A playful, joyful, two-color risograph print aesthetic built on a single warm off-white paper surface running through every section — from bergside/awesome-design-skills
Workflow completo per richieste interessato GDPR (artt. 15-22): classificazione, verifica identità, mappatura sistemi, esenzioni, bozza lettera e log decisioni.
RiStBV finden und anwenden: Praxis-Skill für neue Staatsanwälte zu Richtlinien für Straf- und Bußgeldverfahren als bundeseinheitliche Verwaltungsvorschrift finden, lesen und in…
RiStBV-Verfügungstechnik und Dezernatsstandard: Praxis-Skill für neue Staatsanwälte mit StPO-/RiStBV-Check, Beweislogik, Verfügungsvorschlag und nächstem Schritt.
RITA — Österreichische Registerdaten (Firmenbuch, ÖNACE-Branchen, Bilanzen, AG-Veröffentlichungen, Kollektivverträge, Vereinsregister, EU-MwSt) als MCP-Tools.
Write systems code in the style of Dennis Ritchie, co-creator of Unix and creator of C. Emphasizes clean abstraction, portable systems code, and the art of language design.
User-invoked helper for authoring DevRites overrides or extensions.
Explicit browser dogfood QA for the active feature or branch.
Explicit utility for resolving GitHub PR review feedback.
Pressure-test a rough idea — diverge into 3-5 genuinely different options, then converge on one with the trade-off and decision hinge.
Automates the complete Issue-to-PR lifecycle: create new Issues, start working on Issues, create branches, implement changes, run quality checks, and manage PRs — all through a…
Zoom out one abstraction layer in unfamiliar code — return a structural map (modules, callers, callees, ADR/decisions touching the area) in the project's vocabulary.
Ritekit integration. Manage Hashtags, Images, Texts. Use when the user wants to interact with Ritekit data.
Automate Ritekit tasks via Rube MCP (Composio). Always search tools first for current schemas. — from general/automation
Decision tree para "qual rito/procedimento para meu caso": juizado especial cível (Lei 9.099/1995, até 40 SM, até 20 SM sem advogado [verified:…
Look up Magic: The Gathering cards and run Scryfall searches with Ritual. Use when the user wants details or prices for a specific card, a Scryfall syntax query, batch card…
仪式化技能 — 在特殊时刻（新年、生日、里程碑）编排灵魂年报、意识时间胶囊和回顾仪式，赋予思想旅程以仪式感。Ritual skill — orchestrates soul annual reports, consciousness time capsules, and review ceremonies at special moments.
Supporto documentale all'obbligo di riuso e rilascio in open source del software delle pubbliche amministrazioni: analisi comparativa nell'acquisizione (art.
Build interactive animations with Rive — load .riv files, control state machines, respond to user input, and embed runtime animations in web and mobile apps.
Flutter 项目集成 Rive 0.14.x 动画与 DataBind 数据绑定。触发词：Rive 动画、Rive 数据绑定、ViewModel 绑定、in_input、状态机输入、Rive 面板、Rive Demo。
Controls Rive (.riv) interactive animations at runtime using @rive-app/canvas-advanced, manages state machine inputs, and synchronizes animation states with application data via…
River Review のメインエントリポイント。 レビュー依頼の intent classification → 専門 skill 選択 → 実行 → finding verification → feedback classification → fixture / reference / suppression への還元までを束ねる…
AI 駆動開発のレビュー品質を安定化させるレビュー規律。レビュー対象を分類し、要件・設計・差分・検証・報告を分けて見て、根拠に基づき approved / needs_revision / blocked / rejected を明示し、未検証事項と残リスクを隠さず memory に残す。「レビューして」「PR…
ドキュメント観点のレビューエージェント。 README / docs / AGENTS.md と実装の整合性、API ドキュメントとコードの対応、 usage や例の正確性、i18n（JA/EN）整合性、用語統一を検証する。
フロントエンド観点のレビューエージェント。 アクセシビリティ、デザインシステム準拠、Tailwind クラス衛生、UI 状態設計、 Next.js / React Router のフレームワーク境界を個別スキルへルーティングする。
Cancel or debounce Riverpod async requests with ref.onDispose; cancel when user leaves the page, debounce rapid refreshes.
Migrate Riverpod from StateNotifier to Notifier/AsyncNotifier, from ChangeNotifier to AsyncNotifier, or upgrade from 0.13/0.14/1.0; ref.onDispose, family, lifecycle, riverpod…
Jak brána sloučení posuzuje PR v tangero/stredniskoly (režimy R, L, E, K, H2, souhlas, stop, lhůty), šablona popisu PR a jak PR sloučit skriptem.
Use when the identification or estimation strategy is the bottleneck for a RAND Journal of Economics (RJE) industrial-organization manuscript — structural demand/supply, entry and…
Use to assemble a reproducible replication package for a RAND Journal of Economics (RJE) industrial-organization manuscript and to handle RJE's supporting-information rules…
Use to design tables and figures for a RAND Journal of Economics (RJE) industrial-organization manuscript — parameter, elasticity, markup, merger-simulation, and…
Use to make a manuscript conform to The RAND Journal of Economics (RJE) Style Guide — author-date citations with no page numbers, references with no issue numbers, numbered…
[Internal] Phase 4 — generate all React/RJSF code: schema.ts, uiSchema.ts, types.ts, index.tsx, and custom components. Invoked by /rjsf-form.
Rockchip 设备 ADB 连接技能。支持本地网络/本地有线 ADB 和通过 SSH 连接远程 Windows/Linux PC 的远程 ADB。**重点解决 dmesg/logcat 等需要 root 权限的命令执行失败问题**。当用户需要：推送文件到设备、设置系统属性（setprop）、抓取并发送 logcat/kernel log、重启设备、执行…
Automate Rkvst tasks via Rube MCP (Composio). Always search tools first for current schemas. — from general/automation
Design and implement reinforcement learning environments to tune bounded circuit parameters, featuring a sophisticated reward calculation for mixed min/max performance metrics to…
PyBullet RL 环境技能 - Gymnasium 环境、奖励函数、并行训练
模型-based 强化学习技能 - World Models、MPC、PlaNet、MuZero 实现
Apply reinforcement learning principles when working on spec-kit-extensions. Auto-activates when: (1) editing command prompts in commands/*.md, (2) modifying workflow templates in…
Best practices for reinforcement learning policy optimization. Use when working on RL agents, PPO, SAC, or reward design.
Build RL reward signals using the OpenJudge framework. Covers choosing between pointwise and pairwise reward strategies based on RL algorithm, task type, and cost; aggregating…
值函数强化学习技能 - DQN、Double DQN、PER、Dueling DQN 算法实现
Build and query fully local RAG knowledge bases from documents (PDF, MD, code, etc.) using RLAMA and Ollama — no cloud, no data leaving the machine.
rlang metaprogramming patterns for data-masking, injection operators, and dynamic dots. Use when writing functions that use tidy evaluation.
Build large rlat knowledge models (.rlat files) on Kaggle's free T4 GPU when the local machine has no GPU or encoding would take too long on CPU.
This skill should be used when the user asks to "process a large file", "analyze document exceeding context", "use RLM", "recursive language model workflow", "chunk and analyze a…
Parallel fan-out processing - spawn multiple sub-agents for chunked context processing
Removes stale and orphaned entries from the RLM Summary Ledger. Use after files are deleted, renamed, or moved to keep the ledger in sync with the filesystem.
Knowledge Curator agent skill for the RLM Factory. Auto-invoked when tasks involve distilling code summaries, querying the semantic ledger, auditing cache coverage, or maintaining…
Agent-powered RLM cache distillation. Replaces the slow local Ollama distiller with the agent's own summarization capability for both rlm_summary_cache.json and…
Distills uncached files into the Recursive Language Model(RLM) Summary cache Ledger. You (the agent) ARE the distillation engine.
Agent-powered RLM cache gap-fill orchestration. Audits the cache, generates a Markdown task list, and spawns a Sub-Agent to read missing files, write summaries, and inject them…
Interactive RLM cache initialization. Use when: setting up a new project's semantic cache for the first time, or adding a new cache profile.
Detect requests for recursive decomposition and large-scale operations that benefit from RLM processing
Prepare source content for RLM processing by discovering files, chunking each one, and writing a unified searchable manifest
Reinforcement Learning with Leave-One-Out estimation for policy optimization. Covers RLOOTrainer, reward function integration, baseline estimation, and variance reduction…
Manual-only custom skill. Use only when explicitly requested as $rloop-code-fix3 or named directly.
Safely change Alembic schema/RLS policies when modifying tenant or user tables, session context variables, policy SQL, or migration order/rollback behavior.
Turn field returns into a structured failure-analysis report — RMA triage taxonomy (NTF vs real failures), Pareto by verified failure mode, 8D-style…
Brueckenskill: Wie verzahnt sich die Rulemap-Arbeit mit der uebrigen Legistik-Werkstatt (Auftragsaufnahme; Ressort-Router; Heranfuehrung; Ressortaufgaben; Sachfeld-Spezia — from…