AI & ML

bytesagain Bundle

Conda package and environment manager reference. Covers environment creation and export, environment.yml, channels (conda-forge, nvidia), Mamba fast solver, GPU/CUDA setup, pip integration, conda-lock, and troubleshooting.

bytesagain Bundle

Chroma embedded vector database reference. Covers in-process and persistent modes, auto-embedding, Python SDK CRUD, metadata and document filters, OpenAI/HuggingFace/Cohere embedding functions, LangChain integration, and server deployment.

bytesagain Bundle

Milvus open-source vector database reference. Covers Python SDK (pymilvus), collection schema, similarity search with metadata filters, RAG pattern with OpenAI, index types (HNSW/IVF/SCANN), distance metrics, and vector DB comparison.

bytesagain Bundle

YubiKey hardware security key reference. Covers FIDO2 passkeys, U2F two-factor, TOTP authenticator codes, GPG smartcard for commit signing, ed25519-sk SSH keys, PIV certificates, ykman CLI, OTP slots, PIN management, and model comparison.

bytesagain Bundle

ArangoDB multi-model database reference covering document, graph, and key-value operations. Includes AQL query language, graph traversals, shortest path algorithms, indexing, ArangoSearch, clustering, backup, and administration.

bytesagain Bundle

Weaviate AI-native vector database reference. Covers auto- vectorization modules (OpenAI/Cohere/CLIP), hybrid search (vector+BM25), generative search (built-in RAG), Python v4 SDK, multi-tenancy, GraphQL API, and backup/restore.

kensaurus Skill

Add/upgrade PWA capabilities: manifest, service worker, offline mode, install prompt, push notifications, background sync. Use when "make it a PWA", "offline support", "install prompt", "service worker", or "add to home screen". Native Capacitor → mobile-capacitor-platform.

kensaurus Skill

Co-author structured documents (specs, PRDs, RFCs) through a 3-stage workflow: context gathering, drafting, and reader testing. Use when writing proposals, technical specs, or similar structured content. Repo decision-memory system (INDEX.md, rejected alternatives, agent rules) → docs-adr.

kensaurus Skill

Static OWASP review of app code (injection, headers, deps). Use when "review security" or "check vulnerabilities". Session/route×gate/getSession → audit-auth-flows. Plan-only burndown → plan-security-audit. Table RLS → plan-rls-audit. LLM attacks → audit-llm-security.

kensaurus Skill

Scaffold and implement Model Context Protocol (MCP) servers that expose external services, APIs, and data sources as typed tools and resources for LLM agents. Use when the user says "build an MCP server", "give Claude access to X", "create an MCP tool", "expose my API to an agent", or "AI agent integration".

kensaurus Bundle

Stop vibe-coding with a spec → plan → TDD loop before writing a line. Use when "spec first", "TDD", "do it properly", or LLM output keeps being wrong. End-to-end feature through PR → workflow-build-feature. One named bug → workflow-fix-and-ship.

kensaurus Skill

Read-only OWASP LLM Top 10 audit of app-facing AI: prompt injection, data leakage, unsafe output/agency, RAG risks, misinformation, and unbounded spend. Use when "audit LLM security", "prompt injection", "jailbreak my chatbot", or "is my AI safe?". General app security → audit-security.

kensaurus Skill

Create or update a pack SKILL.md (frontmatter, house limits, T1–T6). Use when authoring a cursor-kenji skill. Prompt-only upgrade → enhance-skill-prompts. Cursor skill wizard → create-skill.

kensaurus Skill

Build and sharpen a project's domain model — a CONTEXT.md glossary and ubiquitous language. Use when pinning down terminology, or the agent "uses the wrong words". Repo decision-memory system (INDEX.md, rejected alternatives) → docs-adr.

kensaurus Skill

Read-only audit of an agent-skill pack for contradictory directives, overlapping triggers, stale cross-refs, and context bloat. Use when "audit my skills", "conflicting skills", "wrong skill triggered", or after adding a batch. Per-file spec → validate:skills. How to write one → meta-skill-creator.

kensaurus Bundle

Upgrade an existing SKILL.md prompt (not its behavior) to 2026 practice: degrees of freedom, structured CoT, one worked example, self-critique rubric, term consistency. Use when "enhance this skill's prompts", "upgrade skill authoring", or "apply the prompt playbook". New skill from scratch → meta-skill-creator.

kensaurus Skill

Turn an agent failure—premature stop, false completion, gamed check, missed file, broken handoff—into a durable rule/skill/hook/CI guard plus regression test. Use when "the agent stopped early again", "it gamed the test", or "add a guard so this doesn't recur". App bugs → workflow-fix-and-ship.

kensaurus Skill

Install guardrails-as-code so AI sessions cannot reintroduce leaked secrets, injection, or untested code. Use when "set up guardrails", "stop vibe-coding regressions", "add pre-commit security checks". Gate-logic audit → audit-gate-logic. Gate sprawl → housekeep-gates.

kensaurus Skill

Audit an LLM-powered app for runaway-cost and quota-abuse exposure, then produce a phased guardrail plan. Use when the user says "cap my AI costs", "my LLM bill could blow up", "rate limit my AI", "token budget", "runaway agent loop", or is hardening LLM features before launch.

kensaurus Skill

Apply behavioral guardrails when writing, editing, refactoring, or debugging code. Use when vibe-coding keeps producing wrong results, or for any task needing "think before coding", "simplicity first", "surgical changes". Adapted from Karpathy's LLM coding observations.

baofeng-tech Bundle

Requires python3, and AISA_API_KEY. Uses the supplied AISA_API_KEY to send requests to https://api.aisa.one. Native-first ClawHub plugin for `us-stock-analyst`. Ships the packaged AIsa skill with an `openclaw.plugin.json` manifest and a Claude-compatible bundle fallback. Professional US stock analysis with financial data, news, social sentiment, and multi-model AI. Comprehensive reports at $0.02-0.10 per analysis. Use when: the user needs market data, stock analysis, watchlists, or portfolio workflows.

baofeng-tech Bundle

Requires python3, and AISA_API_KEY. Uses the supplied AISA_API_KEY to send requests to https://api.aisa.one. Native-first ClawHub plugin for `openclaw-media-gen`. Ships the packaged AIsa skill with an `openclaw.plugin.json` manifest and a Claude-compatible bundle fallback. Generate images and videos with AIsa. Four image models (Google Gemini 3 Pro Image, Alibaba Wan 2.7 image + image-pro, ByteDance Seedream) and four Wan video variants (wan2.6/2.7 × t2v/i2v). One API key; the client routes each model to the correct endpoint automatically. Use when: the user needs AI image or video generation workflows.

nous-hermeshub Skill

Expert on Odoo's external JSON-RPC and XML-RPC APIs. Covers authentication, model calls, record CRUD, and real-world integration examples in Python, JavaScript, and curl.

nous-hermeshub Skill

<!-- canonical copy: engineering/llm-wiki/commands/wiki-init.md — keep in sync -->

nous-hermeshub Skill

<!-- canonical copy: engineering/llm-wiki/commands/wiki-query.md — keep in sync (root copy uses repo-root-relative script paths) -->

nous-hermeshub Skill

Agent Memory Systems

nous-hermeshub Skill

Multi-Agent Architecture Patterns

nous-hermeshub Skill

Expert guide for creating custom Odoo modules. Covers __manifest__.py, model inheritance, ORM patterns, and module structure best practices.

nous-hermeshub Skill

Seek and analyze video content using Memories.ai Large Visual Memory Model for persistent video intelligence

nous-hermeshub Skill

ML engineering skill for productionizing models, building MLOps pipelines, and integrating LLMs. Covers model deployment, feature stores, drift monitoring, RAG systems, and cost optimization. Use when the user asks about deploying ML models to pro...

nous-hermeshub Skill

Run parallel feature work safely with Git worktrees. Standardizes branch isolation, port allocation, environment sync, and cleanup so each worktree behaves like an independent local app. Optimized for multi-agent workflows where each agent or term...

nous-hermeshub Skill

Scoped CLAUDE.md memory system that reduces context token spend. Creates directory-level context files, tracks savings via dashboard, and routes agents to the right sub-context.

nous-hermeshub Skill

Claude in Chrome MCP Troubleshooting

michaelschecht Skill

Use the Gemini CLI for one-shot Q&A, summarization, and generation tasks. Trigger when Gemini-specific CLI usage, model selection, or JSON-formatted output is needed.

michaelschecht Skill

AI-optimized web search using the Tavily API for current events, domain-filtered research, answer summaries, and raw content extraction. Use when live web research needs cleaner LLM-ready results than generic search.

michaelschecht Bundle

Lightweight WSI tile extraction and preprocessing. Use for basic slide processing tissue detection, tile extraction, stain normalization for H&E images. Best for simple pipelines, dataset preparation, quick tile-based analysis. For advanced spatial proteomics, multiplexed imaging, or deep learning pipelines use pathml.