Separate a strategy return series into declared baseline exposure and residual edge with returns-based OLS attribution, HAC inference, rolling stability, alternate-baseline sensitivity, and regime breakdowns. Use when evaluating whether backtest, out-of-sample, or live returns contain independent alpha beyond market, equal-weight, momentum, sector, or user-supplied factor returns; when explaining whether a drawdown came from baseline exposure or strategy-specific behavior; or when a strategy needs an attribution quality gate after backtesting. Do not use for holdings-based Brinson attribution, feature-level Shapley explanations, or analysis from summary metrics without a dated return series.

Group a session-metrics session's turns into higher-level SEMANTIC TASKS ("what was I actually trying to do") and render a Tasks companion page (*_tasks.html + *_tasks.md) with a worth-it / mixed / likely-waste verdict per task. Trigger when the user runs /task-breakdown, when session-metrics suggests a task breakdown after a JSON export, or when the user asks to "group my turns into tasks", "what tasks did this session cover", "which work was worth it vs wasted", or "break this session into tasks". Consumes the deterministic per-request breakdown (request_units) from a session-metrics JSON export — it never re-derives cost or token numbers. Args: $ARGUMENTS[0] = path to a session-metrics JSON export (optional; if omitted, generate one first).

Use when a notebook run fails on a missing package (ImportError, ModuleNotFoundError, "there is no package called"), when you need to inspect an installed package version, or when you need to install, add, or manage Python or R packages for the notebook runtime. Covers inspect_packages, routing Python vs R through manage_packages, why in-cell %pip/!pip/install.packages() and OS installers are forbidden, restarting the kernel after an install, and when to stop and ask the user.

Predict small-molecule binding poses with DiffDock-L (Corso et al. 2023/2024, github.com/gcorso/DiffDock) — blind diffusion docking that places a ligand into a protein pocket without a predefined search box and ranks the samples with a learned confidence model. Reach for this skill to dock a SMILES or SDF against a PDB, to generate ranked 3D poses for a small fragment library, or to get a starting pose for downstream rescoring. DiffDock predicts geometry, not affinity.

Predict protein structure for monomers and multimers with AlphaFold2 via the ColabFold runner (Mirdita et al. 2022, github.com/sokrypton/ColabFold; AlphaFold2 Jumper et al. 2021). Reach for this skill to fold a sequence or complex with the AF2/AF2-Multimer evoformer, to validate designed sequences by self-consistency pLDDT, ipTM, and RMSD, or to run a quick MSA-backed prediction using the public MMseqs2 server.

Query images with a local Ollama vision model without loading the image into the main agent context. Use when you need to describe a screenshot, check whether rendered content is present, detect overlapping elements, or ask any visual question about a PNG/JPEG/WebP file. Requires Ollama running locally with the Gemma 4 multimodal model (`gemma4` on Ollama). Script: .agents/skills/vision/scripts/ask.py. Trigger phrases: "describe image", "what does this screenshot show", "does the canvas contain content", "check screenshot visually", "look at this image", "any overlapping elements", "vision query".

Control and stream a running iOS, iPad, or Apple Watch Simulator with npx serve-sim. Use for simulator preview, taps, gestures, hardware buttons, rotation, camera injection, permissions, accessibility, and CoreAnimation debug.

Install or repair the FoundationPose perception pipeline and build its FoundationStereo TensorRT engines. Use for SAM3/TAO dependency conflicts, CUDA library failures, and depth-engine shape or precision decisions.

Brev instance operating guidance for NeMo-RL agents working in /home/ubuntu/RL with limited workspace disk, a larger /ephemeral volume, and optional /home/ubuntu/RL/.env secrets. Use when running nemo-rl-auto-research campaigns, experiments, training jobs, model or dataset downloads, shared cache-heavy commands, log-producing runs, checkpoint generation, W&B or Hugging Face authenticated workflows, or any workflow that may create large files on Brev.

Use this skill when the user needs to locate authoritative information about NVIDIA DOCA without access to the source tree — finding the right docs.nvidia.com page for a library/service/tool, identifying which DOCA libraries are installed and at what version, locating a sample on disk or its public GitHub source, decoding an on-disk path under /opt/mellanox/doca, or recovering from a 404'd or renamed doc URL. Trigger even when the user does not explicitly mention 'DOCA' or 'docs.nvidia.com' — typical implicit phrasings include 'where can I read about this library', 'which version do I have installed', 'where is the sample for X', 'this NVIDIA URL is broken what is the new one', 'what is in /opt/mellanox/doca', or 'where can I ask NVIDIA about this'. Refuse and route elsewhere for hands-on programming patterns, env prep and install verification, library API tutorials, or hardware/firmware mutation — those belong to doca-programming-guide, doca-setup, the per-library skills, and doca-hardware-safety.

Create a library-grade Vue composable that accepts maybe-reactive inputs (MaybeRef / MaybeRefOrGetter) so callers can pass a plain value, ref, or getter. Normalize inputs with toValue()/toRef() inside reactive effects (watch/watchEffect) to keep behavior predictable and reactive. Use this skill when user asks for creating adaptable or reusable composables.

Use when the user wants to run SQL — especially analytical SQL — on local files (parquet/csv/json), URLs, S3 paths, or remote databases (Postgres, MySQL, MongoDB, ClickHouse Cloud, Iceberg, Delta Lake) without setting up a server. Provides chDB — embedded ClickHouse SQL in Python with 1000+ functions, Session for stateful multi-step pipelines, parametrized queries, and cross-source joins via `s3()`, `mysql()`, `postgresql()`, `iceberg()`, `deltaLake()`, `remoteSecure()` table functions. TRIGGER when: user wants SQL on parquet/csv/files or across remote analytical sources; uses ClickHouse SQL features (window functions, windowFunnel, geoToH3, JSON path ops, Session, parametrized queries); imports `chdb` or calls `chdb.query()`. SKIP this skill for pandas-style DataFrame method-chaining (use chdb-datastore instead) or ClickHouse server administration.

Use when the user has tabular data (pandas DataFrame, parquet, csv, Arrow, json) and wants to filter, group, aggregate, join, or speed up slow pandas. Provides chDB DataStore — same pandas API, ClickHouse engine underneath. Also handles reading from S3, MySQL, PostgreSQL, MongoDB, ClickHouse Cloud, Iceberg, Delta Lake as DataFrames and joining across sources. TRIGGER when: user mentions DataFrame, parquet, csv, "fast pandas", "speed up pandas", or cross-source DataFrame joins; user imports `chdb.datastore` or `from datastore import DataStore`. SKIP this skill for raw SQL syntax (use chdb-sql instead), ClickHouse server administration, or non-Python DataStore API work.

Track and visualize ML training experiments with Trackio. Use when logging metrics during training (Python API) or retrieving/analyzing logged metrics (CLI). Supports real-time dashboard visualization, HF Space syncing, and JSON output for automation.

Training patterns for autoregressive neural PDE solvers (FNO, DeepONet, CNO). Covers rollout training, noise injection for stability, multi-component loss functions (H1, frequency-sensitive, boundary-aware), per-channel normalization for coupled multi-variable systems, and the PDEBench nRMSE metric. Use when training any neural operator that predicts time-dependent PDE solutions.

Write, validate, and improve XML documentation comments in C# source code. Use when asked to add, fix, review, or complete XML docs for C# APIs.

Reviews code diffs and files for security vulnerabilities (OWASP Top 10), error handling, complexity, naming conventions, and performance issues. Use when the user asks to review a PR, pull request, diff, merge request, or code changes.

Ingest a raw source document into the wiki. Reads the source, extracts key information, creates or updates wiki pages, maintains cross-references, and logs the operation. Use when the user adds a new source or says 'ingest this'.

Configures and runs agents with different adapters including Claude, OpenAI, CrewAI, Lyzr, and GitHub Models. Supports local execution, remote git repos, and one-shot prompts. Use when the user wants to run an agent, switch LLM providers, configure adapter settings, or launch agents from git repositories.