102 skills · sorted by relevance
Build question answering and document retrieval workflows with DSPy by defining inputs, outputs, and reusable components. Use training examples and evaluation metrics to automatically optimize prompts and compare results before and after optimization.
Build DSPy 3.2.x programs through spec, program, metric and baseline; extend to optimization and export when requested and justified by task budget. Orchestrates the other four DSPy skills (dspy-fundamentals, dspy-evaluation-harness, dspy-gepa-optimizer, dspy-rlm-module) in the correct order. Use for greenfield DSPy builds; prototypes may stop at a validated baseline.
The English summary is being prepared. Showing the original description.
Build AI workflows with DSPy by defining inputs and outputs and combining reusable components. Create question answering systems that use retrieved documents, tool-using agents, and automatically optimized prompts, then compare results with evaluation data.
Build AI workflows with DSPy by defining inputs and outputs and combining reusable components. Create question answering systems that use retrieved documents, tool-using agents, and automatically optimized prompts, then compare results with evaluation data.
Decision rubric for promoting a prose prompt into a typed DSPy Signature. This is an ENHANCE overlay on top of the [[dspy]] library skill: it does NOT teach DSPy syntax — it answers the coder-agent decision "when do I stop hand-writing a prompt string and declare it as a `dspy.Signature`, and how do I name/describe its fields so the optimizer and the calling code both get a clean contract." Activate when: a prompt string grows past ~50 lines; the LM output is consumed by code (parsed, branched on, stored) rather than read by a human; the same prompt is reused across >1 call site; or a teammate asks "should this be a Signature?". Do NOT activate for one-shot throwaway prompts, or for HOW-TO questions about DSPy modules /optimizers/compile — defer those to the [[dspy]] skill and the [[agentsop-dspy]] workflow skill. Search keywords: typed prompt, structured prompt, DSPy Signature, prompt as a function, prompt contract, when to formalize a prompt.
The English summary is being prepared. Showing the original description.
Analyze compiled .NET and C# programs by identifying managed files, removing obfuscation, inspecting intermediate instructions, and debugging runtime behavior. Save extracted configuration and code changes as evidence for further review.
Write idiomatic DSPy 3.2.x programs — typed Signatures, dspy.Module subclasses, Predict/ChainOfThought/ReAct/ProgramOfThought, and save/load. Use this when starting any new DSPy project or when fixing non-idiomatic DSPy code (hard-coded prompts, ad-hoc string templates, untyped outputs, non-serializable classes).
The English summary is being prepared. Showing the original description.
Build DSPy evaluation harnesses with rich-feedback metrics that are essential for GEPA optimization. Use when writing a metric function, calling dspy.Evaluate, splitting dev/val sets, debugging "why is my optimizer not improving?", or designing CI-ready DSPy eval suites.
The English summary is being prepared. Showing the original description.
Optimize DSPy programs with dspy.GEPA — a reflective/evolutionary optimizer to consider against task-specific baselines within an authorized evaluation budget. Use when the user says optimize, compile, GEPA, reflective optimization, or "make this program better" and a DSPy program + metric + trainset exist.
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.
Investigate SGLang runs that freeze across multiple GPUs. It uses stack traces, communication logs, GPU memory dumps, and comparisons between processes to locate state differences, trace their causes, and guide fixes.
Inspect game code, data files, live memory, and graphics captures to understand the internals needed for a mod. Choose tools for the game’s technology, document findings, and validate unknown file formats by decoding and re-encoding them.
An overview of the core data API of ObsPy, a Python framework for processing seismological data. It is useful for parsing common seismological file formats, or manipulating custom data into standard objects for downstream use cases such as ObsPy's signal processing routines or SeisBench's modeling API.
The English summary is being prepared. Showing the original description.
Reverse-engineer successful affiliate strategies from competitors. Use this skill when the user asks about spying on competitors, researching what other affiliates promote, analyzing competitor affiliate sites, understanding how top affiliates in a niche make money, or says "what programs does X promote", "how does [site] make money", "what affiliate strategy does this site use", "spy on competitor affiliates", "reverse engineer affiliate site", "copy what works in my niche", "who are the top affiliates in X niche", "what content gets traffic in my niche", "competitor affiliate analysis".
The English summary is being prepared. Showing the original description.
Operating SOP for DSPy (Stanford NLP) — the declarative framework for "programming, not prompting" language models. Activate when the user says any of: "use DSPy", "compile a prompt", "optimize prompts/programs", "MIPRO/MIPROv2", "BootstrapFewShot", "GEPA", "Signatures + Modules", "teleprompter", "auto-tune prompts for a different LM", or whenever a brittle hand-crafted prompt pipeline needs to be turned into a *compiled*, measurable, swappable program. Do NOT activate for one-shot prompt tweaks, no-metric exploratory work, or pipelines where prompts must remain human-authored verbatim — use raw prompting or LangChain templates instead.
The English summary is being prepared. Showing the original description.
Use ANTsPy/antspyx for medical image IO, ANTsImage metadata, image operations, registration, segmentation, visualization, and learning helper workflows.
The English summary is being prepared. Showing the original description.
Use dspy.RLM (Recursive Language Model) for reasoning over contexts too large to fit in an LLM's working window — entire codebases, long logs, massive documents, or multi-step data exploration that needs a sandboxed Python REPL. Use when the input is >100k tokens, needs recursive chunking, or benefits from the LLM writing and running code to probe data.
The English summary is being prepared. Showing the original description.
DSPy is a Python framework from Stanford NLP that replaces hand-written prompts with code: you declare LLM tasks as typed signatures, compose them into modules, and let optimizers (BootstrapFewShot, MIPROv2, GEPA) tune the prompts and few-shot examples against your metric. Use when the user asks about DSPy, signatures, ChainOfThought, ReAct, teleprompters or optimizers, or wants to stop hand-tuning prompts.
The English summary is being prepared. Showing the original description.
Construa sistemas de IA complexos com programação declarativa, otimize prompts automaticamente, crie sistemas RAG modulares e agentes com DSPy - framework de Programação Sistemática de Modelos de Linguagem da Stanford NLP
The English summary is being prepared. Showing the original description.
Build complex AI systems with declarative programming, optimize prompts automatically, create modular RAG systems and agents with DSPy - Stanford NLP's framework for systematic LM programming
The English summary is being prepared. Showing the original description.
Build a Python system that follows DNS history, domain registration records, and certificate information from known suspicious domains or IP addresses. Map related attack infrastructure, identify shared connections, and monitor for newly discovered domains matching known patterns.
Convert long Markdown specifications, reports, and plans into a single HTML document with a sticky table of contents, search, section tracking, and code-copy buttons. Apply previously configured brand colors and layout styles.
Investigate how a limited Linux account could gain root, the system administrator's privileges. The skill guides checks of permissions, scheduled tasks, services, and known vulnerabilities, while outlining evidence defenders can monitor during authorized security assessments.
ObsPy allows you to easily download earthquake data from various data centers/networks through its client API. This is an overview of available services and a demo of the client API for International Federation of Digital Seismograph Networks (FDSN). Use this if you need to download earthquake research data.
The English summary is being prepared. Showing the original description.