Loading...
Loading...
Found 516 Skills
Information collection and exploration before Spec creation. Invoked by the role spec-explorer. Trigger conditions: (1) The spec-explorer role needs to collect background information before Spec creation, (2) Need to retrieve historical experience (exp-search), (3) Need to explore the project codebase, external documents or third-party libraries, (4) TeamLead notifies the spec-explorer to start working.
Design exploration with parallel agents. Use when brainstorming ideas, exploring solutions, or comparing alternatives.
Explore-lane experimental execution skill for deep learning research repositories. Use when the researcher explicitly authorizes exploratory runs such as small-subset validation, short-cycle guess-and-check, batch sweeps, idle-GPU search, or quick transfer-learning trials, with results summarized in `explore_outputs/`. Do not use for end-to-end exploration orchestration on top of `current_research`, trusted baseline execution, conservative training verification, default routing, or implicit experimentation.
Conduct a targeted code exploration of the repository, and document the process of "Ask Questions → Read Code → Draw Conclusions" as searchable evidence for direct reuse when similar questions arise next time. There are three types: question (investigate code around a specific question and provide conclusions), module-overview (sort out the structure, boundaries, entry points, and dependencies of a module), and spike (conduct lightweight technical exploration of multiple possible directions without making final decisions). Trigger scenarios: Users say "Let's explore first", "How is X implemented in this repository", "Quickly get familiar with this module", "Archive the exploration results". Refer to `codestable/reference/system-overview.md` for how to distinguish it from learning / tricks / decisions.
Documents the results of a time-boxed technical or design exploration (spike). Use after completing a spike to capture learnings, findings, and recommendations for the team.
LLM fine-tuning with LoRA, QLoRA, and instruction tuning for domain adaptation.
Fast, low-cost exploration of Robonet trading resources. Browse 8 data tools to explore available trading pairs, technical indicators, Allora ML topics, existing strategies, and backtest results. All tools execute in <1 second with minimal cost (free to $0.001). Use this skill first before building or testing strategies to understand what resources are available.
Teaches learners to extract transferable design lessons from real-world codebases through critical evaluation and systematic exploration. Use when a learner wants to study existing code to learn patterns, architecture, or design decisions—not just understand what it does. Guides through navigation, pattern recognition, critical evaluation (deliberate choice vs. compromise), and lesson extraction. Triggers on phrases like "learn from this codebase", "study how X is implemented", "understand design patterns in Y", or when a learner wants to improve by reading real code.
Create algorithmic art using p5.js with seed-based randomness and interactive parameter exploration. Use this when users request to create art with code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art instead of copying existing artists' works to avoid copyright infringement.
Best practices for doing quick exploratory data analysis with minimal code and a Pandas .plot like API using HoloViews hvPlot.
Context-driven aesthetic exploration with anti-cliche validation: typography, color, animation, atmosphere. Use when starting a frontend needing distinctive aesthetics, refreshing generic designs, or auditing for "AI slop" patterns. Use for "distinctive frontend", "unique aesthetics", "avoid generic design", "creative frontend". Do NOT use for quick prototypes, strict brand compliance, backend projects, or data visualization.
EDA, dashboards, Matplotlib, Seaborn, Plotly, and BI tools. Use for creating visualizations, exploratory analysis, or dashboards.