9K skills · sorted by popularity
Guide GAIA benchmark runs from environment checks and cost estimates to result comparison. Create a signed submission package compatible with HAL, including agent traces, metadata, and an audit report that checks for benchmark exploitation.
Compare models available through the HuggingFace router with chat-ui configuration, research missing models, and write short English descriptions of their architecture and capabilities. Add entries to both production and development configuration files and commit the changes.
Calculate portfolio weights from a covariance matrix, which describes how asset returns move together, and expected returns using Conjugate Gradient. Save the weights with the solver used, numerical error, and timing so the calculation can be checked later.
Manage stored agent memories for backups, project transfers, and team knowledge sharing. Work with RVF, a portable memory format, to export and import records, upgrade formats, inspect storage statistics, and transfer patterns between local projects.
Test trading strategies against historical market data and collect performance metrics. The skill checks whether data is real or synthetic and can digitally sign results to help detect tampering before a strategy moves into live trading.
Generate RuVLLM settings for local language model inference and create MicroLoRA or SONA instances. Adjust their small internal weights using quality scores as feedback, with instances held in server memory for subsequent adaptation calls.
Store useful patterns and solutions in AgentDB, then find them through semantic search, which matches meaning rather than exact wording. Use saved knowledge before starting work and record successful approaches and new lessons afterward.
Import Claude Code auto-memory into AgentDB and search past notes by meaning across sessions and projects. The skill checks import status, consolidates near-duplicate entries, and returns search results with their memory sources identified.
Find stored Ruflo memories by meaning, keywords, or an optional ranking method. Search across storage groups, retrieve past solutions and task context, and see which search method actually ran, including any fallback.
Represent dependency trees, taxonomies, and other hierarchies inside a Poincare ball, a geometric model for hierarchical distances. Use tree depth for radius and text embeddings for direction, then measure distances to examine the encoded structure.
Compare ruflo and HAL systems for running the GAIA benchmark, an AI evaluation. Examine differences in code execution, browsing, file handling, memory, and model selection to prioritize improvements by expected impact and effort.
Convert text, code, or documents into 384-dimensional vectors, numerical representations used for meaning-based search, similarity comparison, and clustering. Save vectors to files, check their dimensions and magnitude, and optionally record metadata in AgentDB.
Classify market conditions as bullish, bearish, ranging, or volatile to guide strategy selection and historical testing. Distinguish synthetic demonstrations from analysis of actual price data, with confidence levels and historical comparisons where available.
Find candlestick and chart patterns in previously ingested market data. Classify detections by reversal or continuation, bullish or bearish direction, and reliability score, then rank and store them for later reference.
Experiment with the policies that govern an AI agent, such as planning, memory, and tool use. Test one policy change per variant in a sandbox, an isolated environment, and promote only candidates with measured improvements.
Send proofs, planning questions, or difficult debugging tasks to DeepSeek's reasoning model. Receive the final answer and model-provided reasoning text in separate fields, with token usage reported for reviewing responses and costs.
Send a single request to DeepSeek for summarization, information extraction, or simple classification. Receive the response and token usage as JSON for further processing, with structured status information when the API is unavailable.
Prepare market history for pattern detection and comparison. Import opening, high, low, and closing prices plus volume, validate and normalize the values, then store them by symbol and date for later retrieval. It does not place orders.
Capture token usage from Claude Code session logs, calculate USD costs using the supplied pricing reference, and save structured records to AgentDB. Review totals by model and tier, and provide data for cost reports.
Define reusable reasoning and decision patterns for agents, embed them in executable workflows, and review their performance. Share successful approaches, including conditional decision trees, stepwise problem solving, analogies, and evaluation from multiple perspectives.
Evaluate and improve the policy instructions that guide an AI agent using scored coding tasks. Run a learning cycle to compare candidates, or use the default dry run to inspect tasks and estimated costs without model calls.
Choose an agent and model tier using the task description and learned patterns. The skill can explain its recommendation, use compiler-based edits for supported simple changes, and record task outcomes to inform future routing decisions.
Inspect evolved prompt configurations, validate their structure, and view the system prompts they produce. You can also classify failures in run transcripts to support reviews before adopting or changing an agent policy.
Create agents that learn from interactions and adapt their behavior over time. Monitor learning progress, review efficiency and accuracy metrics, trigger adjustments from feedback, and share acquired knowledge with other agents through dedicated tools.