A pipeline execution strategy where downstream stages start before upstream stages finish, using staggered timing with configurable delays.
Review a PR across multiple dimensions — description, code changes, code scan, unit tests — using parallel subagents. Supports GitHub, GitLab, and enterprise platforms.
Present options with trade-offs for informed decision-making — use when choosing between approaches
Apply the principle of Mimicry — borrowing the form, behavior, or visual language of something familiar to make a new design recognizable.
High-compression professional communication mode. Use when the user wants fewer tokens, less reading, no filler, compact coding-agent status, terse technical answers, or…
Analyse student work against criteria to identify specific gaps between current performance and learning objectives.
Set up, index, and manage SocratiCode codebase indexing. Use when the user wants to index a project, check infrastructure health, start/stop file watching, configure context…
轻量级快速执行模式，跳过完整 /team-* 链路，适用于小型、低风险、边界清晰的任务。 融合 GSD quick-mode 理念，在保持质量底线的前提下大幅缩短交付路径。
Resume an interrupted workflow run with verify-first strategy — loads sidecar state, verifies the last step, and continues execution.
Apply natural mapping — the strongest form of mapping, in which the spatial position, motion, or shape of a control directly corresponds to what it affects.
Evaluate a teacher-drafted central historical question for its capacity to drive genuine historical inquiry.
End-to-end Frappe and ERPNext implementation guidance spanning backend Python, backend JavaScript surfaces, Vue or React frontends, customizations, and bench-aware delivery.
Multi-AI requirements scoping using Codex and Gemini CLIs (Double Diamond Define phase)
Design a Concrete-Pictorial-Abstract learning sequence for a mathematical concept using manipulatives.
Create self-explanation prompts that deepen understanding of worked examples, texts, or diagrams. Use when students read material passively without engaging with underlying…
Design targeted interventions that strengthen belonging and inclusion for specific classroom dynamics.
Analyse existing written feedback for quality, specificity, actionability, and impact on student learning.
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…
Auto-detect work context (Dev vs Knowledge) — use to tailor workflows based on current task type
Codex-native batch Amazon keyword research using LaunchFast MCP. Use when the user wants a ranked comparison across many keywords and optionally wants HTML and CSV artifacts…
Run tasks in a loop until goals are met — use for iterative refinement, polling, or convergence
Predicts access barriers in a learning task before delivery, given a learner variability profile. Distinguishes between barriers addressable through design and those requiring…
Anchor curriculum learning in a specific local place with connections to community, culture, and identity.
将需求发现、领域建模、一致性审计整合到 /team-* 主链， 以 artifacts/adr/memory 为唯一落盘目标产出可审计文档。 当 Tech Lead、Architect、QA 需要补齐或演进架构文档时使用。
Design a diagnostic hinge question that reveals whether students understand enough to move on. Use when planning key checkpoints mid-lesson during explicit or direct instruction.
Plan a unit using backwards design from desired outcomes through assessment evidence to learning activities.
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots — from…
Build a library of metacognitive prompts targeting planning, monitoring, or evaluation for a specific task.
Use when the user invokes /agent-vision, /agent-vision snapshot, /agent-vision streaming, /agent-vision roast, /agent-vision mood, or asks Codex to snapshot, inspect, roast,…
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
GitHub Copilot CLI as optional zero-cost provider via copilot -p programmatic mode
High-performance CLI proxy that reduces LLM token consumption by 60-90%. Transparently rewrites 100+ common dev commands (git, gh, cargo, npm, docker, kubectl, aws, etc.) via…
Use as the main intake for fuzzy or under-specified feature work before coding. Trigger on: dev-grill-docs, grill-with-docs, grill with docs, 拷问需求, 拷问方案, 压测方案, 术语沉淀, 帮我设计, 写个方案,…
ERPNext-aware reasoning for module customization, workflows, reports, dashboards, workspaces, and choosing between configuration, metadata, and code changes.
Convert markdown to DOCX, PPTX, XLSX, PDF office documents — use when you need exportable deliverables
Design metacognitive checkpoints that prevent AI-assisted learning from bypassing genuine understanding.
Design a learning task where mixed-age students work together with mutual benefit for all age groups.
Surface beliefs, assumptions, stories, and values shaping a system. Use when deeper mental models need examining with care and evidence.
Generate slide deck presentations from briefs — use when you need slides, pitch decks, or visual summaries
System architecture and API design with multi-AI consensus — use for design reviews and new subsystems
Optional knowledge-graph integration. When `graphify-out/graph.json` is present, architect/researcher/reviewer/task-builder agents can query symbol-level dependencies (IMPORTS,…
Install or refresh codex-multi-auth for the official Codex CLI, run first login, and verify account health and routing.
Stage exploration before instruction on complex problems. The learner produces two attempted approaches before consolidation — which builds on those attempts, not from scratch.
Design a document set for a document-based lesson — selecting and sequencing sources for analytical tension around a central question.
Use when user wants to update requirements-dev.in with latest PyPI versions while preserving version patterns
OWASP compliance, vulnerability scanning, and adversarial red team testing — use for security reviews
Pro+ subscription required. Tenant-wide Power Automate monitoring using the FlowStudio MCP cached store: failure rates, run-health trends, maker/app inventory, inactive owners,…
Select and sequence reading comprehension strategies matched to a specific text's challenges and demands. Use when students struggle with a text or need targeted reading support.
Use when the user wants to design, revise, or validate a Tandem workflow (V2 automation, workflow plan, or mission).
Select and configure a structured discussion protocol matched to the purpose, topic, and group readiness.
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。
Use this skill when designing for the edges and corners of the screen — where the cursor cannot overshoot, making them effectively infinite-sized targets along one axis.
Use this skill whenever a user must navigate within a non-trivial space — a multi-page web app, a documentation site, a hierarchical settings panel, a conference site, a…
Use this skill when the user must commit to an irreversible or high-stakes action and reversibility isn''t enough — confirmation dialogs, type-to-confirm patterns, password…
Use this skill when designing for touch — phones, tablets, kiosks, in-car displays, smart-TV remotes, anything where the input is a finger or thumb rather than a precise pointer.
Use this skill when designing the visible states an interactive element passes through (idle / pending / success / error) and matching feedback timing to the user''s perceptual…
Use this skill when the question is *what to delete* — running a structured audit of a UI to remove decorative elements that don''t earn their pixels.
Use this skill when designing or fixing long forms that ask the user for many fields — sign-up flows, profile setup, settings panels, checkout, intake forms, applications.
Use this skill when designing the visual or aesthetic layer of a product, deciding between expressive style and functional restraint, evaluating decorative elements, or arguing…
Use this skill whenever the question is *how* to develop a design — through one big push or through repeated cycles of build, test, learn, refine.