「outputs」の検索結果

Experimental NotebookLM harness for listing notebooks, managing sources, asking questions, generating artifacts, and downloading outputs through an installed notebooklm 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。

Command-line interface for CloudAnalyzer — Agent-friendly harness for CloudAnalyzer, a QA platform for mapping, localization, and perception outputs. Supports 27 commands across 8 groups: point cloud evaluation, trajectory evaluation, ground segmentation QA, config-driven quality gates, baseline evolution, processing, visualization, and interactive REPL.

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。

Prompt engineering regression test matrix register: baseline outputs, semantic drift thresholds, judge evaluations, and golden dataset.

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 the user asks to "implement LLM-as-judge", "compare model outputs", "create evaluation rubrics", "mitigate evaluation bias", or mentions direct scoring, pairwise comparison, position bias, evaluation pipelines, or automated quality 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。

Read, create, or edit Excel spreadsheets (.xlsx/.xlsm) — sheet data, formulas, styles, charts, multi-sheet workbooks — and bulk .csv/.tsv tables; use whenever a spreadsheet is the input or the deliverable (extract/analyze data, add columns/formulas/formatting/charts, clean messy tables, build from scratch), but not for Google Sheets API or Word/PDF/script outputs.

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。

Convert evaluation traces and production logs into SFT examples and preference pairs. Use when graded traces or failure examples exist and need to become training data, when applying rejection sampling to model outputs, or when building DPO pairs from passing and failing runs.

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 Excalidraw diagrams from natural language descriptions. Use when asked to "create a diagram", "make a flowchart", "visualize a process", "draw a system architecture", "create a mind map", or "generate an Excalidraw file". Supports flowcharts, relationship diagrams, mind maps, and system architecture diagrams. Outputs .excalidraw JSON files that can be opened directly in Excalidraw.

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。

Quickly screen inbound deal flow — CIMs, teasers, and broker materials — against the fund's investment criteria. Extracts key deal metrics, runs a pass/fail framework, and outputs a one-page screening memo. Use when reviewing new deal flow, triaging inbound materials, or deciding whether to take a first call. Triggers on "screen this deal", "review this CIM", "should we look at this", "triage this teaser", or "deal screening".

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。

Real DCF (Discounted Cash Flow) model creation for equity valuation. Retrieves financial data from SEC filings and analyst reports, builds comprehensive cash flow projections with proper WACC calculations, performs sensitivity analysis, and outputs professional Excel models with executive summaries. Use when users need to value a company using DCF methodology, request intrinsic value analysis, or ask for detailed financial modeling with growth projections and terminal value calculations.

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。

Solve competition math problems (IMO, Putnam, USAMO, AIME) with adversarial verification that catches the errors self-verification misses. Activates when asked to 'solve this IMO problem', 'prove this olympiad inequality', 'verify this competition proof', 'find a counterexample', 'is this proof correct', or for any problem with 'IMO', 'Putnam', 'USAMO', 'olympiad', or 'competition math' in it. Uses pure reasoning (no tools) — then a fresh-context adversarial verifier attacks the proof using specific failure patterns, not generic 'check logic'. Outputs calibrated confidence — will say 'no confident solution' rather than bluff. If LaTeX is available, produces a clean PDF after verification passes.

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 and improve CLAUDE.md files in repositories. Use when user asks to check, audit, update, improve, or fix CLAUDE.md files. Scans for all CLAUDE.md files, evaluates quality against templates, outputs quality report, then makes targeted updates. Also use when the user mentions "CLAUDE.md maintenance" or "project memory 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。

Replay-first debug flow for SGLang serving problems. Use when a live or recent server shows health-check failures, latency or throughput regressions, queue growth, timeouts, distributed stalls, crash dumps, wrong outputs after deploys, or PD/EP/HiCache issues, and the job is to turn the problem into a replay plus the right next debug tool.

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 research framework for pre-IPO / private companies (Ant Group, SpaceX, Stripe, ByteDance...). Six analyst lenses — business model, financial forensics, competitive landscape, risk & governance, tech & IP, alternative-data signals — run in parallel via run_swarm, then cross-validated for signal consistency before any verdict. Built around the core challenge of private-company work: information is scarce, so every data point carries a confidence label (high / medium / low), inference is shown separately from fact, and 'I don't know' is a valid output. Outputs a fair-value range, exit-path analysis, and an information-gap map. Use for any unlisted company where you need to judge what the business is actually worth.

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。

Supply-chain bottleneck arbitrage. Given a super-trend (AI infra, energy transition, defense, semiconductor reshoring, space economy), decompose its physical supply chain down to Layer 2/3 choke points (optics, lasers, InP/SOI substrates, IC substrates, probe cards, specialty fiberglass...) and surface under-the-radar listed companies sitting on each bottleneck. Scores each link on 6 scarcity criteria, applies mandatory valuation gates (PS/PE/safety-margin) via the financial_rigor tool, and Munger-style reverse-validates. Outputs a ranked bottleneck opportunity board. Use when the user wants hidden beneficiaries of a structural trend rather than already-priced leaders.

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 management assessment — the 'buying a stock is buying a person' layer. For a company or a named executive, evaluate integrity (promise-vs-delivery tracking, crisis behavior, stakeholder treatment), ability (strategic foresight, execution, capital-allocation record) and governance (equity structure, compensation, related-party deals). Outputs a weighted score across integrity / ability / capital-allocation / governance plus Duan Yongping's 3-question verdict ('would you hand this person your money for 10 years'). Use when standard research leaves management quality uncertain, or when management IS the investment thesis.

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。

Detect MITRE ATLAS AML.T0024 attacks (model stealing, inversion, membership inference) performed via inference-API abuse, by monitoring per-principal query volume/distribution, rate-limiting and perturbing outputs, and red-teaming your model's extractability. Use for a public or partner inference API needing cloning/inversion/membership-inference detection, or a pre-deployment red-team exercise to measure extraction risk.

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。

Automates the enrichment of raw indicators of compromise with multi-source threat intelligence context using SOAR platforms, Python pipelines, or TIP playbooks to reduce analyst triage time and standardize enrichment outputs. Use when building automated enrichment workflows integrated with SIEM alerts, email submission pipelines, or bulk IOC processing from threat feeds. Activates for requests involving SOAR enrichment, Cortex XSOAR, Splunk SOAR, TheHive, Python enrichment pipelines, or automated IOC processing.

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 production-ready AI agents with PydanticAI — type-safe tool use, structured outputs, dependency injection, and multi-model support.

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。

Anthropic's method for training harmless AI through self-improvement. Two-phase approach - supervised learning with self-critique/revision, then RLAIF (RL from AI Feedback). Use for safety alignment, reducing harmful outputs without human labels. Powers Claude's safety system.

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。

Guarantee valid JSON/XML/code structure during generation, use Pydantic models for type-safe outputs, support local models (Transformers, vLLM), and maximize inference speed with Outlines - dottxt.ai's structured generation library

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。

LLM observability platform for tracing, evaluation, and monitoring. Use when debugging LLM applications, evaluating model outputs against datasets, monitoring production systems, or building systematic testing pipelines for AI 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。

Fast structured generation and serving for LLMs with RadixAttention prefix caching. Use for JSON/regex outputs, constrained decoding, agentic workflows with tool calls, or when you need 5× faster inference than vLLM with prefix sharing. Powers 300,000+ GPUs at xAI, AMD, NVIDIA, and LinkedIn.

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 a PR or branch diff using the knowledge graph for full structural context. Outputs a structured review with blast-radius 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。

Systematic claim-by-claim verification for any content before it ships. Modeled on professional fact-checking desks (The New Yorker, ProPublica, IFCN standards): extract every verifiable claim, check each against live citable sources (never training data), assign a 6-level confidence status, apply corrections, and produce a scored pass/fail report. Includes a data-derived-claims gate for outputs produced FROM the brain or a database: PRODUCER ≠ VERIFIER (re-derive each claim via a different query path) and AFFILIATION ≠ AUTHORSHIP (person→thing claims resolve through typed edges), with delivery hard-blocked on unsupported claims.

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。