reduce LLM cost, cheaper model, lower token cost, model cascade, route to cheap model, strong model plus cheap model, LLM cost optimization.

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 multiscale chunking for RAG by embedding small units for retrieval precision and returning larger context for synthesis. Use when fixed-size chunks either lose surrounding context or dilute relevance in long documents, manuals, filings, or codebases. Covers sentence-window and parent-child or auto-merging strategies, base chunk sizing, and evaluation. Do not use when a single chunk scale already meets retrieval and generation needs.

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。

Adds and tunes a reranker stage for RAG using the retrieve-wide, rerank-narrow pattern. Use when relevant documents appear in the initial top-N but are buried by noise, top-1 precision or MRR is low despite adequate recall, or too many marginal chunks consume context. Covers cross-encoder, API, and local rerankers; N-to-k selection; and latency/cost tradeoffs. Do not use when retrieval recall itself is failing.

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。

Translate a complete mathematical modeling contest problem sentence by sentence into precise modeling language, preserve every substantive condition and definition, expose hidden constraints, draw a mandatory Mermaid cross-question flowchart, audit omissions, and deliver one easy-to-open Markdown report. For Huawei Cup (CPGMCM) graduate-contest problems, additionally prepend a plain-language layer that rewrites the background and questions as a primary-school word problem with a mandatory term-mapping table. Optionally render the finished report as one standalone HTML page on request. Use whenever a user supplies a CUMCM, CPGMCM, or other modeling problem and asks to interpret, translate, unpack, read closely, identify requirements, or avoid missing details before modeling.

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。

Plan, scope, and execute an authorized red-team engagement — distinct from a penetration test. Covers engagement methodology, assumed-breach scenarios, ATT&CK emulation plans, rules of engagement, deconfliction with the blue team, post-engagement debriefs, and the program-level work that makes red teams actually improve defenses. Use when the user mentions 'red team,' 'red team engagement,' 'red teaming,' 'adversary emulation,' 'ATT&CK emulation,' 'assumed breach,' 'purple team exercise,' 'tabletop with technical execution,' 'red team scope,' 'rules of engagement,' 'red team RoE,' 'deconfliction,' 'red team debrief,' or wants to design or run a red-team engagement against systems with authorization.

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。

Research a specific CVE or vulnerability disclosure end-to-end — what version is affected, is your code reachable, is there a public PoC, is there a patch, what's the exposure window, what's the mitigation if you can't patch immediately. Use when the user mentions 'CVE,' 'vulnerability research,' 'is this CVE relevant,' 'zero-day,' 'CISA KEV,' 'GitHub Security Advisory,' 'reachability analysis,' 'patch analysis,' 'exploit availability,' 'EPSS,' 'CVSS,' or 'should we drop everything and patch this.'

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。

Flags irreversible decisions before commit. Use for data models, infra, auth boundaries, API contracts, event schemas, CI/CD.

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。

Selects the correct CLAUDE.md or LESSONS.md template via decision trees. Use when starting a project or unsure which 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。

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。

Stage implementation changes for commit with precise file selection. Use when the user asks to "stage changes", "stage files", "add files to staging", or "prepare changes for commit".

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。

Align on the shape of a change through an interview, then implement it. Escalates open product decisions and settles the implementation shape in conversation. Use when the user asks to "discuss this change", "align on this change first", "ask me questions first", "interview me then implement", "agree on the approach before coding", or wants the shape of a single change settled before any code is written.

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 a self-contained local prototype at .turbo/prototypes/<slug>.html, drive it, and hand it to the user to settle unknowns that prose cannot answer. Use when the user asks to "prototype this", "build a prototype", "mock this up", "show me what it would look like", "let me try the interaction first", or when a decision waits on seeing a surface or using it firsthand.

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。

Write a handoff file at .turbo/handoff/<YYYY-MM-DD>-<slug>.md capturing current session state — task, status, open decisions, in-flight changes, next step — so a fresh session can continue without re-deriving context. Use when the user asks to "create a handoff", "create handoff", "save handoff", "handoff before compact", "save session state", "handoff for next session", or "capture session state".

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 what the user cares about, prepare useful work privately, and prompt them with clear visual decisions. Use to start or continue Agency or handle its tickets.

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 should be used when drafting GitHub issues for the Positron repository. It provides workflows for searching duplicates, selecting appropriate labels, gathering complete context through questioning, and writing terse, fluff-free issues that precisely describe what is needed or wrong. The skill prepares issues for manual submission by the user. Use this skill when the user asks to draft or prepare an issue for Positron.

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。

Assist with core product management activities including writing PRDs, analyzing features, synthesizing user research, planning roadmaps, and communicating product decisions. Use when you need help with PM documentation, analysis, or planning workflows that integrate with your codebase.

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 multi-cloud architectures using a decision framework to select and integrate services across AWS, Azure, and GCP. Use when building multi-cloud systems, avoiding vendor lock-in, or leveraging best-of-breed services from multiple providers.

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 should be used at the start of any computationally intensive scientific task to detect and report available system resources (CPU cores, GPUs, memory, disk space). It creates a JSON file with resource information and strategic recommendations that inform computational approach decisions such as whether to use parallel processing (joblib, multiprocessing), out-of-core computing (Dask, Zarr), GPU acceleration (PyTorch, JAX), or memory-efficient strategies. Use this skill before running analyses, training models, processing large datasets, or any task where resource constraints matter.

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 stuck in circular debugging, when solutions aren't working despite multiple attempts, or when the user expresses frustration with lack of progress. Bring in GPT-5 as a third-party consultant to provide fresh perspective on complex technical problems, architectural decisions, or multi-system debugging issues. Ideal when you've tried multiple approaches without success, when the problem involves obscure edge cases or novel challenges, or when a second expert opinion would help break through an impasse. Gather all context from the conversation so far and present it comprehensively to GPT-5.

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。

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。