Maintains PRD implementation-phase status and artifact links. Always use when a PRP workflow records a planned, implemented, or merged phase in its source PRD, when the user asks to update PRD progress, or when the user invokes /prp-prd-update.

Review Chatto frontend implementation quality, including Svelte reactivity and lifecycle, component boundaries, design-system reuse, and unnecessary complexity. Use for every review that includes apps/frontend, including self-review, branch or PR review, and frontend architecture review.

Screen post-earnings gap-up stocks for PEAD (Post-Earnings Announcement Drift) patterns. Analyzes weekly candle formation to detect red candle pullbacks and breakout signals. Supports two input modes - FMP earnings calendar (Mode A) or earnings-trade-analyzer JSON output (Mode B). Use when user asks about PEAD screening, post-earnings drift, earnings gap follow-through, red candle breakout patterns, or weekly earnings momentum setups.

Analyze recent post-earnings stocks using a 5-factor scoring system (Gap Size, Pre-Earnings Trend, Volume Trend, MA200 Position, MA50 Position). Scores each stock 0-100 and assigns A/B/C/D grades. Use when user asks about earnings trade analysis, post-earnings momentum screening, earnings gap scoring, or finding best recent earnings reactions.

Execute a strict Red-Green-Refactor TDD cycle for one requirement at a time while applying KISS and DRY. Use when the user provides a business rule, acceptance criterion, bug fix, or feature requirement and wants test-first development, behavioral tests, failing tests first, TDD, red-green-refactor, or high-quality code. Works for unit, integration, UI component, API, and CLI tests across stacks.

Run the full DEFT AOI improvement loop for NVIDIA TAO VisualChangeNet / ChangeNet PCB inspection models: baseline evaluate, RCA, Cosmos AnomalyGen / AMP synthetic defects, k-NN mining, retraining, and deployment gating against a customer-defined primary metric and optional constraints. Use only when the request identifies an AOI / automated-optical-inspection, PCB-defect, VisualChangeNet, or ChangeNet workflow. Supports air-gapped/offline runs with pre-staged assets. Never infer AOI from generic iterative-improvement language. Do not use for CLIP / SigLIP image retrieval, attribute-labelled image data, standalone TAO training, one-off inference, generic anomaly generation, or RCA-only analysis.

Run container-backed AutoML / hyperparameter optimization (HPO) for NVIDIA TAO networks using AutoMLRunner. Handles algorithm selection (bayesian, hyperband, asha, bohb, llm, hybrid, autoresearch), WandB experiment tracking, job execution on any TAO SDK platform, result interpretation, and per-rec custom evaluation hooks. Use when the user mentions TAO AutoML, hyperparameter optimization, HPO, automl, automl_settings, AutoMLRunner, tao_automl, bayesian search, hyperband, ASHA, LLM-guided search, autoresearch, or wants to tune train/evaluate/inference/distill/prune/quantize for a TAO network. Model actions use the resolved image; venv training requires an explicit request. Platform-agnostic — runs on any SDK (Brev, SLURM, Kubernetes, Docker). Do not use generic "keep improving" language alone to override a matching domain-specific DEFT workflow; attribute-labelled CLIP / SigLIP image-retrieval loops belong to tao-run-deft-pas unless HPO is explicit.

Multi-step video annotation pipeline that turns raw videos into Chain-of-Thought training data — multi-level captions, structured descriptions, and QA pairs (MCQ, binary, open-ended) with reasoning traces, via VLM/LLM distillation. Use when the user wants to "create video training data", "generate video QA datasets", "build CoT reasoning traces from videos", "auto-label videos", or run the video_reasoning_annotation pipeline. Triggers include "video annotation", "video CoT", "video QA", "chain-of-thought", "video captioning pipeline", "video distillation".

Fine-tune any HuggingFace CV / VLM / LLM model on local NVIDIA GPUs inside an NGC PyTorch container when no dedicated TAO model skill matches. Use when the user wants to fine-tune a HuggingFace model (full or LoRA), train a vision / VLM / LLM model end-to-end, generate a reproducible HF training pipeline, smoke-test a HuggingFace model locally before scale-up, push a fine-tuned model to the HF Hub with a model card, or emit a self-contained rerun skill for an existing HuggingFace finetune. Supports image classification, object detection, semantic / instance / panoptic segmentation, depth estimation, image-text-to-text VLM (SFT / LoRA), and LLM SFT / DPO / GRPO. Six-step workflow: inspect and qualify, hardware and NGC image, research, generate and smoke, train + eval + infer, push and emit rerun skill. Do not use for any Hugging Face model ID claimed by a dedicated `skills/models/*` skill; the model skill and its declared execution environment take precedence.

设计、改写或审查有作者顺序的分页出版物、现场演示、连续长文与自动化报告。用于需要编辑取舍、叙事顺序、页型、网格、母版、来源、印刷或专业交接的任务；不用于持续内容站、自由数据探索、产品工作流或单张营销图。

Sweep open (or listed) PRs with up to 100 parallel agents: security-scan outside contributors, rebase onto main when behind (push --force-with-lease), approve pending first-time-contributor CI when relevant, optionally rebase in-house PRs, and report who should review. Supports full, changed-only, behind-only, and conflict-only scopes for cheap daily runs. Use when the user runs /pr-sweep (or /pr-inbound-sweep), or asks to "sweep PRs", "sweep inbound PRs", "security-check outside PRs", "rebase outsider PRs", "rebase our PRs", "approve waiting CI on PRs", "daily PR sweep", or "prep external PRs for review".

Sweep open (or listed) PRs with up to 100 parallel agents: security-scan outside contributors, rebase onto main when behind (push --force-with-lease), approve pending first-time-contributor CI when relevant, optionally rebase in-house PRs, and report who should review. Supports full, changed-only, behind-only, and conflict-only scopes for cheap daily runs. Use when the user runs /pr-sweep (or /pr-inbound-sweep), or asks to "sweep PRs", "sweep inbound PRs", "security-check outside PRs", "rebase outsider PRs", "rebase our PRs", "approve waiting CI on PRs", "daily PR sweep", or "prep external PRs for review".

Write a blameless incident postmortem under postmortems/ following the Google SRE shape — evidence-based timeline, trigger vs root cause vs symptom, contributing factors, what went well, and owned+dated+verifiable action items. Read when asked to write a postmortem, do an incident review, run a root cause analysis, write up the outage, retro on the outage, or when the user says we had an incident and wants it documented. Do NOT read to frame a proposal (use frame-a-proposal), write a spec (use write-a-spec), record a decision (use record-a-decision), or review a design (use review-a-design) — a postmortem documents an incident that already happened, it does not propose, specify, decide, or critique future work.

Reviews whether a design is SOUND — solving the right problem, derived from its stated goals and constraints — and emits ranked, evidence-backed findings, not edits. Read when asked to 'review this design', 'is this design sound', 'pressure-test this proposal', 'do a design review', 'does this solve the right problem', 'poke holes in this spec', 'should we build this', or to critique a proposal / spec / ADR / architecture or product decision. Do NOT read when the user wants to AUTHOR one of these — routing a new proposal is frame-a-proposal, a spec is write-a-spec, a decision record is record-a-decision, a postmortem is write-a-postmortem. Do NOT read for code review of a diff, or to fact-check individual claims (that is a correctness pass, a different job).

Records an architecture decision as a Nygard/MADR-shaped ADR under decisions/ — capturing the context that forced the choice, the options weighed, the decision itself, and its consequences in both directions, plus the supersedes chain that keeps a decision log honest. Read when asked to record an architecture decision, write an ADR, log the decision we made, document why we chose X over Y, capture this decision for the record, or supersede an old decision with a new one. Do NOT read to frame a proposal or explore an idea not yet decided (frame-a-proposal), to write a spec or implementation plan (write-a-spec), to write an incident postmortem (write-a-postmortem), or to judge whether a design is sound (review-a-design). This skill records a decision already made; it does not make one.

Read before modifying the scan pipeline (server/scan/session_events.py, server/scan/device_handling.py). Covers process_scan()'s call order and why it's load-bearing, the CurrentScan/Events/Sessions/DevicesView relationships, how a session actually closes (there is no close function), and the FIELD_SPECS field-write authority mechanism. Use this when touching device presence, connect/disconnect events, or session/timeline behavior.

Use when the user provides Warp commit SHA(s) and GitHub issue number(s) to assess, draft issue comments, post progress updates, or recommend whether issue threads should stay open or close.

Writing unit and integration tests for the tldraw SDK. Use when creating new tests, adding test coverage, or fixing failing tests in packages/editor or packages/tldraw. Covers Vitest patterns, TestEditor usage, and test file organization.

Deletes memories by search query or memory ID with confirmation before removal. Use when removing outdated decisions, incorrect memories, sensitive data, or cleaning up after experiments. Also handles undo of recent additions.

Guide for migrating PowerToys modules from WPF to WinUI 3 (Windows App SDK). Use when asked to migrate WPF code, convert WPF XAML to WinUI, replace System.Windows namespaces with Microsoft.UI.Xaml, update Dispatcher to DispatcherQueue, replace DynamicResource with ThemeResource, migrate imaging APIs from System.Windows.Media.Imaging to Windows.Graphics.Imaging, convert WPF Window to WinUI Window, migrate .resx to .resw resources, migrate custom Observable/RelayCommand to CommunityToolkit.Mvvm source generators, handle WPF-UI (Lepo) to WinUI native control migration, or fix installer/build pipeline issues after migration. Keywords: WPF, WinUI, WinUI3, migration, porting, convert, namespace, XAML, Dispatcher, DispatcherQueue, imaging, BitmapImage, Window, ContentDialog, ThemeResource, DynamicResource, ResourceLoader, resw, resx, CommunityToolkit, ObservableProperty, WPF-UI, SizeToContent, AppWindow, SoftwareBitmap.