Loading...
Loading...
Found 1,166 Skills
Instrument, trace, evaluate, and monitor LLM applications and AI agents with LangSmith. Use when setting up observability for LLM pipelines, running offline or online evaluations, managing prompts in the Prompt Hub, creating datasets for regression testing, or deploying agent servers. Triggers on: langsmith, langchain tracing, llm tracing, llm observability, llm evaluation, trace llm calls, @traceable, wrap_openai, langsmith evaluate, langsmith dataset, langsmith feedback, langsmith prompt hub, langsmith project, llm monitoring, llm debugging, llm quality, openevals, langsmith cli, langsmith experiment, annotate llm, llm judge.
Conduct an interactive discovery interview to produce a structured product specification. Triggers: write a spec, PRD, feature spec, requirements, product requirements, scope a project, brainstorm a feature, flesh out an idea, plan a new project. Uses AskUserQuestion for all user choices; WebSearch/WebFetch when the user wants research. Outputs: user stories, acceptance criteria, technical constraints, prioritized requirements in docs/specs/ per SPEC_TEMPLATE.md. Do NOT use for: implementation, code review, debugging, refactors, or when the user already has a complete spec they only want edited.
Fine-tunes and evaluates OpenVLA-OFT and OpenVLA-OFT+ policies for robot action generation with continuous action heads, LoRA adaptation, and FiLM conditioning on LIBERO simulation and ALOHA real-world setups. Use when reproducing OpenVLA-OFT paper results, training custom VLA action heads (L1 or diffusion), deploying server-client inference for ALOHA, or debugging normalization, LoRA merge, and cross-GPU issues.
Fine-tune and serve Physical Intelligence OpenPI models (pi0, pi0-fast, pi0.5) using JAX or PyTorch backends for robot policy inference across ALOHA, DROID, and LIBERO environments. Use when adapting pi0 models to custom datasets, converting JAX checkpoints to PyTorch, running policy inference servers, or debugging norm stats and GPU memory issues.
Apply when building or debugging a VTEX IO session transform app (vtex.session integration). Covers namespace ownership, input-vs-output fields, transform ordering (DAG), public-as-input vs private-as-read model, cross-namespace propagation, configuration.json contracts, caching inside transforms, and frontend session consumption. Use when designing session-derived state for B2B, pricing, regionalization, or custom storefront context.
Comprehensive Pal MCP toolkit for code analysis, debugging, planning, refactoring, code review, and execution tracing. Provides systematic workflows with expert validation for complex development tasks.
Create and debug Cloudinary transformation URLs from natural language instructions. Use when building Cloudinary delivery URLs, applying image/video transformations, optimizing media, or debugging transformation syntax errors.
Systematic evidence-based debugging using runtime logs. Generates hypotheses, instruments code with NDJSON logs, guides reproduction, analyzes log evidence, and iterates until root cause is proven with cited log lines. Use when the user reports a bug, unexpected behavior, or asks to debug an issue.
Review Skill definition quality. Use when user asks to "review skill", "check skill quality", "validate skill", "lint skill", "review my skill", or wants to check if a Skill follows best practices. For execution trace analysis, use when user explicitly mentions "analyze execution", "review trace", or "evaluate execution process". Do NOT use for runtime debugging (use agent-debug skill), code review (use code-review skill), or general file validation.
Build identity-preserving character generation workflows and pipelines in ComfyUI. Selects the optimal identity method (InfiniteYou, FLUX Kontext, PuLID, InstantID, IP-Adapter) based on use case requirements. Handles face preservation, likeness transfer, cross-domain conversion (3D to photo), multi-reference consistency, iterative character editing, and character variation generation. Triggers on requests to generate consistent characters, preserve identity across images, create face-swapping workflows, or convert 3D renders to photorealistic portraits. Does NOT cover general image generation without identity preservation, model training/LoRA fine-tuning, animation, technical explanations, or workflow debugging.
Flux CD and Flux Operator expert — answers questions and generates schema-validated YAML for all Flux CRDs (not repo auditing or live cluster debugging). Use when users ask about Flux concepts, want manifests for HelmRelease, Kustomization, GitRepository, OCIRepository, ResourceSet, FluxInstance, or any Flux resource, or need guidance on GitOps repository structure, multi-tenancy, OCI-based delivery, image tag automation, drift detection, preview environments, notifications, or the Flux Web UI and MCP Server. Whenever users mention FluxCD, Flux Operator, or any Flux CRD in a question or manifest generation context, always use this skill.
LLDB debugger skill for C/C++/Swift/Objective-C programs. Use when debugging with LLDB on macOS, FreeBSD, or Linux-clang environments, mapping GDB mental models to LLDB commands, using LLDB in Xcode or VS Code, or debugging Swift/Objective-C. Activates on queries about LLDB commands, GDB to LLDB migration, Apple platform debugging, LLDB Python scripting, or IDE-integrated debugging with clang-built binaries.