“accuracy”的搜索结果

Pick the right LLM for LEGAL RESEARCH & ANALYSIS — issue-spotting, rule application, case/statute analysis, memos, and multi-step agentic research. Vendor-neutral routing grounded in mid-2026 benchmarks (Vals AI LegalBench across 124 models; Harvey Legal Agent Benchmark for agentic work). Asks up to 4 quick questions (cost, speed, accuracy/stakes, privacy/jurisdiction/language), then recommends a primary model + fallback + what to avoid + what a human must verify. Use when someone asks "which model for legal research / case analysis / a memo", "best AI for legal reasoning", "route this research task", or is starting legal analysis without a fixed model.

中文简介正在准备中。当前显示原文说明。

Adversarial verification of AI-generated legal content with systematic fact-checking, source validation, and quality control. Use when a user asks to verify, fact-check, red-team, validate sources, or quality-control a legal document, briefing, compliance summary, or regulatory analysis before it is distributed to clients, stakeholders, or published. Trigger phrases include "verify", "fact-check", "red team", "red-flag", "check accuracy", "validate sources", "quality control", "is this correct", and "review for errors". Produces a structured verification report with severity-categorized errors, verified sources, unsupported claim list, missing disclaimers, and an explicit distribution-readiness assessment.

中文简介正在准备中。当前显示原文说明。

Routes any legal task to the right LLM, like OpenRouter but for legal work and grounded in benchmarks instead of brand loyalty. Built from mid-2026 legal evals (legalbenchmarks.ai, Vals AI × Stanford LegalBench across 124 models, Harvey's Legal Agent Benchmark, the Atticus Project's CUAD/MAUD/ACORD) plus translation evidence (WMT25, SwiLTra-Bench, ArabLegalEval). Covers five verticals: contract drafting, info extraction, legal research, contract review, and legal translation (including Arabic/MENA). Each asks up to four questions (cost, speed, accuracy/stakes, privacy/jurisdiction/language), then returns a primary model, a fallback, what to avoid, and what a human must verify. Core principle: capability is not controllability, so every route ends with a verification step. Not legal advice; a lawyer owns the output.

中文简介正在准备中。当前显示原文说明。

Mandatory external verification workflow for ALL non-trivial factual claims before presenting them as true. This skill MUST be used whenever Claude is asked to research any topic, answer factual questions, provide current information, draft documents containing factual claims, give legal advice or cite legal authority, discuss current events or public figures, provide technical or scientific information, state statistics or data points, or answer ANY question where the answer could have changed over time. Also trigger when the user asks Claude to 'check', 'verify', 'confirm', 'research', 'look up', or 'find out' anything, or when the user needs information that requires freshness, precision, or source accuracy. This skill overrides any default tendency to answer from memory. If a task involves stating facts, citing sources, or providing current information — use this skill.

中文简介正在准备中。当前显示原文说明。

Review the week using accumulated session evidence — retrieval rates, hint depths, calibration accuracy, transfer and unassisted results. The learner identifies patterns and sets a strategy goal. Use weekly or after a multi-session period.

中文简介正在准备中。当前显示原文说明。

Verify a BibTeX file for hallucinated or fabricated references by cross-checking every entry against CrossRef, arXiv, and DBLP. Reports each reference as verified, suspect, or not found, with field-level mismatch details (title, authors, year, DOI). Use when the user wants to check a .bib file for fake citations, validate references in a paper, or audit bibliography entries for accuracy.

中文简介正在准备中。当前显示原文说明。

Use when the user wants to compare or benchmark multiple LLMs/agents arena-style but it's unclear which specific workflow fits — a general-purpose win-rate comparison on a custom task, or a benchmark specifically about reference/citation hallucination rate. Also use when the user mentions model arena, agent arena, pairwise model comparison, win-rate ranking, or comparing models on a task and hasn't specified whether that task is generic or about citation accuracy. This skill is the entry router for the arena-eval suite: it asks one diagnostic question when needed, then recommends the workflow or workflows needed to cover the request.

中文简介正在准备中。当前显示原文说明。

Use when the user wants to build an evaluation system for an LLM/agent application but doesn't know where to start — they have traces, prompts, RAG pipelines, or nothing at all. Also use when the user mentions evaluation, eval, benchmarking, testing LLM quality, measuring agent performance, assessing RAG accuracy, or wants to compare prompts/models. This skill is the entry router: it asks diagnostic questions then recommends which sub-skill (local workflow) to use next.

中文简介正在准备中。当前显示原文说明。

Run fable-mode execution discipline on Claude Fable 5.1 — the top of the escalation ladder and the strongest staged run available. Routes the task to the @fable-orchestrator agent with its model overridden to Fable (`model: "fable"`), which stages the work, delegates artifact production to @fable-worker-sonnet / @fable-worker-haiku, and cold-checks deliverables with @fable-verifier. Trigger when the user explicitly asks for thorough/systematic/"deep work" handling on the strongest model ("fable on fable", "stage this on fable", "deep work mode, fable", "run this on 5.1"), or when a fable-opus run reports the task exceeds Opus's ceiling. Benchmarked 2026-09-02: zero correctness delta on Fable 5.1 at ~1.1× tokens, ~2× wall — a provenance runner, not an accuracy runner. Do NOT use for ordinary single-pass tasks — prefer fable-opus, fable-sonnet, or fable-haiku when the task doesn't need peak reasoning. Fable is plan-included; bulk work still routes down-tier.

中文简介正在准备中。当前显示原文说明。

Comprehensive truth scoring, code quality verification, and automatic rollback system with 0.95 accuracy threshold for ensuring high-quality agent outputs and codebase reliability.

中文简介正在准备中。当前显示原文说明。

A robust and outlier-aware method for testing differential tissue composition from single-cell data. This model can infer changes in tissue composition and heterogeneity, and can produce realistic data simulations based on any existing dataset. This model can also transfer knowledge from a large set of integrated datasets to increase accuracy further.

中文简介正在准备中。当前显示原文说明。

Return rate reduction — root cause analysis, listing accuracy, packaging improvements, size guides

中文简介正在准备中。当前显示原文说明。

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

中文简介正在准备中。当前显示原文说明。

Keep the agent's context lean so accuracy doesn't collapse. Use on long sessions, big files, or when the agent starts hallucinating.

中文简介正在准备中。当前显示原文说明。

Mandatory pre-flight-search reference. Contains the Seats.aero workflow (pull ALL programs first), source accuracy hierarchy, Southwest/Companion Pass specifics, small-market caveats, and Duffel limitations.

中文简介正在准备中。当前显示原文说明。

Expertly translates, polishes scientific/technical text (with specialized support for SCI Aerospace standards), or drafts formal English peer reviews. Ensures accuracy, clarity, and adherence to high academic standards.

中文简介正在准备中。当前显示原文说明。

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, update or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

中文简介正在准备中。当前显示原文说明。

Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.

中文简介正在准备中。当前显示原文说明。

Ultra-compressed communication mode. Cuts token usage ~75% by dropping filler, articles, and pleasantries while keeping full technical accuracy. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman.

中文简介正在准备中。当前显示原文说明。

Standardizes the creation and evaluation of high-density Agent Skills (Claude, Cursor, Windsurf). Ensures skills achieve high Activation (specificity/completeness) and Implementation (conciseness/actionability) scores. Use when: writing or auditing SKILL.md, improving trigger accuracy, or refactoring skills to reduce redundancy and maximize token ROI.

中文简介正在准备中。当前显示原文说明。

Produces human-sounding text that avoids detectable AI writing patterns. Activates on any writing task — tweets, emails, articles, bios, captions, reports, copy, messages, LinkedIn posts, cover letters, README files, or any content where the output must not read as AI-generated. Enforces banned vocabulary, structural variety, punctuation discipline, accuracy rules, and voice calibration. Use when the user says "write," "draft," "rewrite," "make this sound human," "anti-slop," "not AI," or any variation of wanting authentic-sounding output.

中文简介正在准备中。当前显示原文说明。

Code comment accuracy verification, documentation completeness assessment, comment rot detection.

中文简介正在准备中。当前显示原文说明。

Fast file editing via Morph Apply API (10,500 tokens/sec, 98% accuracy)

中文简介正在准备中。当前显示原文说明。

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, update or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

中文简介正在准备中。当前显示原文说明。