В каталоге 183 730 навыков в 14 категориях.
Generate or maintain a project-local verify skill that launches, drives, and proves the real app with a user-POV feature...
Review recurring cross-feature evidence and propose durable project guidance.
Re-plan existing work when reality invalidates the plan: reslice a slice that is too big, repair drift, reorder dependen...
Polish the active feature's code and any touched UI before review. Use for finish or normalization requests; not for rep...
Project-grounded verdict for adopting, switching, rejecting, or revisiting a named external technology, library, platfor...
Explicit utility for resolving GitHub PR review feedback.
User-invoked throwaway prototype for one logic or UI design question; delete or absorb after the answer.
Prove a completed feature with tests and the full test suite, build/typecheck/lint, end-to-end/browser evidence, screens...
Express lane for a small reversible change: typo/copy/config, rate-limit constant, error message, local variable rename,...
User-invoked resume verb for answering, dropping, or batch-resolving open `questions.md` gates.
Review polished feature diff for correctness, readability, architecture, security, tests proving acceptance, Critical/Im...
Decide GO/NO-GO for an active feature; /rite-ship owns commit, push, tag, and close.
Commit, push, tag, archive, or close a sealed feature after /rite-seal GO. Use for repository mutation; not for GO/NO-GO...
Specify new, vague, or high-risk behavior before code. Use for features, auth, migrations, or public API changes; not fo...
User-invoked read-only active-feature report: phase, active slice, next action, evidence, open questions, drift, risks,...
Temper a readied spec before planning. Use when the user says "temper this", "strategy review", "pre-mortem the spec", o...
Audit and reconcile an older released DevRites workspace. Proves a current-contract defect, then routes its phase owner...
Review a defined engineering plan before code. Use for plan vetting or lock-in; not for implementation review or final r...
Observe one GitHub PR and CI state without mutating code, Git, threads, checks, or shared state. Safe for native host sc...
User-invoked read-only structural map of unfamiliar code: modules, callers, callees, and relevant decisions.
Rithum B2B patterns and distribution API
Design repeatable fan rituals, naming systems, participation loops, and recurring community formats, then output a ritua...
Create original short videos using the 仪式黑场复位｜期待微笑、吹灭中断与冷光回归 Creative DNA for MiniMax H3 or Seedance 2.0. Use when the u...
Deterministic deep research via RivalSearchMCP. 9 tools: 5-engine web search (DuckDuckGo/Bing/Yahoo/Mojeek/Wikipedia), 9...
Build interactive animations with Rive — load .riv files, control state machines, respond to user input, and embed runti...
Use when implementing Disney's 12 animation principles with Rive interactive animations
State machine-based vector animation with runtime interactivity and web integration. Use this skill when creating intera...
Animaciones Rive (.riv) con máquinas de estados, inputs (boolean/number/trigger), ViewModel data binding y eventos en Re...
| ID | flutter-riverpod-state |
Use when setting up providers, combining requests, managing state disposal, passing arguments, performing side effects,...
| Atributo | Valor |
Migrate Riverpod from 2.0 to 3.0; automatic retry, paused listeners, legacy providers import, Ref simplification, Family...
Enable automatic disposal of Riverpod providers when they have no listeners; keepAlive, onDispose, invalidate, ref.keepA...
Cancel or debounce Riverpod async requests with ref.onDispose; cancel when user leaves the page, debounce rapid refreshe...
Use Riverpod code generation (@riverpod, riverpod_generator) and hooks (hooks_riverpod, HookConsumerWidget, flutter_hook...
Use Riverpod Consumer, ConsumerWidget, and ConsumerStatefulWidget to read and watch providers in widgets; WidgetRef, bui...
Use ProviderScope in Flutter and ProviderContainer in Dart for Riverpod; where provider state is stored, overrides, obse...
Eagerly initialize Riverpod providers at app startup by watching them in a root Consumer; handle loading/error in the in...
Use Riverpod family providers to pass parameters and cache per parameter; FutureProvider.family, NotifierProvider.family...
Answers Riverpod FAQ (ref.refresh vs invalidate, ConsumerWidget vs StatelessWidget, Ref vs WidgetRef, reset all provider...
Migrate from package:provider to Riverpod; ChangeNotifierProvider, ProxyProvider to ref.watch, context.watch to ref.watc...
Install Riverpod (flutter_riverpod or riverpod), wrap the app in ProviderScope, run a hello-world provider, and optional...
Migrate Riverpod from StateNotifier to Notifier/AsyncNotifier, from ChangeNotifier to AsyncNotifier, or upgrade from 0.1...
Use Riverpod mutations for UI-driven async operations like form submit; Mutation.run, MutationIdle/Pending/Success/Error...
Use ProviderObserver to log or debug Riverpod provider lifecycle; didUpdateProvider, ProviderScope observers, naming pro...
Persist Riverpod notifier state offline with Storage and persist(); riverpod_sqflite, JsonPersist, key, destroyKey, cach...
Override Riverpod providers for tests, debugging, or environment-specific behavior; ProviderScope and ProviderContainer...
Declare and use Riverpod providers (Provider, FutureProvider, StreamProvider, NotifierProvider, AsyncNotifierProvider, S...
Implement pull-to-refresh with Riverpod using RefreshIndicator and ref.refresh; show spinner on initial load, show previ...
Use Ref and WidgetRef to read, watch, listen, invalidate, and refresh providers; onDispose and onCancel lifecycle; ref.r...
Customize Riverpod automatic retry on provider failure; retry function, per-provider and global retry, disabling retry,...
Scope Riverpod providers to a subtree using overrides and dependencies; page-specific behavior, ListView optimization, a...
Reduce rebuilds with ref.watch(provider.select(...)); select a subset of state so widgets rebuild only when that part ch...
Test Riverpod providers and widgets; ProviderContainer.test, unit tests, widget tests with ProviderScope, tester.contain...
Use when the user asks to download, back up, export, or search their own Riverside.com (Riverside.fm) podcast or video a...
Capture decisions and requirements from conversation history. Use when user says "harvest", "capture decisions", or "sav...
Initialize Rivet by scanning codebase structure. Use when SessionStart hook reports no .rivet/systems.yaml, when user sa...
Use when using Rivet SDK.
Reference skill for Zoom Rivet SDK. Use after routing to a Rivet-based server workflow when implementing auth handling,...
Zoom Rivet SDK for JavaScript/TypeScript server-side integrations. Use for auth handling, webhook event consumers, API e...
Beginner-friendly reverse-engineering workflow for Rizin Binary Analysis. Use it to collect evidence, choose static or d...
rj-auth-agent
rj-devops-agent
Generate professional graphics, thumbnails, banners, ebook covers, social media visuals. Auto-writes optimized generatio...
rj-linear-agent
rj-meta-agent
Full social media content engine. Creates TikTok scripts, Instagram carousels/reels/captions, LinkedIn posts, X threads,...
rj-stripe-agent
RK1 NPU pool — rkllama server con RKLLM models en RK3588 NPU de los nodos TuringPi 2. Gotchas de device exclusivo, token...
Automate Rkvst tasks via Rube MCP (Composio). Always search tools first for current schemas.
Manage Reinforcement Learning (A/B testing) experiments via Drush CLI. Thompson Sampling multi-armed bandit experiments:...
Design and implement reinforcement learning environments to tune bounded circuit parameters, featuring a sophisticated r...
训练与推理数据不一致的端到端根因分析。当模块映射/值比较不足以定位问题时使用，可追踪首个可信的分歧边界，过滤融合或结构性误报，遵循生产者-消费者链，并生成包含具体假设和证据的根因报告。
通用训推一致性(prefill)的 dump 数据分析 skill。分析**已采集**的训推两侧 dump:探查 dump 结构 → 语义边界映射(不要求算子同名)→ 逐边界精确门禁比对 → 定位首差异 → ULP 量化区分舍入/逻辑级 →...
Systematic RL debugging - diagnose learning failures, common bugs, diagnosis trees
Gym/gymnasium API - custom environments, spaces, wrappers, vectorization, debugging
Rigorous RL evaluation - statistical protocols, train/test discipline, metrics, generalization
Master RL theory - MDPs, value functions, Bellman equations, value/policy iteration, TD
Reinforcement learning for ion shuttling optimization on trapped-ion quantum computers
训推一致性(prefill)采集侧:为训练/推理两侧采集可比的 prefill dump(输入对齐 PROMPTS_ONLY → 参数对齐校验(dump 前前置:校验两侧 config 超参/结构/权重,不一致输出参数不一致点并对齐)→ m...
Reinforcement Learning for Quantum Error Correction control methodology. Based on Google Quantum AI's Willow processor...
Build RL reward signals using the OpenJudge framework. Covers choosing between pointwise and pairwise reward strategies...
RL training for robot control using simulation with sim-to-real transfer
Extend RL to open-ended tasks using structured rubrics as reward anchors, enabling fine-grained evaluation of subjective...
Compute RLAIF AI-labeler alignment, pairwise win rate, harmless rate, and proxy target consistency metrics.
Build RLAIF pairwise AI-feedback labels from label-token logits, optional chain-of-thought rationales, and swapped-order...
Train and validate tiny soft-label pairwise reward models that distill RLAIF AI preference distributions with cross-entr...
Local RAG system management with RLAMA. Create semantic knowledge bases from local documents (PDF, MD, code, etc.), quer...
Understanding Reinforcement Learning from Human Feedback (RLHF) for aligning language models. Use when learning about pr...
Comprehensive guide to rlhf. Master the concepts, implementation, best practices, and real-world applications of rlhf in...
Set up and run the full RLHF pipeline (SFT, reward model training, RL from reward model) using the Tinker API. Use when...
Autonomous RLHF feedback capture - Claude self-captures mistakes and successes
Executing reinforcement learning from human feedback loops.
Use rLLM for language-agent evaluation, dataset/task management, RL/SFT post-training, CLI setup, and gateway-backed rol...
Run a Recursive Language Model-style loop for long-context tasks. Uses a persistent local Python REPL and an rlm-subcall...
Process large codebases (>100 files) using the Recursive Language Model pattern. Treats code as an external environment,...
Use RLM (Recursive Language Models) for verified code execution, calculations, data analysis, and task decomposition. Ex...
Recursive Language Models (RLM) CLI - enables LLMs to recursively process large contexts by decomposing inputs and calli...
Process large codebases (>100 files) using the Recursive Language Model pattern. Orchestrates parallel sub-agents to map...
Parallel fan-out processing - spawn multiple sub-agents for chunked context processing