AI & ML

aperivue Bundle

Batch download open-access PDFs by DOI using legitimate OA APIs (Unpaywall, PMC, OpenAlex, Crossref). Optional PDF→Markdown conversion for token-efficient LLM analysis.

aperivue Bundle

Design or audit the uncertainty-quantification, out-of-distribution (OOD) detection, and selective-prediction layer of a medical-imaging model framed for deployment — so a clinical-use claim carries calibrated per-case uncertainty (MC-dropout / deep ensemble / conformal / Bayesian), an OOD guard validated on a held-out OOD set, an abstention rule at a pre-specified operating point, and uncertainty checked under distribution shift. Emits an uncertainty manifest and a deterministic gate that flags a deployment claim built on point predictions, conformal intervals with unmeasured coverage, and an OOD claim with no held-out OOD data. Integrates MAPIE / captum / pretrained OOD scorers; it does not reimplement them and never runs a model on real patient data.

aperivue Bundle

Design and validity review for studies that benchmark one or more AI systems against a human-expert panel as the reference. Covers the evaluation question and arm definition, decoupled multi-dimensional rubrics with anchors, planted calibration probes, reviewer-panel construction, inter-rater reliability targets, LLM-as-judge versus human-as-judge adjudication, construct-independence guards, and a structured rating-export schema. Use before data collection on an AI-vs-expert evaluation.

nvidia-tao Bundle

NV-Tesseract AD Diffusion — diffusion-based anomaly detection and fine-tuning for multivariate time series. Use when the user asks to "fine-tune NV-Tesseract", "run AD diffusion inference", "detect anomalies with diffusion", "time series anomaly detection", "finetune ad-diffusion", "use perform_anomaly_analysis_with_diffusion", "automl ad-diffusion", "hyperparameter search ad-diffusion", "hyperparameter optimization" or mentions "curriculum_medium.yaml", "final_model.pth", "nv-tesseract-ad-diffusion", "ad_diffusion", or "TSDiffuser_Generic".

0xdarkmatter Bundle

Landing discipline for parallel work: sequential test-gated landing queue, pre-land scrub, auto-rebase of in-flight lanes, fleet status, one-shot revert. Native primitives spawn; fleet-ops lands. Triggers: landing queue, land branches, merge queue, test gate, fleet status, land agent-team/background-agent branches, sequential merge.

djnsty23 Skill

Distill accumulated observations for a code area into a focused domain knowledge brief

djnsty23 Skill

Writing a document another agent will execute: a SKILL.md, a CLAUDE.md or AGENTS.md line, a subagent brief, a scheduled-task prompt, a doc reached by a pointer. Use when creating or editing any of those.

djnsty23 Skill

How many agents to spawn, at which model and effort, so a fan-out does not burn the session's limits. Load before spawning subagents, running a workflow, or dispatching background sessions.

spartan-stratos Bundle

Create a structured on-call log by pulling alerts from monitoring and writing a summary to your team's wiki. Requires a monitoring MCP (recommended: Datadog) and a wiki MCP (Confluence or Notion).

joabgonzalez Skill

Human-centric communication with empathy and clarity. Trigger: When improving prompts, agent behavior, or user-facing content.

joabgonzalez Skill

Synchronization across model directories. Trigger: After creating or modifying skills, agents, or prompts to sync across directories.

spartan-stratos Skill

Investigate a monitoring alert end-to-end. Pulls metrics, logs, traces, and recent code changes to identify root cause. Works with any monitoring MCP.

kaakati Bundle

Design PostgreSQL/PostGIS schemas and create safe ActiveRecord migrations with rollback plans, spatial column design, index strategy, and zero-downtime deployment patterns. Use this skill whenever someone asks to create a table, modify a schema, write a migration, design a data model, add an index, or says things like "create a migration for X", "add a column to Y", "design the database schema", "what indexes do I need", "plan the data model", or "how do I safely change this column type". Also trigger when someone mentions zero-downtime migrations, expand-and-contract pattern, backfills, PostGIS spatial columns, or large table migration strategy.

joabgonzalez Bundle

Standards-compliant agent definitions with templates. Trigger: When creating agent definitions, setting up project agents, or documenting workflows.

0xdarkmatter Bundle

Audit any repo against the agentic-quality doctrine — score entry docs, structure, and enforcement gates, then map each finding to its fix. Triggers on: repo doctor, repo audit, agentic quality, is this repo agent-friendly, doc drift, stale AGENTS.md, monorepo structure, nested CLAUDE.md.

0xdarkmatter Bundle

Comprehensive Windows workstation operations - diagnose slow boot, failing drives, BSOD crashes, startup bloat, event logs. Use for: Windows is slow, slow bootup, won't boot, blue screen, BSOD, kernel crash, drive failing, SMART errors, disk errors, Event 41, Event 129, storahci reset, BugCheck, CRITICAL_PROCESS_DIED, crash dump, MEMORY.DMP, minidump, msconfig, services.msc, registry Run keys, StartupApproved, scheduled tasks at logon, slow login, high CPU at boot, disable startup app, unexplained UAC prompt, what asked for admin, prefetch forensics, BAM, process attribution, Security 4688. A drive letter alone does not name the skill: mapped network drive, SMB, UNC, NAS route to net-ops.

0xdarkmatter Bundle

One cheap headless Claude Code worker on a cheaper brain (GLM via z.ai, or Sonnet/Haiku) - full tool harness, isolated git worktree + CLAUDE_CONFIG_DIR - fanned out and gated by an Opus orchestrator. Triggers: fleet-worker, GLM worker, grunt worker, cheap parallel agent, offload to GLM, sonnet worker, haiku worker.

0xdarkmatter Bundle

Router for parallel or recurring agent work across six skills. Covers: parallel agents, fan out work, delegate to workers, run overnight, scheduled loop, land branches, mixed-model fleet, orchestrate workers, background agents at scale. Triggers on: which skill for parallel work, fan out agents, spawn workers, run this overnight, schedule a loop, land my branches, heterogeneous fleet, delegate to cheaper model, autonomous loop.

kaakati Bundle

Design and implement Rails backend features with Panko serializers, PostgreSQL/PostGIS, Redis caching, Sidekiq jobs, and Centrifugo real-time channels. Use this skill whenever someone asks to build a backend feature, design a Rails model, create an API endpoint, architect a service, or says things like "build the backend for X", "design the model layer", "add a Sidekiq job", "implement caching for X", "create the controller", or "how should we structure this service". Also trigger when someone mentions Panko serializer design, PostGIS spatial queries, Redis cache strategy, or Centrifugo channel topology.

kaakati Skill

Agent team coordination conventions — file ownership, task sizing, worktree isolation, dynamic spawning, quality gates. Use when coordinating multi-agent teams.

kaakati Skill

AI/ML engineering conventions — notebooks vs modules, MLflow experiment tracking, reproducibility, FastAPI model serving, pgvector embeddings, LLM (Anthropic) integration, evals. Use when writing training pipelines, inference services, or LLM features.

joabgonzalez Bundle

Context prompts for AI assistants with schema validation. Trigger: When creating context prompts for AI assistants or documenting project config.

joabgonzalez Skill

Eliminate overthinking: act on intent, cache decisions, stay in scope. Trigger: When agent hesitates, over-analyzes, or re-litigates.

aselimc Bundle

Machine learning in Python with scikit-learn. Use when working with supervised learning (classification, regression), unsupervised learning (clustering, dimensionality reduction), model evaluation, hyperparameter tuning, preprocessing, or building ML pipelines. Provides comprehensive reference documentation for algorithms, preprocessing techniques, pipelines, and best practices.

aselimc Bundle

This skill should be used when working with pre-trained transformer models for natural language processing, computer vision, audio, or multimodal tasks. Use for text generation, classification, question answering, translation, summarization, image classification, object detection, speech recognition, and fine-tuning models on custom datasets.

aselimc Skill

Fine-tune LLMs with LoRA/QLoRA, instruction tuning, and alignment (DPO/ORPO).

joabgonzalez Bundle

Model logic as explicit states and transitions. Trigger: When managing multi-step workflows, async states, or logic with impossible flag combinations.

kaakati Bundle

Validate and implement Clean Architecture patterns including entity/use-case/adapter/framework layer separation, dependency direction enforcement, and architectural conformance checking. Use this skill whenever someone asks about architecture validation, layer boundaries, dependency direction, or says things like "check architecture", "validate clean architecture", "are my layers correct", "dependency direction", "refactor to clean architecture", "layer violation", or "architectural conformance". Also trigger for discussions about service object patterns, controller responsibilities, or domain model isolation.

0xdarkmatter Bundle

Building applications ON Claude - the Anthropic API and Claude Agent SDK. Use for: anthropic api, claude api, messages api, tool use, function calling, prompt caching, agent sdk, claude-agent-sdk, structured output, json schema output, batches api, extended thinking, adaptive thinking, model selection, claude pricing, build claude agent, anthropic sdk, stop_reason handling, streaming claude, token counting, cache_control, output_config, tool_choice, agentic loop, rate limits anthropic.

aselimc Skill

Systematic prompt design. Structured output, few-shot, chain-of-thought, and anti-patterns.

munlucky Bundle

Internal Moonshot Architecture stage for writing C4 model artifacts and ADRs from accepted architecture decisions.

0xdarkmatter Bundle

FastAPI web framework patterns. Triggers on: fastapi, api endpoint, dependency injection, pydantic model, openapi, swagger, starlette, async api, rest api, uvicorn.

0xdarkmatter Bundle

Process Compose orchestration for non-containerized local services: process-compose.yaml schema, health checks, restart policies, dependencies, TUI/REST/MCP control, scheduling, and boot persistence. Use as a PM2/supervisord/Foreman replacement for local dev service management.

0xdarkmatter Bundle

Defend the agent against adversarial Unicode it obeys but a human can't see: bidi/Trojan Source, tag-char smuggling, zero-width text, homoglyphs. Triggers on: prompt injection, scan for hidden unicode, hidden characters, zero-width space, Trojan Source, ASCII smuggling, poisoned CLAUDE.md, MCP tool poisoning, is this file safe.

aselimc Skill

Learned dynamics models for prediction and planning. RSSM, JEPA, Dreamer, imagination-based RL.

aselimc Skill

Export PyTorch models to ONNX/TensorRT for production deployment. Validate numerical equivalence.