584 个 · 按相关度排序
Run repeated code improvement experiments with multiple agents. It plans and reviews candidate changes, compares benchmark results, merges candidates that pass rechecking, and records progress until a target, iteration limit, or another stopping condition is reached.
中文简介正在准备中。当前显示英语简介。
Investigate how transformer language models produce predictions with TransformerLens. This skill guides inspection of intermediate values and attention patterns, plus experiments that replace internal values to test their effects and identify components involved in model behavior.
中文简介正在准备中。当前显示英语简介。
Investigate why a PyTorch model behaves a certain way by changing its internal values with pyvene. The skill guides experiments that swap or remove activations, train interventions, compare outputs, and save or share intervention configurations.
中文简介正在准备中。当前显示英语简介。
Use TensorBoard to visualize training loss and accuracy, compare experiments, and inspect model structure. Includes PyTorch and TensorFlow logging examples for examining weight distributions, predictions, and performance bottlenecks during machine learning training.
中文简介正在准备中。当前显示英语简介。
Improve the experience after signup by identifying where new users drop off and helping them reach their first useful result. Develop setup flows, checklists, guidance, email triggers, and prioritized experiments based on activation metrics.
中文简介正在准备中。当前显示英语简介。
Plan controlled failure experiments to uncover system weaknesses. Define normal operating metrics, estimate affected users and reliability risk, set abort and recovery conditions, and turn experiment results into a structured review with follow-up actions.
中文简介正在准备中。当前显示英语简介。
Create and refine Jupyter notebooks for experiments, exploratory analysis, or tutorials. Bundled templates help organize runnable code and short explanations into clear steps, while validation guidance supports notebooks that others can read and rerun.
中文简介正在准备中。当前显示英语简介。
Build a product strategy across nine connected areas, including vision, target markets, customer value, growth, and competitive advantages. Clarify priorities, work to exclude, success metrics, and assumptions, then propose small experiments to test the strategy.
中文简介正在准备中。当前显示英语简介。
Design product pricing based on customer value, competitor offerings, and willingness to pay. Compare charging models, define plan tiers and included features, and outline experiments to test prices and assumptions before introducing a new pricing structure.
中文简介正在准备中。当前显示英语简介。
Analyze users grouped by signup period or another shared characteristic to compare retention and feature adoption over time. Produce charts, highlight unusual changes, and recommend follow-up research or experiments to investigate the patterns.
中文简介正在准备中。当前显示英语简介。
Improve a measurable target in a working system by tracing workload costs or scoring alternative implementations. Compare results against a baseline, keep confirmed improvements on a dedicated branch, and record experiments for review or resumption.
中文简介正在准备中。当前显示英语简介。
Inventory feature flags, switches that control feature availability, and remove eligible flags with their unused code branches. Leave ongoing rollouts and experiments untouched, run verification checks, and prepare a pull request for human review.
中文简介正在准备中。当前显示英语简介。
Reviews research ideas, papers, and experimental results through repeated critical discussion. Identifies unsupported claims, missing experiments, and weaknesses in the paper’s story, then records agreed conclusions, evidence requirements, and prioritized improvements in a review document.
中文简介正在准备中。当前显示英语简介。
Plan and run ablation studies, experiments that remove or replace parts of a method to test their contribution. Organize reviewer questions, priorities, expected outcomes, and compute costs, then record results and findings.
中文简介正在准备中。当前显示英语简介。
Develop a vague research approach into a concrete method proposal through repeated Gemini reviews. Keep the original problem and constraints in focus while specifying implementation details, removing unnecessary components, and outlining the minimum experiments needed to test the claims.
中文简介正在准备中。当前显示英语简介。
Turn a broad research direction into ranked ideas, a refined proposal, and an experiment plan. The workflow combines literature searches, novelty checks, small pilot experiments, and Gemini review to assess evidence and identify useful next steps.
中文简介正在准备中。当前显示英语简介。
Turn a rough research approach into a focused plan with concrete implementation details and a small set of validation experiments. Repeated Claude reviews help refine the method while keeping the original problem and resource constraints in view.
中文简介正在准备中。当前显示英语简介。
Get critical feedback from Claude on research ideas, papers, and experimental results. Through multiple review rounds, identify unsupported claims, missing experiments, and narrative weaknesses, then document agreed conclusions and a prioritized improvement plan.
中文简介正在准备中。当前显示英语简介。
Improve research through repeated Gemini reviews, code changes, experiments, and analysis. The workflow records full feedback and actions, then stops when both the score and readiness criteria are met or the round limit is reached.
中文简介正在准备中。当前显示英语简介。
Turn a vague research approach into a concrete method proposal with focused contributions and minimal validation experiments. Ground the plan in relevant papers, then refine it through GPT-6-Astra reviews while preserving the original problem and resource constraints.
中文简介正在准备中。当前显示英语简介。
Have Gemini critically review research developed with Codex. Multiple rounds of discussion examine logical gaps, missing experiments, and narrative weaknesses, then turn the findings into experiment plans, paper outlines, and documented research priorities.
中文简介正在准备中。当前显示英语简介。
Prepare a polished paper for a different venue by addressing prior reviewer concerns through limited text edits. Adapt formatting, check page limits and anonymity, and preserve earlier submissions without adding experiments or changing the bibliography.
中文简介正在准备中。当前显示英语简介。
Get critical feedback on research ideas, papers, and experimental results from an external AI reviewer. Repeated discussions help identify unsupported claims, plan missing experiments, and document agreed improvements with priorities and estimated computing costs.
中文简介正在准备中。当前显示英语简介。
Audit research experiments before using their results to support claims. An independent model checks reference data, metric calculations, result files, and evaluation scope, producing reports with evidence, findings, and specific actions to address concerns.
中文简介正在准备中。当前显示英语简介。