AI & ML

samraddhashrivastavatech Skill

android_multi_device

samraddhashrivastavatech Skill

academic-research

samraddhashrivastavatech Skill

document-research

samraddhashrivastavatech Skill

literature-review

samraddhashrivastavatech Skill

claim-verification

samraddhashrivastavatech Skill

community-research

samraddhashrivastavatech Skill

error-investigation

tristan-hauber Bundle

Periodically audit each agent's notes file for size, clarity, repetition; surface skill candidates and reference-doc splits. Recommend only.

tristan-hauber Bundle

Cross-agent adversarial review of an agent skill for operational correctness, algorithmic effectiveness, scope, cost, safety, self-containedness, and demonstrated behaviour where static inspection is insufficient.

orcaqubits Skill

Expose NLWeb as an MCP (Model Context Protocol) server — JSON-RPC 2.0 endpoint at /mcp, the `ask` / `list_sites` / `who` tools, protocol revision negotiation, and integration with ChatGPT, Claude, Gemini, and other agent clients. Use when wiring NLWeb to an AI agent via MCP or building an MCP client that consumes an NLWeb site.

orcaqubits Skill

Secure Saleor applications — JWT authentication, OIDC integration, App tokens, permission model, rate limiting, CORS, and security headers. Use when configuring Saleor security.

orcaqubits Skill

Navigate Spree's canonical data model — the Catalog (Product/Variant/OptionType/Taxon/Property/Metafield), Pricing (Price/PriceList), Order graph (Order/LineItem/Adjustment/Shipment/Payment/PaymentSession/Refund/Reimbursement), Inventory (StockLocation/StockItem/StockMovement), Shipping (ShippingMethod/Zone), Promotions, Identity (User/Role/Address/StoreCredit/GiftCard), Taxes, and the v5.4+ Markets + Store multi-region model. Use when designing a feature that touches Spree models, writing decorators, or building admin/storefront UIs.

belazy167 Bundle

Use when asked to build, extend or debug a Claude Mod, a Claude Code plugin with function hooks (a hooks module, register(on), hooks shaped ($, e, next), events like tool.call, prompt.submit, ui.render), or when a hooks module loads but its hook never fires.

arcturus-labs Bundle

Retrieve Artificial Analysis model data and update per-company and combined cost-versus-quality Pareto frontiers, including API-key setup, reports and charts, and optional Pi or Oh My Pi model configuration.

arcturus-labs Skill

Prepare portable public updates to existing skills from JnBrymn/agent-skills, removing private and local information and requiring John's review before committing. Use for selective public-skill synchronization.

raven Bundle

Guide for the C -fbounds-safety language extension. Covers the language model, pointer annotations, adopting bounds-safety in existing C code, compiler build settings and modes, and runtime debugging of bounds violations.

tristan-hauber Bundle

Surface regressions, process slips, and agent execution mistakes from git history and the shared workflow-improvement store; recommend only.

orcaqubits Skill

Configure Spree for multi-store and multi-region commerce — one Rails install running many `Store` records, the v5.4+ `Market` model (currency + locale + payment methods + shipping per region), what's shared vs per-store (products+inventory+customers shared; orders+payments+themes per-store), the Marketplace module (Enterprise — vendors/commission/payouts via Stripe Connect), and the Multi-tenant SaaS model. Use when planning a multi-brand or multi-region Spree deployment.

learningmatter-mit Bundle

Fine-tune MatGL machine learning interatomic potentials on custom datasets.

learningmatter-mit Bundle

Benchmark MLIP accuracy against a labeled dataset — compute MAE/RMSE for energy/atom and forces, and generate parity plots.

learningmatter-mit Bundle

GPU-accelerated batched inference for MACE, MatGL (TensorNet/M3GNet/CHGNet), and FairChem MLIPs using NValchemi, enabling parallel static, relax, and MD workflows across multiple structures simultaneously.

orcaqubits Skill

Implement AP2 as an A2A extension — mandate DataParts in A2A messages, Agent Card AP2 capabilities, payment-specific task flows, and inter-agent payment communication. Use when integrating AP2 payment capabilities into A2A multi-agent systems.

orcaqubits Skill

Build an AP2 Merchant Agent — the seller-side agent that receives intent mandates, searches product catalogs, creates signed cart mandates, and represents the merchant in agentic transactions. Use when implementing the Merchant Endpoint role.

orcaqubits Skill

Build an AP2 Shopping Agent — the main orchestrator that handles user requests, creates mandates, coordinates with merchants and credentials providers, and manages the transaction flow. Use when implementing the Shopping Agent role.

orcaqubits Skill

Customize NLWeb's LLM prompts and per-Schema.org-type behavior via `prompts.xml` and `tools.xml` — covers the `<promptString>` template format, `<returnStruc>` JSON schemas, prompt inheritance, decontextualization/ranking/generate templates, per-site overrides, and pitfalls of editing prompts in place. Use when tuning answer quality, supporting a new domain, or localizing prompts.

orcaqubits Skill

Build an AP2 Credentials Provider — the agent that manages payment credentials, provides payment methods to users, handles tokenization (DPAN), and facilitates secure payment between Shopping Agent and Payment Processor. Use when implementing the Credentials Provider role.

learningmatter-mit Bundle

Generate novel crystal structures and molecules using ADiT (All-atom Diffusion Transformer), a unified latent diffusion model.

learningmatter-mit Bundle

Benchmark of inference speed of Machine Learning Interatomic Potentials (MLIPs).

learningmatter-mit Skill

Automate hyperparameter tuning for MLIPs (MACE, MatGL, FairChem) using an LLM-driven search framework.

orcaqubits Skill

Implement the AP2 human-not-present transaction flow — autonomous agent shopping with Intent Mandate authorization, constraint enforcement, and merchant escalation. Use when building autonomous agent purchasing that works after the user has left.

vulnerscom Bundle

Use when modifying, testing, documenting, or reviewing the Vulners Python SDK. Covers the v4 architecture (typed sync/async clients, resource namespaces, bulletin model hierarchy, unasync codegen), the preserved legacy v3 surface, uv-based tooling, the 100% branch-coverage gate, safe API-key handling, and defensive vulnerability-intelligence examples.

nelchandler Bundle

Operations Research and simulation engineering agent. Designs, codes, verifies, validates and runs stochastic simulation models — discrete-event (simpy), agent-based (mesa), system dynamics, Markov/Bayesian — following a strict 8-step simulation lifecycle with statistical rigor: distribution fitting, Welch warm-up, replication counts from a target confidence interval, variance reduction, ANOVA across scenarios. Use whenever the user wants to simulate, model or size anything stochastic — queues, capacity, staffing, throughput, lead times, inventory, risk or "what are the odds" questions, load models, agent populations, sensitivity sweeps, what-if scenarios. Use it when the user types START and expects the OR workflow. Use it too when simulation code is slow, noisy, non-reproducible or producing numbers nobody trusts — including when you merely see simpy, mesa, np.random, random.seed, a replication loop or a results-averaging script and the word "simulation" is never spoken.

nelchandler Bundle

Lean Six Sigma Master Black Belt and continuous improvement agent. Runs DMAIC — Define, Measure, Analyze, Improve, Control — as a gated state machine with statistical rigor: process capability (Cp, Cpk, Pp, Ppk, DPMO, sigma level, rolled throughput yield), measurement system analysis, SPC control charts (X-bar/R, I-MR, p, c, u) with Nelson rules separating common from special cause, hypothesis testing to prove root causes rather than guess them, DOE, and control plans that hold the gains. Use whenever the user wants to improve, optimize, stabilize or de-bottleneck a process — defect rates, cycle time, lead time, throughput, rework, yield, deployment failure rate, incident volume, variation, waste. Use it when the user types START and expects the DMAIC workflow. Use it too when someone asks why a process got worse, whether a change helped, or what the root cause is — and when you merely see defect counts, cycle-time logs, a before/after comparison or a run of measurements someone is eyeballing for trends.

learningmatter-mit Skill

Real-time monitoring tools for stability, equilibration, and diffusion during ASE molecular dynamics simulations.

learningmatter-mit Bundle

Fine-tune MACE machine learning interatomic potentials on custom datasets.

learningmatter-mit Bundle

Calculate ionic diffusion coefficients and activation energy from MD trajectories using pymatgen.