713 个 · 按相关度排序
Review consequential or ambiguous decisions through ten stages of structured reflection. Separate observations from assumptions, examine alternatives and risks, and produce a recommendation supported by evidence, with verification needs and conditions for revisiting the decision.
中文简介正在准备中。当前显示英语简介。
Explore computer science and AI research directions using eight creativity frameworks. Combine ideas across fields, question hidden assumptions, and transfer mechanisms from other disciplines to develop research questions with testable predictions.
中文简介正在准备中。当前显示英语简介。
Fine-tune language models with TRL using GRPO, a method that compares scored responses to the same prompt. Covers training data, scoring functions, GPU-conscious settings, and monitoring for tasks with measurable correctness or required output formats.
中文简介正在准备中。当前显示英语简介。
Examine important choices and assess claims by rebuilding their reasoning from basic knowledge. Use mental models, reusable ways to understand problems, to compare conclusions, identify unknowns, and consider long-term consequences.
中文简介正在准备中。当前显示英语简介。
Compare technology options, review a system design, or plan a new component from requirements and constraints. The skill organizes the reasoning into an architecture decision record, a document covering alternatives, trade-offs, consequences, and next steps.
中文简介正在准备中。当前显示英语简介。
Review a product launch against the team's legal framework and risk standards. Produce a category-by-category memo with required actions, owners, and deadlines, plus a separate tracker comment that omits internal legal reasoning.
中文简介正在准备中。当前显示英语简介。
Helps an agent take over an existing role after a planned handover. It guides checks of inherited records, identity, authority, and recurring duties, while explaining how to recover the predecessor’s reasoning and preserve lessons for the next agent.
中文简介正在准备中。当前显示英语简介。
Pin the current parent thread to a chosen AI model through Weave Router while subagents keep automatic model selection. An optional effort setting controls the model's reasoning effort.
中文简介正在准备中。当前显示英语简介。
Investigate a Codex CLI session by matching its local conversation record with production router logs. Use the session ID to examine missing reasoning summaries, routing markers, unexpected models, or unusual tool calls and trace relevant code paths.
中文简介正在准备中。当前显示英语简介。
Design, debug, and tune OpenRouter API integrations. It checks model capabilities, reasoning settings, output limits, and fallback routes, then validates results against quality, cost, privacy, and performance requirements, including failed attempts.
中文简介正在准备中。当前显示英语简介。
Run basic engineering checks for NV-Reason-CXR using chest X-ray images or test fixtures. Test commands with mock responses or run the model locally or through a public API, then inspect JSON results. Not for clinical use.
中文简介正在准备中。当前显示英语简介。
Run inference on Fireworks AI — direct, through the Leanmcp AI Gateway proxy (aigateway.leanmcp.com) for observability, or via LiteLLM / the OpenAI SDK / raw HTTP. Covers the endpoint-and-key matrix for each route, serverless vs dedicated deployments and their cold starts, browsing and filtering the model catalogue, reasoning models that return content:null with the answer in reasoning_content, function calling, concurrency and load testing, and runner scripts where many models share one protocol with a --use-proxy toggle. Use this skill whenever the user mentions Fireworks, FIREWORKS_API_KEY, api.fireworks.ai, fireworks_ai/ model ids, accounts/fireworks/models/..., a Fireworks deployment id, the Leanmcp gateway or LEANMCP_API_KEY, app.leanmcp.com observability, or gpt-oss / kimi / glm / qwen / deepseek served on Fireworks; wants to route LLM calls through a proxy for logging or cost tracking; is debugging empty responses, 404s, scope errors, cold starts, or "the gateway isn't working"; wants to pick a Fireworks model with tool calling; or wants to sweep several models over one benchmark. Reach for it even on vague asks like "why is this model returning nothing" or "set up inference for these models" when Fireworks is in play.
中文简介正在准备中。当前显示原文说明。
Apply general knowledge reasoning across diverse domains — trivia, commonsense inference, analogy, and factual question answering.
中文简介正在准备中。当前显示原文说明。
Perform closed-book frontier reasoning — complex problem solving from internalized knowledge without external retrieval or tool use.
中文简介正在准备中。当前显示原文说明。
Applies cognitive science frameworks for creative thinking to CS and AI research ideation. Use when seeking genuinely novel research directions by leveraging combinatorial creativity, analogical reasoning, constraint manipulation, and other empirically grounded creative strategies.
中文简介正在准备中。当前显示原文说明。
Generate a complete marketing campaign brief from a launch goal, ICP, and product context. Pure reasoning skill. Outputs channel plan, messaging angles, content types, timeline, and success metrics. Designed for seed/Series A founders and small GTM teams who aren't professional marketers but need to run focused campaigns. No scripts — pure reasoning.
中文简介正在准备中。当前显示原文说明。
Assesses a legal argument, submission, or piece of structured reasoning from the perspective of a judge reading it cold under time pressure. Produces a structured seven-part assessment: what the case appears to be about, immediate points of confusion, what feels strong, what feels weak, what is assumed but unproved, a provisional confidence level (low/medium/high), and what would be needed to persuade. The skill does not rewrite, improve, or attack the argument — it tells you how it actually lands on a sceptical, experienced reader with no prior context. Works on skeleton arguments, witness statements, letters before action, position statements, academic articles, and non-legal structured reasoning.
中文简介正在准备中。当前显示原文说明。
Implement ReasoningBank adaptive learning with AgentDB's 150x faster vector database. Includes trajectory tracking, verdict judgment, memory distillation, and pattern recognition. Use when building self-learning agents, optimizing decision-making, or implementing experience replay systems.
中文简介正在准备中。当前显示原文说明。
Implement adaptive learning with ReasoningBank for pattern recognition, strategy optimization, and continuous improvement. Use when building self-learning agents, optimizing workflows, or implementing meta-cognitive systems.
中文简介正在准备中。当前显示原文说明。
Search past reasoning for relevant decisions and approaches
中文简介正在准备中。当前显示原文说明。
Decision rubric for when an LM agent should write-and-run code (Program-of-Thought / code interpreter) versus reason in natural language: classify each step as deterministic- computable (emit + execute code, feed the result back) vs judgment (stay in prose). Use when designing or debugging an agent step that does arithmetic/parsing/data transforms, when prose reasoning hallucinates a computation (under-coding), or when a sandbox round- trip is wasted on a judgment task (over-coding). Search keywords: code interpreter, agent does math wrong, calculator hallucination, when to run code vs reason, program of thought, PoT, tool vs reasoning.
中文简介正在准备中。当前显示原文说明。
Implement ReasoningBank adaptive learning with AgentDB's 150x faster vector database. Includes trajectory tracking, verdict judgment, memory distillation, and pattern recognition. Use when building self-learning agents, optimizing decision-making, or implementing experience replay systems.
中文简介正在准备中。当前显示原文说明。
Implement adaptive learning with ReasoningBank for pattern recognition, strategy optimization, and continuous improvement. Use when building self-learning agents, optimizing workflows, or implementing meta-cognitive systems.
中文简介正在准备中。当前显示原文说明。
Implement ReasoningBank adaptive learning with AgentDB's 150x faster vector database. Includes trajectory tracking, verdict judgment, memory distillation, and pattern recognition. Use when building self-learning agents, optimizing decision-making, or implementing experience replay systems.
中文简介正在准备中。当前显示原文说明。