Data & AI skills

Enhancement-overlay decision protocol for STREAMING the output of long-running LLM / agent runs from the *backend*, not just wiring a typing animation in the UI. Activates when a coder agent must stream final tokens to a chat client, surface intermediate agent steps (which tool, which node, partial reasoning), emit custom tool-progress events, choose a transport (SSE vs WebSocket), or decide what to do when the client disconnects mid-stream. The langchain / langgraph skills mention stream modes but stop at "you can stream"; this skill encodes *what to stream, over what transport, and how to fail safely*.

The English summary is being prepared. Showing the original description.

LEAP builds skills through two pipelines: Branch A distills a skill from raw data, while Branch B combines multiple skills into one. It is called by the main SkillAlchemy workflow. Use when SkillAlchemy requires distillation or fusion.

The English summary is being prepared. Showing the original description.

Enhancement overlay for multi-agent / tool-using coder agents. Encodes the per-agent tool- scoping discipline that role-based frameworks (CrewAI, LangChain) document only as a passing best-practice: which agent gets which tool, and why blanket-sharing every tool to every agent is a correctness and blast-radius risk. Activates when an agent system has tools AND there is more than one agent (or one agent holding many tools). Treat a tool as a capability grant; scope by least-privilege. ENHANCE overlay — read alongside [[crewai]], [[agentsop-http-tool-wrapping]], [[agentsop-llm-tool-idempotency]]. Search keywords: which tools per agent, least-privilege agent, agent tool access, tool permissions, limit agent tools, scope tools to roles.overlay_type: enhancement

The English summary is being prepared. Showing the original description.

ENHANCE overlay on [[dspy]] — the upfront rubric for choosing a reasoning SHAPE (Predict / ChainOfThought / ReAct / ProgramOfThought) BEFORE you write a prompt or pick an optimizer. The local `dspy` skill lists the modules but never surfaces the *selection criterion*: reasoning shape is chosen by task structure, not by reflexively defaulting to CoT. Activate every time a new LM-calling node/step is added to a pipeline. Do NOT activate for one-shot prompts, optimizer/teleprompter choice (that is the dspy SOP's job), or non-LM control flow. Search keywords: chain of thought vs ReAct, when to use CoT, reasoning type, ReAct vs CoT vs PoT, which dspy module, predict vs chain of thought.

The English summary is being prepared. Showing the original description.

Adds and tunes a reranker stage for RAG using the retrieve-wide, rerank-narrow pattern. Use when relevant documents appear in the initial top-N but are buried by noise, top-1 precision or MRR is low despite adequate recall, or too many marginal chunks consume context. Covers cross-encoder, API, and local rerankers; N-to-k selection; and latency/cost tradeoffs. Do not use when retrieval recall itself is failing.

The English summary is being prepared. Showing the original description.

Lifecycle SOP for **per-model prompt artifacts** — the compiled prompts, instructions, few-shot demos, edit-format pins, and embedding-bound indices that change behavior when the underlying LM, dataset, or framework version changes. Activate when adopting compiled prompts (DSPy, GEPA, BootstrapFewShot output), when supporting multiple LMs in production, when a provider deprecates a model snapshot, or when a framework deprecates a config surface (LlamaIndex `ServiceContext` → `Settings`, Aider edit-format defaults). Do NOT activate for one-off raw prompt edits or for truly model-agnostic system prompts that have been swap-tested. Search keywords: prompt portability, model swap, recompile prompt, model deprecation, prompt per model, prompt breaks on new model, version compiled prompts.

The English summary is being prepared. Showing the original description.

A 5-minute gate the coder runs at project kickoff (and again whenever the repo shape changes). Classifies the workspace into Greenfield / Brownfield-large / Mid-size-familiar / Library-SDK, then maps the state to an agent strategy (autonomy, context primitive, tool choice). Use BEFORE picking Cursor vs Claude Code vs Aider, BEFORE turning on repo-map, BEFORE writing the first prompt. Skip only if the same repo was gated within the last day and nothing changed. Search keywords: greenfield vs brownfield, new project vs existing codebase, project setup strategy, legacy codebase agent, where to start a coding agent.

The English summary is being prepared. Showing the original description.

Routes heterogeneous queries to the appropriate index, tool, or answering engine before retrieval. Use when one endpoint serves multiple handlers, such as summary, vector retrieval, text-to-SQL, or tools, and query types require different paths. Covers LLM, semantic, and rule-based routers, confidence thresholds, fallbacks, and framework mappings. Do not use when one handler serves all queries or branching is fixed.

The English summary is being prepared. Showing the original description.

Designs multiscale chunking for RAG by embedding small units for retrieval precision and returning larger context for synthesis. Use when fixed-size chunks either lose surrounding context or dilute relevance in long documents, manuals, filings, or codebases. Covers sentence-window and parent-child or auto-merging strategies, base chunk sizing, and evaluation. Do not use when a single chunk scale already meets retrieval and generation needs.

The English summary is being prepared. Showing the original description.

Security-first SOP for multi-tenant RAG systems. Activate when a calling agent is building, reviewing, or debugging any retrieval pipeline whose vector store is shared across more than one user, organisation, workspace, customer, or permission scope. Encodes the single non-negotiable rule — **filter at the vector store query, never after retrieval / never after rerank** — together with the per-vendor query-time filter APIs (Pinecone namespaces + `$eq`/`$in`, Weaviate `multiTenancyConfig` + tenant handle, Qdrant `is_tenant` payload index + `Filter.must`, Chroma `where`, pgvector RLS), and the cross-framework adapters (LlamaIndex `MetadataFilters`, LangChain `filter=` dict). Frame the work as preventing CVE-2024-41892 / EchoLeak / Slack-AI-class cross-tenant leakage, not as "adding a filter for relevance".

The English summary is being prepared. Showing the original description.

Cross-engine decision rubric for self-hosting or recommending an LLM serving stack. Picks among vLLM, SGLang, TensorRT-LLM, TGI, llama.cpp, Ollama, and MLX as a function of (hardware × workload × constraint), not "which is fastest". Activates whenever a coder-agent must choose, defend, or migrate a serving runtime.

The English summary is being prepared. Showing the original description.

The compile-readiness gate for prompt auto-optimization. Decide whether you have earned the right to run an optimizer (DSPy MIPROv2 / GEPA / BootstrapFewShot) before spending compute. Two preconditions only — a real metric, and enough examples for the optimizer you picked. Garbage metric in, garbage prompt out. Pick the optimizer by data scale; GEPA inverts the scale assumption (~10 examples + textual feedback).

The English summary is being prepared. Showing the original description.

Decision protocol for making side-effectful agent tools idempotent — so when an LLM tool call is retried (timeout, framework resume, user re-run, model duplicate emit), the second call is a no-op instead of a double-send. The load-bearing premise: the LM cannot promise it'll call exactly once; the tool must promise the second call is safe. Framework-agnostic — applies to LangGraph node bodies that re-run on resume, MCP tools, OpenAI tool-calling retries, CrewAI delegated tool invocations, and direct HTTP wrappers. Search keywords: duplicate email sent, charged twice, exactly-once, idempotency key, tool called twice, retry side effect, double-send, at-least-once delivery.

The English summary is being prepared. Showing the original description.

Read from a UModel object-graph semantic layer with the `umctl` CLI (MCP alternative noted). Three kinds of read: (1) entities & relationships / topology (`.entity`, `.topo`) and (2) the model itself (`.umodel`, and `.entity_set` methods, including entity-linked `list_skills`) return real rows; (3) metrics & logs (`get_metrics` / `get_logs`) return an executable *plan* — PromQL / Elasticsearch DSL with the entity id pre-substituted — that you run against the backend. Against a PaaS endpoint the same calls return data rows instead of a plan. Use to query or read UModel entities, relations, topology, or model metadata; to read a service's metrics or logs; to look up services and dependencies; or to discover what objects, datasets, and methods exist. For root-cause analysis on top of these reads, see the `umodel-rca` skill. Triggers: UModel, object graph, .entity / .topo / .umodel / .entity_set, query entities, read topology, read metrics / logs, get_metrics / get_logs, list services / dependencies / datasets / skills, 实体查询, 关系/拓扑查询, 读模型, 读指标, 读日志, 查指标, 查日志, 查服务依赖.

The English summary is being prepared. Showing the original description.

Behavioral guardrails for LLM-assisted coding. Use when writing, reviewing, or refactoring code in any project to avoid overcomplication, keep changes surgical, surface assumptions early, and execute against verifiable success criteria.

The English summary is being prepared. Showing the original description.

Curated free APIs with verified free-tier limits. Use when suggesting APIs or finding free weather, news, finance, or sports data.

The English summary is being prepared. Showing the original description.

Acquire, clean, analyze, verify, visualize, and explain data for journalism. Use for reproducible data reporting, statistical analysis, maps, or public methodology.

The English summary is being prepared. Showing the original description.

Connect to a hospital's FHIR R4 server (Epic, Oracle Health/Cerner, MEDITECH, athenahealth, or any SMART-on-FHIR endpoint), pull a patient's clinical data and notes, and extract structured findings. Use when users say "connect to the EHR", "connect to Epic/Cerner", "pull notes for patient X", "what do the last 6 months of notes say about Y", or any task that starts from a live EHR rather than pasted text.

The English summary is being prepared. Showing the original description.

Extract structured data from clinical notes with span-level provenance and null-safety. Use when users say "extract [variables] from this note", "abstract this chart", "pull structured data from these notes", "what does this note say about [field]", or when building a chart-abstraction, registry, or cohort dataset from unstructured clinical text.

The English summary is being prepared. Showing the original description.

Screen a Medicare/Medicaid claims corpus for fraud, waste, and abuse and produce ranked, fully-cited investigation referrals for an SIU / program-integrity team. Use when asked to run a fraud sweep, screen claims for FWA, find billing anomalies, or generate investigation referrals over a claims dataset.

The English summary is being prepared. Showing the original description.

Walk-forward validation framework for trading strategies and ML models with time-series-aware splits, overfit detection, and regime-aware validation

The English summary is being prepared. Showing the original description.

Market regime identification using volatility clustering, trend detection, and statistical methods for adaptive trading

The English summary is being prepared. Showing the original description.

Feature construction from market data for ML trading models including price, volume, on-chain, and microstructure features

The English summary is being prepared. Showing the original description.

ML trading signal classifiers using XGBoost and LightGBM with walk-forward validation, SHAP feature importance, and threshold optimization

The English summary is being prepared. Showing the original description.