В каталоге 183 730 навыков в 14 категориях.
Manage shared open-ended quests through one canonical Markdown lifecycle. Use for /quest, listing or opening quests, sta...
Multi-agent quest orchestration. Plans, reviews, builds, and fixes features through coordinated agent handoffs.
Game planning and production agent responsible for GDD structuring, game balance mathematics, narrative design, economy...
Sustained search quest — iterative exploration of ill-defined problems with coverage tracking, where the journey maps th...
Extract quest entities from narrative text. Use when analyzing quest chains, objectives, moral choices, prerequisites, r...
Expand a quest hub with recurring NPC voices, items, and artifacts.
Create, manage, and track quests for Ezra. Use when adding quests, checking progress, updating categories, or managing p...
Interrogate an ask before acting on it. What was asked, why, is it still right, and where does it fit. Use at the start...
Search and fetch real K12 primary, middle, and high school questions from the Tizhuang question-bank service by subject,...
Starts a local question form (question-board) where the user answers several independent agent questions on one screen,...
Quy trình xử lý Questions kỹ thuật được giao cho FrontendWeb. Dùng khi: kiểm tra câu hỏi mới, trả lời câu hỏi từ agent k...
Take a surface question and forge the question actually worth asking — diagnose what's broken in the asked question (smu...
Workflow for analyzing ambiguous data questions. Covers decomposing questions, identifying implicit assumptions and edge...
Create original short videos using the 功能问答闭环｜人物疑问由设备状态完成证明 Creative DNA for MiniMax H3 or Seedance 2.0. Use when the us...
Systematically resolve questions - determine if answerable, gather evidence
Write discussion or text-dependent questions at a target rigor (Socratic, close reading). Do NOT use for assessment item...
Help users run question-storming sessions to explore problem spaces. Use when someone needs to understand a new domain,...
Use when several well-reasoned fixes on the same hypothesis have all failed, or when a symptom looks impossible.
Unified entry skill that converts a user's natural-language question into a collaboration frame and prompt pack, then ro...
Advanced reasoning skill integrating Atom of Thoughts (AoT) and Chain of Verification (CoVe) frameworks. Use when facin...
Use this skill when facing complex problems requiring rigorous reasoning, systematic decomposition, or factual verificat...
Guide for effective questioning in GSD
Fresh-session security questionnaire response for {{projectName}}. Parses a new inbound questionnaire from {{questionnai...
Ensures questions are answered literally before taking action. Triggers on user input containing '?' or patterns like 'w...
QuestPDF report generation with fluent C# API. Use when generating PDF documents, designing report layouts, creating inv...
A standardized framework for AI agents to track and guide humans through complex long-term tasks. The quest is the singl...
Use when implementing new features in Quetrex. Ensures TDD, TypeScript strict mode, Next.js App Router patterns, ShadCN...
Defer a request to run after the current turn instead of interrupting it.
Rule under the delivery law for a tree on GitHub — the work queue audit. Load when editing the audit and its modules, or...
Pattern of rule queue-audit. Load when the work queue audit has printed lines — running it, and the move that answers ea...
Stack prompts in queue while agent runs, minimizing context switches to achieve sustained 6k lines per day output and pr...
Reconcile the task queue against everything the user has asked in this session. Use when the user says "queue check", "y...
Queue bug fixes and hotfixes to the portfolio manager pipeline for background execution. Converts fix requests into HOTF...
Use when ending a turn, finishing a slice, blocked on another agent's work, or escalating to a human — durable work hand...
Implements background job processing with BullMQ/Redis including job queues, workers, scheduling, retries, and monitorin...
Manage the content processing queue for batch content consumption. Use when user mentions queue, batch later, save for l...
You are the multiple queue system architect for Modcaster, solving the
Comprehensive guide to monitoring message queues including RabbitMQ, Redis, and Kafka for production systems. This skill...
Use when an "enable observability" card asks for queues, or a worker's queue.backlog / consumer lag signals are unbound...
Monitor message queues, job processing, and detect backpressure
Design safe queue consumers and retries. Use when a mid-level developer needs reliable background processing.
Vercel Queues guidance — durable topics with at-least-once delivery, independent consumer groups, retries, delays, and i...
Design and operate Laravel queues, jobs, workers, and Horizon with retry safety, idempotency, failure handling, tests, a...
QUIC channel quality grading with BBRv3 congestion control analysis. Classifies network paths into GF(3) tiers based on...
Execute a quick task with GSD guarantees (atomic commits, state tracking) but skip optional agents
Lightweight analysis for straightforward decisions. Compresses research, evaluate, critique, and synthesize into a singl...
Harmonia express lane - implementer plus lead-solo review for trivial fixes. Use ONLY when explicitly invoked as /harmon...
Streamlined code review for rapid assessment and targeted feedback
Quick mode for the rest of the session. Instead of CI's full checks, a change runs only the checks it can affect (format...
Tracked lightweight execution with composable rigor flags: --trivial, --discuss, --research, --full. Covers zero-ceremon...
Implement small Phoenix changes without planning — add validations, update routes, fix components, create migrations. Us...
Fast ticker analysis for /analysis page. Provides quick BUY/SELL/HOLD recommendations based on technical indicators, rec...
Lightweight brainstorming for bug fixes, small features, or code improvements that need clarification before implementat...
Quickly produces accurate calculation results when a user needs arithmetic, unit conversion, or mathematical formula sol...
Turn dictated notes, ideas, list items and tasks into faithful text with honest persistence confirmation.
scripts/・.claude/hooks/・eslint-rules/・.claude/skills/ 配下のスクリプトを編集した直後の軽量レビュー。バグ・セキュリティ・ESLint で落とせない決まりの3観点だけをメインの会話で見て、...
Create a git commit with a short message (up to 50 characters). Use when the user asks to commit changes with a short/co...
簡易コミット。変更をステージング、コミットメッセージ生成、コミット実行を一括で行う。PRは作成しない。トリガー: /quick-commit, クイックコミット, 簡易コミット
测试失败时免登跳转原地排查修复。触发：排查、纠错、debug、定位符失败、超时、元素找不到、断言失败。
Lightweight spec for small changes — tuning adjustments, minor mechanics. Embeds directly into stories; skips full GDD.
Create a lightweight approved design specification for a bounded change that does not require a full GDD.
Lightweight design spec for small changes — tuning adjustments, minor mechanics, balance tweaks. Skips full GDD authorin...
Lightweight design spec for small changes — tuning adjustments, minor mechanics, balance tweaks. Skips full CDD authorin...
Implementer rapidement un petit fix ou une petite feature sans le workflow complet feature-planner / sprint-planner / de...
Implement a story tech spec end-to-end. Quick Flow
ドキュメント編集直後の軽量レビュー。よく指摘される項目だけを高速にチェックし、その場で修正する。「quick-doc-review」「軽くdocチェックして」と指示されたとき。大掛かりなレビューは /doc-review。
Execute a bounded Coval evaluation on explicit test cases, then audit conversation, recording and metric evidence. Use w...
Prime the brain for a context switch with one concrete example. Point at a PR, a tech design, a plan, a Mikado graph, an...
Close out a change without the deep review loop: stage, simplify code and docs, run the project's checks, smoke test, up...
Handle a small fix or maintenance task locally end-to-end — no PR, but full review gates and a confirmed local merge int...
Fast bug fix: diagnose the issue, apply minimal fix, verify build passes, run targeted review.
Makes a small, obvious fix directly, without the feature pipeline: a typo, a reversed condition, a missing null check, a...
Applies inline Quick Review findings without review artifacts. Use when choosing Apply fixes after quick-review, fixing...
Lean solo-developer workflow for rapid spec-to-implementation with minimal overhead.
Rapidly scaffold and implement a playable game — no assets, design, audio, deploy, or monetize. Get something on screen...
Clarify a task and pause for plan approval before execution. Use only when the user explicitly requests Quick Grill.
Force quick interview depth for this session. Use when user says '/quick-interview' or 'quick interview mode'.
確認不要で手早く GitHub Issue を起票する。思いついた要望・課題・バグ・割れ窓の起票に使う。「quick-issue」「issueを起票して」「issueを作って」と指示されたとき。
Quick update to today's journal without full review. Use when user wants to quickly log something they did, add a journa...
Use when changing what kasane tells a user about where they are in a series — Quick lookup, the episode/chapter rail, ar...
Identify trivial, low-risk PRs in the `ready for maintainer review` queue of <upstream> that pass every quality gate and...
Create multiple UI design mockups in parallel. Use when asked to create mockups, wireframes, or design variations for a...
Fast path for a small model or back-of-envelope analysis: minimal spec, minimal checks, clear 'not for publication' labe...
Use when you need a bite-sized, TDD-driven implementation plan but do NOT have a brainstorm-beagle spec to plan against....
This skill should be used when the user asks to "create a quick plan", "draft a plan", "capture this idea", "plan this f...
Universal pre-PR checklist that works in ANY project, with or without MCP tools. Use before creating a pull request to e...
在一个工作流中生成包含竞品分析的完整 PRD。当用户需要带竞品上下文的 PRD、想要快速记录功能、说"写一个带竞品对比的 PRD"、或需要综合的产品需求文档时使用。当用户提到创建 PRD 并附带竞品研究，或说"分析竞品并写需求"、"快速为...
Lightning-fast quality check using parallel command execution. Runs theater detection, linting, security scan, and basic...
/============================================================================/
Execute simple network status queries that require 1-2 commands. Use when user asks to "check device status", "show inte...
Use when the user wants each agent response to end with a red/yellow/green status line showing whether the work is finis...
Add or follow a red, yellow, or green status-line convention. Use for compact agent completion status.
This skill should be used when users need comprehensive research on a topic requiring exploration of multiple sources, s...
Automatically perform a fast, reliable web lookup when the user conversationally says "araştırır mısın", "bir bak", "bak...
Performs a fast, focused code review checking for common issues, security vulnerabilities, and best practices without ov...
Reviews uncommitted changes inline without saving by default. Use when requesting a quick review, checking a small local...
Perform rapid initial screening using only sanctions, PEP, and adverse media checks for quick risk assessment
Create a quick but complete technical specification. Quick Flow
轻量级变更规范，适用于小型变更、配置调优、微调，产出精简的变更说明。