AI & ML Agent Skills

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate exte...

Pre-ingestion verification for epistemic quality in RAG systems with 9-point verification and Two-Round HITL workflow

Platform APIs for model management, pricing, and usage tracking

Use when developing in packages/agent-core-v2 (the DI × Scope agent engine) — adding or modifying a domain Service, choosing a LifecycleScope, wiring DI dependencies, splitting a domain across scopes, owning or migrating a config section, gating behavior behind an experimental flag, raising coded errors, working on the permission system, writing DI/Scope tests, porting business logic from agent-core (v1) to v2, triaging a main-branch commit against v2, or exposing a v2 domain over server-v2 while keeping the /api/v1 wire contract compatible with released clients. Self-contained guide organized by development stage (orient → design → implement → test → verify) plus align workflows for v1→v2 migration, main-branch commit triage, and server-v2 wire exposure; each file carries the rules, examples, and red lines for its step.

Use ONLY for code review and test write/review guidance in `packages/agent-core-v2` (the DI × Scope agent engine). Does NOT apply to the legacy `packages/agent-core` or to any other package — for those, do not load this skill. Groups the review and testing lenses used for agent-core-v2 — `slop` (single-level-of-abstraction / layered error-handling review, invoked only on explicit request) and `test` (contract-driven per-test rules for both authoring and reviewing tests). Apply the sub-skill that matches the task; do not apply `slop` unprompted.

Use when designing or building any terminal user interface — choosing a layout paradigm, keybindings/interaction model, color system, data visualization, or motion. Framework-agnostic universal patterns that work with Ratatui, Ink, Textual, Bubbletea, or any TUI toolkit. For the repo's own pythinker-code TUI, use write-tui instead.

Invoke only when the user explicitly asks to review code through the "single level of abstraction / layered error handling" lens — a function does only its own layer's business logic while errors are handled above or below. The agent reports detections, raw-count measurements, and move directions. Apply only when the user explicitly requests this lens.

Invoke a registered skill from the current skill listing. BLOCKING REQUIREMENT: when a skill from the listing matches the user's request, you MUST call this tool (not free-form text). Do not re-invoke a skill to repeat work already done: if a `<skill-loaded>` block for it with the same `args` is already present in the conversation, follow those instructions directly instead of calling the tool again. Do call the tool again when you need the skill with different arguments — the loaded block was expanded with the earlier `args` and will not reflect new inputs.

Discover and reorganize the skill inventory into hierarchical sub-skill bundles. Use when the user asks to review, group, or consolidate skills into a parent bundle.

Analyze the available skill set and recommend candidate groups that could be consolidated into sub-skill bundles. Read-only — proposes a plan, does not move files.

Reranking retrieved documents with cross-encoders and LLM rerankers. Cohere Rerank v3, Voyage rerank-2, BGE reranker, ColBERT late interaction, Jina reranker. Cost and latency tradeoffs, top-K in / top-N out strategy. USE WHEN: user mentions "rerank", "reranker", "cross-encoder", "Cohere Rerank", "Voyage rerank", "BGE reranker", "ColBERT", "Jina reranker", "bi-encoder" DO NOT USE FOR: initial retrieval - use `advanced-retrieval` or `hybrid-search`; query rewriting - use `query-transformations`; agent decisions - use `agentic-rag`

Server-Sent Events for real-time server-to-client streaming. Express, Fastify, FastAPI, Spring WebFlux SSE implementations. Event streams, reconnection, and EventSource API. USE WHEN: user mentions "SSE", "Server-Sent Events", "EventSource", "event stream", "text/event-stream", "live feed", "streaming updates" DO NOT USE FOR: bidirectional communication - use `socket-io`; WebRTC - use `webrtc`; LLM streaming - use AI SDK skills

Caching strategies across the RAG stack. Semantic caching with GPTCache and LangChain, Redis-based embedding-similarity cache, cache key design, TTL/invalidation, partial caching (cache retrieval only), provider-native prompt caching (Anthropic, OpenAI), and hierarchical L1/L2 caches. USE WHEN: user mentions "semantic cache", "GPTCache", "LLM cache", "prompt caching", "Redis vector cache", "cache invalidation for RAG", "reduce LLM cost", "latency reduction LLM" DO NOT USE FOR: retrieval accuracy - use `rag-patterns`; groundedness checks - use `rag-guardrails`; incremental indexing - use `rag-production`

Use when entering a repository with a .ctx/ hub, or when the user asks about project context, agent instructions, tool configuration, health, candidates, broken shims, repair, or cross-tool context.

Find phone numbers for decision makers via Lemlist using Chrome DevTools MCP. Takes LinkedIn profile URLs and returns phone numbers where available.

Determines all follow-up actions due today across the 10-day outreach cadence. Generates content and delivers automatically via Chrome DevTools MCP. Sends Telegram confirmation after completion.

Find and validate email addresses using Snov.io via Chrome DevTools MCP. Takes LinkedIn profile URLs and returns verified emails. Replaces ZeroBounce.

Find 5 decision makers at a company via Apollo.io UI using Chrome DevTools MCP. No enrichment, no credits used.

Claude-Codex-Gemini tri-model orchestration via /ask codex + /ask antigravity (or gemini), then Claude synthesizes results

N coordinated agents on shared task list using Claude Code implicit agent teams

LLM Wiki — persistent markdown knowledge base that compounds across sessions (Karpathy model)

Senior software engineer for story execution and code implementation. Use when the user asks to talk to Amelia or requests the developer agent.

Use first for install/update routing — sends setup, doctor, or MCP requests to the correct OMC setup flow

Orchestrates group discussions between installed BMAD agents, enabling natural multi-agent conversations where each agent is a real subagent with independent thinking. Use when user requests party mode, wants multiple agent perspectives, group discussion, roundtable, or multi-agent conversation about their project.

Lossless LLM-optimized compression of source documents. Use when the user requests to 'distill documents' or 'create a distillate'.

Strategic business analyst and requirements expert. Use when the user asks to talk to Mary or requests the business analyst.

System architect and technical design leader. Use when the user asks to talk to Winston or requests the architect.

Technical documentation specialist and knowledge curator. Use when the user asks to talk to Paige or requests the tech writer.

UX designer and UI specialist. Use when the user asks to talk to Sally or requests the UX designer.

LLM-assisted human-in-the-loop review. Make sense of a change, focus attention where it matters, test. Use when the user says "checkpoint", "human review", or "walk me through this change".

Push the LLM to reconsider, refine, and improve its recent output. Use when user asks for deeper critique or mentions a known deeper critique method, e.g. socratic, first principles, pre-mortem, red team.

Generate music using ElevenLabs Music API. Use when creating instrumental tracks, songs with lyrics, background music, jingles, or any AI-generated music composition. Supports prompt-based generation, composition plans for granular control, and detailed output with metadata.

Use when working with ComfyUI workflows in OpenMontage, including comfyui_image/comfyui_video, custom workflow_json/workflow_path inputs, output_node selection, missing model setup, LoRAs, low-VRAM workflow choices, and community workflow imports.

Agent Vault — fetching secrets from Infisical at runtime

Run a prompt or skill in this session on a recurring or variable interval (e.g. /loop 5m /foo).

Install, configure, and run Hermes Agent locally on a laptop/workstation with the full intelli-verse-x wiring — LiteLLM gateway, admin-mcp, self-hosted Firecrawl, org skills, and the IX Agency desktop app. Use when someone asks "how do I get Hermes on my machine", when bootstrapping a new employee system, or when a local install is missing MCPs/tools/skills that the org supports.