“experiments”的搜索结果

Designs and diagnoses list experiments (the item count technique), covering whether indirect measurement is warranted, control-list construction against floor and ceiling effects, design variants, estimators and assumption tests in the list package, and power planning for the precision penalty. Use when the user measures a sensitive attitude or behavior and asks about list experiments, item count, unmatched count, or veiled questioning, or has an implausible prevalence estimate. Deciding whether sensitivity bias exists at all goes to survey-design.

中文简介正在准备中。当前显示原文说明。

Drafts or audits a scientific paper’s introduction and framing — the real-world "why", an evidence audit, the funnel from theory to a falsifiable if-then with a named estimand, bridges across experiments, and a contribution list matched to the design. Use when the user asks to write, restructure, or critique an introduction, motivate or frame a paper, repair a gap-in-the-literature opening, sharpen or calibrate a contribution claim, or connect experiments into one argument. Sentence-level flow and wording are out of scope.

中文简介正在准备中。当前显示原文说明。

Step 4 of the PaperOrchestra pipeline (arXiv:2604.05018). ONE single multimodal LLM call that drafts the remaining paper sections (Abstract, Methodology, Experiments, Conclusion), extracts numeric values from experimental_log.md into LaTeX booktabs tables, splices the generated figures from Step 2, and merges everything into the template that already contains Intro + Related Work from Step 3. TRIGGER when the orchestrator delegates Step 4 or when the user asks to "write the methodology and experiments sections" or "fill in the rest of the paper".

中文简介正在准备中。当前显示原文说明。

Generalised autonomous optimisation loop — soft RLVR for any artifact a user can measure. Use this skill whenever a user wants to iteratively improve an artifact — code, prompts, documents, configs, designs, content — by running structured experiments, evaluating results against a multi-dimensional rubric, and learning from each attempt. Triggers include: "optimise this", "keep improving until it's good", "run experiments on", "autoresearch", "iterate on this overnight", "try different approaches and pick the best", or any request implying repeated evaluate-and-improve cycles. Also use when the user wants to improve a system prompt, a data pipeline, a writing style, or any artifact where quality can be decomposed into measurable tracks. For inference optimisation tasks (model latency, throughput, quantization, GPU deployment), a* delegates the low-level tuning to AITune while maintaining quality tracking and learning.

中文简介正在准备中。当前显示原文说明。

Generalised autonomous optimisation loop — soft RLVR for any artifact a user can measure. Web runtime package: uses memory in this order: connector-backed, project-pack, none. Never assumes subprocess access or unrestricted local files. Use this skill whenever a user wants to iteratively improve an artifact — code, prompts, documents, configs, designs, content — by running structured experiments, evaluating results against a multi-dimensional rubric, and learning from each attempt. Triggers include: "optimise this", "keep improving until it's good", "run experiments on", "autoresearch", "iterate on this overnight", "try different approaches and pick the best", or any request implying repeated evaluate-and-improve cycles.

中文简介正在准备中。当前显示原文说明。

SWE-bench pipeline for A/B testing Grafema with Claude Code. Use when: (1) running SWE-bench experiments, (2) comparing baseline vs grafema conditions, (3) evaluating results, (4) debugging container issues.

中文简介正在准备中。当前显示原文说明。

Create a new experiment folder by copying reference/ as a template. Auto-generates SESSION_NOTES.md and run.sh. Claude experiments use expA00, A01, ...; human experiments use exp200, 201, ... in sequential numbering.

中文简介正在准备中。当前显示原文说明。

Design statistically rigorous experiments to test data science hypotheses. Use when the user says "design an A/B test", "run an experiment", "test this hypothesis", "is this difference significant", "how many samples do I need", "randomized controlled trial", "causal inference", "uplift test", "holdout group", "significance test", "power calculation", "avoid p-hacking", or needs to determine whether an observed effect is real before making a product or model decision. For lean build-measure-learn product experiments without the statistics, use experiment-design instead.

中文简介正在准备中。当前显示原文说明。

Build Opportunity Solution Trees using Teresa Torres' framework for structured product discovery. Use this skill when: - You need to map a desired outcome to opportunities, solutions, and experiments - You want to decide WHAT to build next based on user research and discovery data - You have workshop findings, pilot feedback, or user research to structure into actionable options - You need a visual tree diagram showing the path from outcome to testable experiments

中文简介正在准备中。当前显示原文说明。

Evaluate ENCODE experiment quality using standard metrics and audit flags. Use when the user asks about data quality, wants to filter for high-quality experiments, needs to interpret quality metrics (FRiP, NSC, RSC, NRF, IDR, TSS enrichment, fragment size), wants to understand ENCODE audit warnings, needs to compare quality across experiments, or is deciding whether data is usable for their analysis. Also use when the user mentions QC, quality control, or data filtering.

中文简介正在准备中。当前显示原文说明。

Runs autonomous keep/discard experiments on a codebase to optimize a single metric for a fixed duration, in the style of karpathy/autoresearch. Use when the user says "autoresearch" (optionally with a focus, e.g. "autoresearch the optimizer"), asks to run experiments on a repo overnight, to hill-climb or optimize a metric autonomously, or points at a repo with a karpathy-style program.md.

中文简介正在准备中。当前显示原文说明。

Stops defensive writing across the entire paper lifecycle — writing, revising, cutting, and organizing experiments. Treats the paper as a press conference, not a project summary, lab log, or self-audit: identify the single most publishable strength of the work and build the most favorable, complete, and persuasive narrative around it. Never present everything evenly, never volunteer weakness, never write an experiment diary, never attack the paper on the reviewer's behalf. Triggers: polish my paper, revise manuscript, write abstract, write introduction, write conclusion, shorten paper, rebuttal, respond to reviewers, organize experiments, defensive writing, AI-flavored academic writing.

中文简介正在准备中。当前显示原文说明。

Launch Marcus multi-agent experiments with independent CLI agents in tmux panes. Use when the user says "build X with Marcus", "run a Marcus experiment", "spawn N agents with Marcus", "/marcus", or references the Marcus multi-agent framework. This skill handles experiment setup, config generation, and spawning independent agent CLI processes that coordinate via the Marcus MCP server. Each agent runs in its own tmux pane with full autonomy. NOT for ClawTeam — this is specifically for the Marcus MCP-based multi-agent system. NOTE: "Marcus" is also the name of the MCP server that agents use for coordination. The /marcus skill launches experiments that USE the Marcus MCP server — they are complementary, not competing. The MCP server must be running before invoking this skill. The Marcus MCP server is agent-agnostic; this skill supports Anthropic's claude CLI, OpenAI's codex CLI, and Google's gemini CLI as agent harnesses (selected via --harness).

中文简介正在准备中。当前显示原文说明。

Launch Marcus multi-agent experiments with independent Claude agents in tmux panes. Use when the user says "build X with Marcus", "run a Marcus experiment", "spawn N agents with Marcus", "/marcus", or references the Marcus multi-agent framework. This skill handles experiment setup, config generation, and spawning independent Claude CLI agents that coordinate via the Marcus MCP server. Each agent runs in its own tmux pane with full autonomy. NOT for ClawTeam — this is specifically for the Marcus MCP-based multi-agent system. NOTE: "Marcus" is also the name of the MCP server that agents use for coordination. The /marcus skill launches experiments that USE the Marcus MCP server — they are complementary, not competing. The MCP server must be running before invoking this skill.

中文简介正在准备中。当前显示原文说明。

Launch Marcus multi-agent experiments with independent CLI agents in tmux panes. Use when the user says "build X with Marcus", "run a Marcus experiment", "spawn N agents with Marcus", "/marcus", or references the Marcus multi-agent framework. This skill handles experiment setup, config generation, and spawning independent agent CLI processes that coordinate via the Marcus MCP server. Each agent runs in its own tmux pane with full autonomy. NOT for ClawTeam — this is specifically for the Marcus MCP-based multi-agent system. NOTE: "Marcus" is also the name of the MCP server that agents use for coordination. The /marcus skill launches experiments that USE the Marcus MCP server — they are complementary, not competing. The MCP server must be running before invoking this skill. The Marcus MCP server is agent-agnostic; this skill supports both Anthropic's claude CLI and OpenAI's codex CLI as agent harnesses (selected via --harness).

中文简介正在准备中。当前显示原文说明。

Guidance for SPR and BLI binding characterization experiments. Use when: (1) Planning binding kinetics experiments, (2) Troubleshooting poor/no binding signal, (3) Interpreting kinetic data artifacts, (4) Choosing between SPR vs BLI platforms.

中文简介正在准备中。当前显示原文说明。

Design leakage-safe machine learning experiments that mirror real deployment and support fair model comparisons. Use when defining prediction timing, feature eligibility, train-validation-test splits, baselines, metrics, or controlled model iterations; not for auditing whether raw labels are trustworthy.

中文简介正在准备中。当前显示原文说明。

Use when the user asks to create, scaffold, or edit Jupyter notebooks (`.ipynb`) for experiments, explorations, or tutorials; prefer the bundled templates and helper script for reproducible notebook structure and safer editing.

中文简介正在准备中。当前显示原文说明。

Guides agents through the 3-step experiment creation flow: defining the hypothesis, configuring rollout, and setting up analytics. Delegates rollout decisions to configuring-experiment-rollout and metric setup to configuring-experiment-analytics. TRIGGER when: user asks to create a new experiment or A/B test, OR when you are about to call experiment-create. DO NOT TRIGGER when: user is updating an existing experiment, managing lifecycle, or only browsing experiments.

中文简介正在准备中。当前显示原文说明。

Resolves a PostHog experiment reference from natural language to a concrete experiment ID by browsing `experiment-list` (not feature-flag tools), with disambiguation when multiple experiments match. Use when the user names or quotes an experiment ("split test demo", "the File engagement boost experiment", "onboarding retention test", "landing page hero experiment", "pricing experiment"), describes it loosely ("the signup experiment", "my pricing test", "the one with the new checkout"), uses a relative reference ("latest", "most recent", "the one I created yesterday"), filters by status (running, draft, stopped, archived), or otherwise refers to an experiment by anything other than its concrete ID.

中文简介正在准备中。当前显示原文说明。

Diagnoses bias, anomalies, and strange-looking results on a specific PostHog experiment. Covers empty / 0-exposure experiments, sample ratio mismatch, identity fragmentation, multi-variant exposure, uneven-split exclusion bias, significance traps (peeking, A/A, Bayesian vs Frequentist), PostHog-vs-SQL discrepancies, and surprises after mid-run edits. Symptom-driven dispatch to the right diagnostic. TRIGGER when: user asks 'is my experiment biased?' or 'why 0 exposures?', references the bias banner, says a variant looks strange / wrong / off, sees significance flipping, notices PostHog numbers disagreeing with their SQL, sees an A/A test showing significance, or reports surprises after mid-run edits. DO NOT TRIGGER when: creating a new experiment (use creating-experiments), only configuring rollout (use configuring-experiment-rollout) or metrics (use configuring-experiment-analytics), or only asking lifecycle questions (use managing-experiment-lifecycle).

中文简介正在准备中。当前显示原文说明。

Track ML experiments, manage model registry with versioning, deploy models to production, and reproduce experiments with MLflow - framework-agnostic ML lifecycle platform

中文简介正在准备中。当前显示原文说明。

Generate ideas that don't sound logical, then validate them with cheap behavioural experiments — Rory Sutherland's 'the opposite of a good idea can be a good idea' plus revealed-preference testing. Use when the obvious/logical solution is saturated and the user wants genuinely different options, asks 'what's a creative/unconventional angle', 'how do we stand out', 'should we run a test/experiment', 'how do we know what people actually want', or is about to trust a survey/focus group. Covers deliberate inversion of the obvious move, why stated preferences lie, and designing small reversible experiments that watch behaviour. Inspired by Rory Sutherland's *Alchemy*. Routed to from psycho-logic. 日本語の相談（「競合と同じ案しか出ない」「アンケートは好評なのに売れない」「思い切った案を安く試したい」）にも使う。中文咨询（“只能想出和竞品一样的方案”“问卷好评却卖不动”）也适用。

中文简介正在准备中。当前显示原文说明。

审查REA的CI与测试集，验证是否存在漏报缺陷的判定或测试数据偏差，并依据实际测量结果，在保留必要缺陷检测能力的前提下评估运行成本。

• 调查漏报缺陷的CI判定
• 核对测试数据与当前规范的差异
• 测量缓慢测试集中的无效开销