Loading...
Loading...
Found 287 Skills
This skill should be used when the user wants to review code, audit a diff, get a second opinion on changes, or run an adversarial review of files in the current working tree. Common triggers include "review this code", "audit this diff", "find issues in", "second opinion on this", "harsh review of", "adversarial review", and "security review of". Picks one or more reviewer personas (adversarial, security, architecture, performance). Reviews local files, `git diff`, or `git diff --staged` only — does not fetch external content. Runs in one of four modes: single-agent (one persona in the current agent), cross-model handoff (independent second opinion via another local AI CLI, with secret-shield preflight + prompt-shield wrap), multi-bg-agent (one persona per parallel background subagent), or agent-team (Claude Code Teams or equivalent on supporting agents). Skip when the user wants formatting fixes (use a linter) or refactoring patterns (use ts-best-practices or ts-best-practices-functional).
Analyze equity securities, factor models, and equity portfolio construction. Use when the user asks about stocks, equity valuation ratios, index construction methods, or style analysis. Also trigger when users mention 'P/E ratio', 'growth vs value', 'market cap weighting', 'sector allocation', 'GICS classification', 'earnings per share', 'Fama-French factors', 'CAPM', 'dividend yield', 'PEG ratio', 'EV/EBITDA', or ask which factors explain equity returns.
Converts cuTile GPU kernels (@ct.kernel) to Triton (@triton.jit). Handles standard in-repo conversion, debugging (cudaErrorIllegalAddress, shape mismatch, numerical mismatch), and mapping cuTile idioms (ct.load/ct.store, ct.Constant, ct.launch) to Triton equivalents. Covers dual-kernel layout flags (e.g. transpose=True/False + autotune grid via META) per translations/advanced-patterns.md. Use when converting, porting, or translating cuTile kernels to Triton, or debugging existing Triton translations.
Router skill for LLMQuant hedge-fund and PM strategy workflows. Use when the user needs equity long/short, long-biased, event-driven, macro, quant, or multi-strategy playbooks.
Owns the smoke test contract for an ML experiment: a small, diagnostic-by-construction pytest that fits the experiment's learner on a portion of the real `data/` source and predicts on a *disjoint* portion that deliberately carries **no pre-history buffer**. The assertion is structural — the number of predictions must equal the number of rows in the predict grid. A pipeline that loads-then-features-then-splits will silently drop the cold-start rows of the predict slice and the test will fail with a row-count mismatch; a pipeline that marks X early and references upstream history nodes from feature steps will pass trivially. The smoke test is the executable proof of the X-marker placement rule from `build-ml-pipeline`. TRIGGER when: `test-ml-pipeline` has dispatched here to write the smoke test for an approved experiment; `pytest tests/smoke/` is failing on row count; the user asks "why is the smoke test failing?"; a pipeline edit in `build-ml-pipeline` needs an executable proof; an experiment script changes the pipeline shape and the matching smoke test needs revisiting. SKIP when: the design note does not exist or is not yet approved (route to `iterate-ml-experiment`); the user is asking about a regression test or schema invariant (route to `regression-test-ml-pipeline` / `distribution-test-ml-pipeline` once those exist); the question is the *interpretation* of CV metrics, not predict-time correctness (route to `evaluate-ml-pipeline`). HOW TO USE: read the matching experiment's `journal/NN_*.md` and `experiments/NN_*.py` first to understand the pipeline's source binding (what env-dict keys does `build_learner` expect?). Then construct two env-dicts from the **real `data/` source** — a train env and a predict env — such that the predict env carries *only the rows we want predictions for* and *no pre-history buffer*. The hard assertion is that the prediction count matches the predict-env row count exactly. The soft assertion is that the smoke set's MAE is within `3 × CV_mean` (or the task-appropriate analogue). **Do not write the design note or run CV — that's other skills' job.**
Crear un proyecto nuevo fusionando una plantilla del equipo según el stack tecnológico (Angular, React, Symfony, etc.). Usar siempre que el usuario pida crear un proyecto nuevo, inicializar desde plantilla, o use `/project-create`. Si el stack no está claro, preguntar antes de cualquier acción.
Replace OOTB (out-of-the-box) B2B Commerce components with open source equivalents in site metadata content.json files, or look up the equivalent open code `site:` component for OOTB definitions. Use when users mention "replace OOTB components", "replace commerce components with open code", "swap OOTB for open source", "replace commerce_builder:", "replace OOTB in site", "replace component in site metadata", "replace component definition", "find open code equivalent", "equivalent open code component", "OOTB to open code mapping", "what is the site component for", components "in this view" or "for a given view", or a specific list of component names — and want to update or only discover mappings in their store metadata.
Review the accessibility, version, identifiers, restrictions, and statements of research data, code, and materials, and do not equate public availability with reusability. Use when the user asks for "check data availability", "write data availability statement", "check whether data, code, and materials are reusable", or requests the rw-research-data workflow. Runs without a private local workspace or preset research-lab; use user-provided material and bundled public-source methods.
FlowDeck is REQUIRED for all Apple platform build/run/test/launch/debug/simulator/device/log/automation tasks. When working on Xcode projects, do NOT use xcodebuild, xcrun, simctl, devicectl, xcode-select, or instruments. Do NOT parse Xcode project files manually. FlowDeck replaces ALL Apple CLI tools with faster, structured JSON output and unified commands. Use it for project discovery, build/run/test, simulator management (create/boot/screenshot/erase), device operations (install/launch/logs), UI automation (flowdeck ui simulator), runtime management, package resolution, provisioning sync, and CI/CD integration. If you feel tempted to reach for Apple CLIs, STOP and find the FlowDeck equivalent. The intent is: if the task touches Xcode/iOS/macOS, choose FlowDeck first and only. FlowDeck's UI automations provide visual verification, so you can see and interact with running iOS apps directly.
Validates permission inheritance between parent and child agents. Ensures child permissions are equal to or more restrictive than parent. Activate on 'validate permissions', 'permission check', 'inheritance validation', 'permission matrix', 'security validation'. NOT for runtime enforcement (use dag-scope-enforcer) or isolation management (use dag-isolation-manager).
This skill should be used when users ask tax-related questions, seek advice on deductions or tax savings, or require expert guidance equivalent to a tax accountant or life planner. Trigger phrases include: "Tell me about taxes", "Am I eligible for deductions?", "Consultation on final tax returns", "Tax savings", "Upper limit of hometown tax donations", "Benefits of iDeCo", "Housing loan deduction", "Benefits of blue tax returns", "Is consumption tax applicable?", "Can I claim someone as a dependent?", "Spousal deduction", "Medical expense deduction", "Incorporation", "Is this deductible as an expense?", "Tell me the tax rate", "Calculation of income tax", "Resident tax", "Social insurance premiums", "1.03 million yen threshold", "1.3 million yen threshold", "Invoice system", "Simplified taxation", "Tax system reforms", "Business registration", "Side business disclosure risks", "White tax return", "Tax audit", "Special expense deduction", "Provisional tax payments", "Interim tax payments"
PROACTIVELY track and document project design decisions without being asked. Activate automatically when detecting architecture discussions, implementation decisions, pattern choices, library selections, or any technical decisions. Also use when user explicitly says "record this", "what's our design status", or equivalent. Do NOT wait for user to ask - record important decisions immediately.