Use when user wants to update requirements-dev.in with latest PyPI versions while preserving version patterns
Use when the user asks to review, audit, score, repair, or rewrite prose against the be-serious scholarly textbook register; when checking for slang, sycophancy, emoji, casual…
System architecture and API design with multi-AI consensus — use for design reviews and new subsystems
After the learner demonstrates understanding of a concept, present near-transfer and far-transfer challenges.
Analyse a learning task for cognitive load problems and recommend specific design improvements. Use when tasks overwhelm students, instructions feel complex, or materials need…
Structure a decision or design challenge through multiple perspectives before committing to action. Use as a synthesis step after scoping, mapping, and dilemma navigation when a…
Tier vocabulary from a text or topic into everyday, academic, and technical categories with teaching priorities.
Apply the principle of Immersion — designing for sustained focus and engagement, where the user becomes absorbed in the activity and loses awareness of the surrounding…
Anchor a multidisciplinary unit in a real-world phenomenon that requires multiple subject lenses to understand.
Use as a one-time design setup for UI, product, landing-page, or brand-heavy work. Scans the project for design context, asks only the UX questions that cannot be inferred, then…
Design a single-point rubric with one criterion and open columns for evidence. Use for student self-assessment, peer feedback, teacher formative feedback, or pre-task planning.
Evaluate a teacher-drafted central historical question for its capacity to drive genuine historical inquiry.
Use when building, reviewing, or refactoring a Remotion project, especially parameterized launch or demo videos with shared props schemas, calculateMetadata, Sequence and Series…
Capture a URL into a full-page screenshot, cropped UI item PNGs, and a JSON manifest. Use when the user says `separateweb capture <url>`, asks to capture a website, or wants UI…
Stage exploration before instruction on complex problems. The learner produces two attempted approaches before consolidation — which builds on those attempts, not from scratch.
Temporary inboxes for agent signup QA — create disposable addresses, wait for verification email, extract OTP or magic links.
Generate elaborative interrogation prompts that deepen encoding through targeted why and how questions.
Design structured perspective-taking activities with anti-projection guardrails. Develops genuine understanding of complexity across history, social sciences, and literature — not…
Connect to MySQL and run read-only queries to inspect table data. Use when the user wants to query MySQL, show tables, view table contents, check schema, or run read-only SQL.
Maven 编码质量闸口（编译 + 单测 + 静态分析 + 启动检测），只做验证不做修复，问题统一记录到 qa-pending.md。当编码完成后需要执行质量门禁时使用，也可单独触发。关键词：QA、质量验证、编译检查、单测、静态分析、启动检测、mvn verify、质量闸口。
URL validation and content sanitization for untrusted sources — use when handling external input safely
Switch to Knowledge Work mode for research and writing — use when task is non-code focused
Create self-explanation prompts that deepen understanding of worked examples, texts, or diagrams. Use when students read material passively without engaging with underlying…
Implement Zagrosi Forge section files with test-first development, focused review, documentation updates, and git hygiene.
Design forms that exploit closure — suggesting shapes through partial outlines, negative space, or strategic gaps so the user''s perception completes them.
List active session overrides scoped to the caller's tenant — useful for auditing dangling overrides or confirming an override is in effect before retrying
Generate slide deck presentations from briefs — use when you need slides, pitch decks, or visual summaries
Analyse the language demands of a classroom task to identify barriers for EAL and multilingual learners.
Create a writing scaffold teaching the genre conventions specific to an academic discipline. Use when students write lab reports, historical essays, or other discipline-specific…
Compare and synthesize findings across multiple completed DeepScan reports. Use when the user wants cross-run analysis, trend comparison, or a unified summary from several…
Apply behavioral mimicry — making an interface element behave like a familiar physical object so the user''s physical-world intuitions transfer to the digital interaction.
Use when reviewing uncommitted or staged git changes before commit. Trigger on: 帮我 commit, 我要 commit, commit 一下, 准备提交, pre-commit, 提交前检查, 看下这次修改, commit 前看一下, I want to commit,…
Use when you need the latest stable JuliaLang version number (e.g., to fill `VERSION=` in an install script) instead of hard-coding a value
Behavioral guardrails for Cavekit agents. Four principles — think before coding, simplicity first, surgical changes, goal-driven execution — that prevent over-engineering, silent…
Use when starting any conversation - establishes how the development-skills plugin works and how to invoke its components on each platform (Claude Code, Codex). Read first.
Modify a classroom task with language scaffolds that preserve cognitive demand for EAL learners. Use when adapting existing tasks for students at different English proficiency…
Apply deliberate dissimilarity (contrast) to distinguish elements that need to be perceived as different — primary vs. secondary actions, normal vs. error states, foreground vs.
Design an error analysis protocol to diagnose the root cause of student mistakes and misconceptions. Use when error patterns appear in student work and targeted feedback is needed.
Trace codepaths in diffs, map against tests, auto-generate missing coverage — use before shipping PRs
Interpret learning analytics data and translate dashboard findings into actionable teaching decisions. Use when reviewing LMS data, quiz patterns, or engagement metrics.
Design a checking-for-understanding protocol with specific techniques for each lesson stage. Use when planning systematic comprehension checks during explicit or direct…
Use when the user asks about Codex token usage, model/reasoning efficiency, usage dashboards, CSV exports, or per-session/per-turn Codex usage stats from local logs.
错误经验库：自动捕获错误模式、根因和解决方案，支持查询和反馈更新。 当遇到 build error、runtime error 或需要查找历史错误解决方案时使用。
Surface the user's recent AxonFlow governance decisions — answers "what just got blocked", "show me my recent denials", or feeds a decision-history forensic flow
How to write Blueprint-quality blueprints that AI agents can consume effectively. Covers implementation-agnostic blueprint design, testable acceptance criteria, hierarchical…
Route ordinary init, review, and security requests to Claude-native capabilities first; escalate to Octopus only when multi-LLM diversity adds value
Use when the task is to get or use amoCRM OAuth access, inspect pipelines/statuses/fields, work with amoCRM data over API, prepare full-control private integrations, or build…
Используй только внутри активного Codex Project Autopilot-проекта для deployment/handoff по его плану; не включай для обычных deploy-задач вне автопилота.
Expert multi-AI code review with inline PR comments — use for thorough quality and security analysis
为编码工作流提供 Langfuse 链路追踪能力。当执行 logic-layer-method-impl 等编码 skill 时，自动上报每个大步骤（识别模式、代码生成、编译、启动、单元测试、代码修复）的开始/结束事件到自部署 Langfuse，实现全流程可观测。凡用户涉及编码流程监控、追踪、可观测性、Langfuse 上报时均应触发此…
Use the OpenProject plugin MCP tools to inspect projects and manage work packages in a configured OpenProject instance.
Apply typeface and size choices for legibility — picking the right typeface for the use case (display, body, code, UI) and sizing it appropriately for the rendering context.
High-compression professional communication mode. Use when the user wants fewer tokens, less reading, no filler, compact coding-agent status, terse technical answers, or…
Verify and design for user-base scaling — broader audiences, more diverse use cases, more edge cases, behaviors that weren''t anticipated.
Structure a student's self-determined project with mentoring checkpoints, competency alignment, and reflection.
Given an Entropy Data data product URL or id, fetch its data contracts (output port ODCS files written next to the SQL under models/output_ports/v<N>/, input port ODCS files…
HTTP API-based documentation server (always running). Questions about project architecture, conventions, decisions, code structure, tech debt, env config, progress, or doc health.
Prune accumulated complexity from a product — features, options, settings, code paths that no longer earn their place.
AI Agent 架构模式目录。提供 ReAct、Multi-Agent Conversation、Multi-Agent Workflow、 RAG Agent、Tool-Use Agent、Autonomous Agent 六种核心模式的参考架构、组件拓扑、 数据流、设计决策和框架无关的最佳实践。供 agent-dev-workshop Phase 2…
Redesign a direct instruction sequence to include productive struggle before the explanation phase. Use when teaching concepts that benefit from failure-first approaches.