Loading...
Loading...
Found 103 Skills
This skill should be used when users want to run any workload on Hugging Face Jobs infrastructure. Covers UV scripts, Docker-based jobs, hardware selection, cost estimation, authentication with tokens, secrets management, timeout configuration, and result persistence. Designed for general-purpose compute workloads including data processing, inference, experiments, batch jobs, and any Python-based tasks. Should be invoked for tasks involving cloud compute, GPU workloads, or when users mention running jobs on Hugging Face infrastructure without local setup.
Salesforce Flex Credit estimation for Agentforce and Data Cloud workloads. TRIGGER when: user needs cost projections, scenario planning, budget sizing, or architecture tradeoff analysis for Agentforce prompts/actions, Data Cloud meters, or monthly Flex Credit usage. DO NOT TRIGGER when: user is building Agentforce metadata or .agent files themselves (use sf-ai-agentforce or sf-ai-agentscript), implementing Data Cloud assets (use sf-datacloud-*), or asking for contract-specific commercial approval that depends on non-public pricing terms.
T-SQL query optimization techniques for SQL Server and Azure SQL Database. Use this skill when: (1) User needs to optimize slow queries, (2) User asks about SARGability or index seeks, (3) User needs help with query hints, (4) User has parameter sniffing issues, (5) User needs to understand execution plans, (6) User asks about statistics and cardinality estimation.
Daily compression of time-series data with merge logic for multiple pipeline runs, structured aggregation for dashboards, and storage estimation for capacity planning.
Use when making high-stakes decisions under uncertainty that require stakeholder buy-in. Invoke when evaluating strategic options (build vs buy, market entry, resource allocation), quantifying tradeoffs with uncertain outcomes, justifying investments with expected value analysis, pitching recommendations to decision-makers, or creating business cases with cost-benefit estimates. Use when user mentions "should we", "ROI analysis", "make a case for", "evaluate options", "expected value", "justify decision", or needs to combine estimation, decision analysis, and persuasive communication.
Use when estimating time, effort, or complexity for features or projects - provides structured estimation workflows with breakdowns, risks, and confidence intervals.
Production-ready RNA-seq differential expression analysis using PyDESeq2. Performs DESeq2 normalization, dispersion estimation, Wald testing, LFC shrinkage, and result filtering. Handles multi-factor designs, multiple contrasts, batch effects, and integrates with gene enrichment (gseapy) and ToolUniverse annotation tools (UniProt, Ensembl, OpenTargets). Supports CSV/TSV/H5AD input formats and any organism. Use when analyzing RNA-seq count matrices, identifying DEGs, performing differential expression with statistical rigor, or answering questions about gene expression changes.
MANDATORY before starting any task. Enforces the GPA execution loop that prevents tool call sprawl. G: GATHER phase combines discover queries + memory reads + file reads into one phase. P: Plan in text with zero tool calls. A: APPLY all writes/edits/verification in one phase. One call per tool type per phase — batch all same-type operations together. Covers dependency analysis, batch opportunities, scope estimation, and loop-back triggers.
Estimate fair market rates for creator partnerships based on platform, follower count, engagement rate, niche, and deliverable type. This skill should be used when estimating influencer rates, calculating creator pricing, building a rate card for a campaign, checking if a creator's rate is fair, comparing influencer costs across platforms, budgeting for a creator campaign, evaluating a creator's rate card, figuring out how much to pay an influencer, benchmarking creator rates against market data, or assessing whether a creator is overcharging. For negotiating rates after estimation, see rate-negotiation-playbook. For full creator vetting beyond pricing, see creator-vetting-scorecard.
Use this skill when writing user stories, defining acceptance criteria, story mapping, grooming backlogs, or estimating work. Triggers on user stories, acceptance criteria, story mapping, backlog grooming, estimation, story points, INVEST criteria, and any task requiring agile requirements documentation.
This skill should be used when the user asks about 'TRON energy', 'TRON bandwidth', 'how much energy do I need', 'energy cost on TRON', 'bandwidth insufficient', 'resource delegation on TRON', 'rent energy on TRON', 'TRON transaction fee', 'why is my TRON transaction expensive', 'optimize TRON costs', or mentions Energy, Bandwidth, resource management, fee estimation, or cost optimization on the TRON network. This is a TRON-specific concept with no direct equivalent on EVM chains. Do NOT use for staking/voting — use tron-staking. Do NOT use for balance queries — use tron-wallet.
Apply statistical methods to financial data including descriptive statistics, covariance estimation, regression, hypothesis testing, and resampling. Use when the user asks about return distributions, correlation between assets, building a covariance matrix, running a CAPM regression, testing whether alpha is significant, checking if returns are normal, or estimating confidence intervals. Also trigger when users mention 'volatility', 'how correlated are these', 'fat tails', 'skewness', 'R-squared', 'beta of a fund', 'bootstrap a Sharpe ratio', 'shrinkage estimator', 'Ledoit-Wolf', or ask why their optimizer produces unstable weights.