296 skills · sorted by relevance
Research topics across multiple sources, cross-check findings, and verify source URLs before producing a report with confidence labels. Choose from quick lookups to iterative investigations that preserve findings, with community sources prioritized for questions about public reactions.
Apply over 240 reusable prompt templates to summarize content, extract insights, improve writing, review code, or analyze security threats. It reads each template directly and returns results in the format defined for that task.
Extract useful ideas from videos, podcasts, interviews, and articles, organized into sections tailored to the content. Choose from five depth levels, preserving surprising claims and, at fuller levels, getting essential takeaways and references to explore.
Clarify implementation choices before planning a development phase. The skill reviews existing project context and code, asks about unresolved decisions, and records the answers in a context file for research and planning agents.
Build and update a study plan for bar exams or law school courses. Allocate time around weak subjects, available hours, and rest days, then adjust upcoming sessions using recorded practice results and progress.
Implement polling, or repeated data checks, that slows down after failures and returns to its normal interval after success. The TypeScript pattern also pauses hidden tabs, staggers overdue refreshes, and manages multiple update tasks independently.
Produce audio in separate stems, meaning individual instrument tracks, and verify each output as you go. Align track lengths with silence, loops, or crossfades, then apply effects, mix a master, and package the files.
Guide a team through questions about users, workflows, and priorities to create a user story map. Organize activities and tasks, then define a minimum viable product and later releases that each cover the full workflow.
Prepare for a senior product leadership role or work through challenges after taking one. Adaptive questions identify your transition stage and produce targeted recommendations on organizational leadership, executive relationships, role evaluation, and communicating business outcomes.
Guide a workshop that maps a specific customer’s experience from start to finish. Capture stages, actions, thoughts, emotions, and pain points, then produce a customer journey map and a prioritized list of improvement opportunities.
Use three adaptive questions to identify where product growth is stuck. The skill recommends a path through new customer segments, geographies, distribution channels, or products, then suggests a low-cost first experiment and a common trap to watch for.
Turn a competitive or market question into a focused research approach through three adaptive questions. Get recommendations for information sources, review frequency, and executing skills, with reasons tailored to the decision and available time.
Work through up to five adaptive questions to clarify your product’s customers, unmet needs, category, benefits, and competitive differences. Turn the answers and supporting evidence into a positioning statement and a concise summary for stakeholder review.
Plan and implement features with a workflow that adapts to their complexity. It connects testable requirements to tasks, tests, and small commits, then checks the finished work against the specification through an independent verification pass.
Measure and improve Three.js or WebGL game performance through repeatable gameplay checks. Identify CPU or GPU bottlenecks, reduce unnecessary rendering and processing, and verify that controls, collisions, visuals, and memory remain stable.
Review SwiftUI projects for outdated APIs, data flow, layout, accessibility, and performance issues. Get findings organized by file, with brief before-and-after code examples and a prioritized summary of the changes that matter most.
Adapt Squad agent coordination to the available Copilot interface. Detect supported tools, choose how to launch helper agents and collect results, and use file-based state for workflows that must work across interfaces.
Assess study quality and risk of bias, meaning systematic distortions in research results. Choose assessment tools suited to the study and review purpose, document judgment rationales, and summarize evidence certainty and recommendations for use in further analysis.
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.
The English summary is being prepared. Showing the original description.
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.
The English summary is being prepared. Showing the original description.
Design experiments and studies BEFORE data is collected — choosing a design, randomizing, blocking, and laying out treatment combinations so the results will actually be interpretable. Use whenever someone is planning a study, asks how to assign subjects/samples to groups, mentions randomization, blocking, stratification, controls, factorial or fractional-factorial designs, design of experiments (DOE), screening many factors, response-surface optimization, crossover or repeated-measures or split-plot designs, cluster/group randomization, Latin squares, plate layouts, batch/run-order effects, replication vs. pseudoreplication, or sequential/adaptive/group-sequential designs. Trigger this even for informal phrasings like "how should I set up this experiment", "how do I avoid confounding", "what's the best way to test these 6 factors", or "assign these mice to conditions". For computing the sample size or power once the design is chosen, use statistical-power; for analyzing data already collected, use statistical-analysis.
The English summary is being prepared. Showing the original description.
Deep research with hyperresearch, for Claude Code and OpenAI Codex. Use when the user asks for deep research, a research report, a literature review, or a multi-source analysis with verified citations. Checks that the hyperresearch CLI is installed, sets it up in the current project for the agent you are running in, then hands off to the hyperresearch pipeline (a tier-adaptive 16-step pipeline with a persistent source vault). Not for quick lookups one or two searches can answer.
The English summary is being prepared. Showing the original description.
Use this skill when NeMo Relay is installed or imported but application-side runtime behavior is missing or incorrect, including load failures, inactive scopes, missing events, and plugin or adaptive wiring problems.
The English summary is being prepared. Showing the original description.
Gather phase context through adaptive questioning before planning. Use --all to skip area selection and discuss all gray areas interactively. Use --auto to skip interactive questions (Claude picks recommended defaults). Use --chain for interactive discuss followed by automatic plan+execute. Use --power for bulk question generation into a file-based UI (answer at your own pace).
The English summary is being prepared. Showing the original description.