Run a configurable multi-LLM council with personas, budget caps, synthesis, veto gates, and optional implementation handoff.
Redesign a lesson to centre students' cultural backgrounds, community knowledge, and lived experience.
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
Design trauma-informed classroom practices that prioritise safety, predictability, connection, and regulation.
Identify when two design options are functionally equivalent so the razor can be applied. Use when comparing design alternatives, evaluating whether two implementations of a…
Report the user's current AxonFlow tier (Free or Pro), Pro license expiry date, endpoint, and whether a license token is configured.
Multi-AI requirements scoping using Codex and Gemini CLIs (Double Diamond Define phase)
Pick up where you left off from a previous session — use after context resets, compaction, or new conversations
After scaffolded practice, run an unassisted check — a problem with no AI help. Separates what the learner can do with support from what they can do independently.
Set line length (measure) for prose — capping the maximum width of body text so lines stay in the 45–75 character range that supports comfortable sustained reading.
Convert markdown to DOCX, PPTX, XLSX, PDF office documents — use when you need exportable deliverables
Design a checking-for-understanding protocol with specific techniques for each lesson stage. Use when planning systematic comprehension checks during explicit or direct…
After any AI-generated explanation, require the learner to identify one place it could be wrong, one thing to check, and one source to consult.
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。
Use Chrome DevTools MCP for frontend performance work such as slow page loads, LCP, CLS, INP, Lighthouse regressions, scripting hotspots, or layout thrash.
Peer Review Ralph Loop — combines Cavekit kits with a Ralph Loop and true cross-model peer review using Codex (OpenAI). Claude builds from specs; Codex reviews adversarially.
Design a document set for a document-based lesson — selecting and sequencing sources for analytical tension around a central question.
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…
Design a sequence where students compare AI's handling of the same question across disciplines, developing a mental model of where AI is reliable vs.
Audit Claude Code to Codex harness migrations, including AGENTS.md/CLAUDE.md scope, hooks, MCP config, skills, secrets, and validation notes.
Install or refresh oc-codex-multi-auth in OpenCode, choose the right config mode, and verify Codex OAuth with ChatGPT Plus or Pro access.
Build out the transformation layers (`staging/`, `intermediate/`) of a data product and run dbt against them, following project-wide conventions adapted from dbt's best practices…
Revoke a previously-created AxonFlow session override — emits an audit event and ensures subsequent policy evaluations no longer consult it
Map evidence-based connections between a wellbeing initiative and specific academic learning outcomes.
Behavioral guardrails for Cavekit agents. Four principles — think before coding, simplicity first, surgical changes, goal-driven execution — that prevent over-engineering, silent…
Create zero-context implementation plans with bite-sized tasks — use for multi-step feature planning
Design a structured outdoor learning sequence embedding curriculum objectives in an available outdoor space.
How to write Cavekit-quality kits that AI agents can consume effectively. Covers implementation-agnostic cavekit design, testable acceptance criteria, hierarchical structure,…
Analyse the language demands of a classroom task to identify barriers for EAL and multilingual learners.
Anchor a multidisciplinary unit in a real-world phenomenon that requires multiple subject lenses to understand.
Create self-explanation prompts that deepen understanding of worked examples, texts, or diagrams. Use when students read material passively without engaging with underlying…
Plan a unit using backwards design from desired outcomes through assessment evidence to learning activities.
Verify, normalize, and enrich a single citation or paper identifier. Use when the user pastes a DOI, URL, arXiv ID, PubMed ID, citation string, or paper title and wants it checked.
Post-ship doc sync across project markdown. Use when: sync docs, update docs, document changes, release notes.
Design a fact-checking protocol for AI-generated text, extending SIFT with AI-specific adaptations for hallucination detection.
Create a research-backed, reviewed, sectionized Zagrosi Forge TDD implementation plan from a markdown spec.
Apply arbitrary and symbolic icon design — using forms with no inherent meaning that depend on convention to communicate (the hamburger menu, the kebab menu, the AI sparkle, app…
Apply in-product expectation cues — typography, animation, spacing, copy tone, micro-interactions, and visual register that signal "this is the kind of product you''re using"…
Design a scope and sequence showing vertical and horizontal curriculum coherence across a programme or year.
Design formative assessments that make students' historical thinking visible — revealing whether they source, close-read, contextualise, and corroborate.
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.
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.
The learner teaches the concept to the AI, which plays a curious novice peer and identifies gaps through authentic questions.
Coordinates UDL and differentiation tools through a universal-first hierarchy: barrier removal before targeted differentiation before individualised accommodation.
Script a multi-turn tutoring dialogue with branching responses for anticipated student difficulties. Use when designing AI tutors, chatbot interactions, or structured one-to-one…
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…
Apply the Gestalt principle of Figure-Ground Relationship — the perceptual separation of what''s perceived as the figure (the focus, the object) from the ground (the surrounding…
Review the week using accumulated session evidence — retrieval rates, hint depths, calibration accuracy, transfer and unassisted results.
Orchestrate compassionate systems tools from issue or aspiration to wise action. Use when a class needs a complete inquiry workflow.
Design a project-based learning brief with a driving question, milestones, and assessment criteria. Use when planning PBL units, inquiry projects, or extended investigations.
Audit a proposed assessment for construct validity, reliability, and alignment to learning objectives. Use when reviewing or quality-assuring assessments before deployment.
Use this skill when the design''s perceived quality affects whether users will tolerate friction, give the product a chance, or judge it as well-made — which is most…
Use this skill when designing or fixing navigation — sidebars, top nav, footer nav, mobile menus, breadcrumbs, tab bars, command palette groupings.
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.
Debug failing Power Automate cloud flows using the FlowStudio MCP server. The Graph API only shows top-level status codes.
Use this skill when the question is whether users can *understand* the UI — predict its behavior, recover from errors, comprehend its labels and copy.
Use this skill when deciding *what to surface* and *what to tuck* — the editorial choices behind progressive disclosure.
Use this skill when the team is in a form-vs-function debate and needs to step back to define what "success" actually means for the design.
Use this skill when scoping a roadmap, prioritizing features, planning an MVP, or deciding what to ship and what to defer.
Use this skill when scoping a redesign or refactor — choosing which existing surfaces deserve full attention and which can be left mostly alone.