Loading...
Loading...
Found 10,272 Skills
Scans Substrate/Polkadot pallets for 7 critical vulnerabilities including arithmetic overflow, panic DoS, incorrect weights, and bad origin checks. Use when auditing Substrate runtimes or FRAME pallets.
Provides guidance for interpreting and manipulating neural network internals using nnsight with optional NDIF remote execution. Use when needing to run interpretability experiments on massive models (70B+) without local GPU resources, or when working with any PyTorch architecture.
Guides annual goal-setting and execution with a systematic framework. Applies when planning the year, breaking down ambitious goals into daily systems, running monthly check-ins, or using the ABC System for consistent habit execution.
Calculate readability scores (Flesch-Kincaid, Gunning Fog, SMOG) and grade levels for text. Analyze writing complexity and get improvement suggestions.
Longitudinal memory tracking, philosophy teaching, and personal accountability with compassion. Expert in pattern recognition, Stoicism/Buddhism, and growth guidance. Activate on 'accountability', 'philosophy', 'Stoicism', 'Buddhism', 'personal growth', 'commitment tracking', 'wisdom teaching'. NOT for therapy or mental health treatment (refer to professionals), crisis intervention, or replacing professional coaching credentials.
Design protein sequences using ProteinMPNN inverse folding. Use this skill when: (1) Designing sequences for RFdiffusion backbones, (2) Redesigning existing protein sequences, (3) Fixing specific residues while designing others, (4) Optimizing sequences for expression or stability, (5) Multi-state or negative design. For backbone generation, use rfdiffusion or bindcraft. For ligand-aware design, use ligandmpnn. For solubility optimization, use solublempnn.
ESM2 protein language model for embeddings and sequence scoring. Use this skill when: (1) Computing pseudo-log-likelihood (PLL) scores, (2) Getting protein embeddings for clustering, (3) Filtering designs by sequence plausibility, (4) Zero-shot variant effect prediction, (5) Analyzing sequence-function relationships. For structure prediction, use chai or boltz. For QC thresholds, use protein-qc.
Accept Bitcoin payments with PayRam's self-hosted infrastructure. Unique mobile app signing flow for BTC transactions without server-side key exposure. HD wallet derivation for unlimited unique deposit addresses. Manual sweep approval via PayRam Merchant mobile app. Use when accepting Bitcoin payments, implementing BTC payment flows, needing self-custody Bitcoin infrastructure, or building Bitcoin payment acceptance without Lightning complexity.
Project Intake & Charter: transform an ambiguous project request into a clear, structured project foundation for consulting engagements. Use when a project is in the **Initiation** phase or when a PM needs to clarify objectives, scope, stakeholders, assumptions, initial risks and open questions without performing detailed planning or estimations.
Prometheus, Grafana, CloudWatch, Azure Monitor, Stackdriver, logging, alerting, and SRE practices
Automate Cabinpanda tasks via Rube MCP (Composio). Always search tools first for current schemas.
Automate Fitbit tasks via Rube MCP (Composio). Always search tools first for current schemas.