Используй только внутри активного Codex Project Autopilot-проекта по утверждённому плану; не включай для обычных backend-задач вне автопилота.
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,…
Design a complete document-based history lesson using the Reading Like a Historian four-part structure.
Use when user says regression test, eval check, eval regression, test before commit, compare versions, check regressions, run evals, benchmark skill, or /eval-regression.
Design a lesson opening that activates prior knowledge and connects previous learning to today's content.
Map curriculum connections across multiple subjects for a real-world problem or authentic context. Use when planning cross-curricular projects or connecting content to real issues.
Verify and design for user-base scaling — broader audiences, more diverse use cases, more edge cases, behaviors that weren''t anticipated.
Build a learning progression showing prerequisite-to-mastery steps for a target skill or understanding.
Generate a cascading hint sequence for a problem type, revealing progressively without giving answers. Use when designing tutoring dialogues or scaffolded worksheets.
Wrap up a branch — run tests, create PR, merge or discard — use when implementation is done
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.
Use when working on substantial writing artifacts where structure, audience fit, critique, revision, translation, style learning, or decision-backed preference learning matters;…
Frappe frontend guidance for Vue and React, including desk pages, `www` pages, `frappe-ui`, Doppio-style frontends, client scripts, and external SPA integrations.
Define the scope and purpose of a complex inquiry before mapping or futures work begins. Use when a class or group needs to agree what they are investigating, who it matters to,…
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"…
Audit a proposed assessment for construct validity, reliability, and alignment to learning objectives. Use when reviewing or quality-assuring assessments before deployment.
Create an interactive digital worked example sequence with fading for online or blended delivery. Use when building e-learning modules, LMS content, or app-based instruction.
Orchestrate compassionate systems tools from issue or aspiration to wise action. Use when a class needs a complete inquiry workflow.
Use when the user asks Codex to inspect Aient telemetry, search logs, explain traces, create/list Aient API keys, or use the Aient MCP server.
Classify a task or feature as quick, standard, or thorough so the rest of the pipeline (budget sizing, model routing, review depth) can right-size itself.
Temporary inboxes for agent signup QA — create disposable addresses, wait for verification email, extract OTP or magic links.
Authors or reviews Know/Understand/Do charts for competency-based learning targets across developmental bands.
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 for AI-assisted Unity work that needs live repo discovery, project-derived routing, runtime-owner proof, runtime-visible output hard stops, runtime numeric proof for repeated…
Decompose and execute large changes, migrations, or multi-issue fixes in parallel with quality gates
Generate a scaffolded sequence of practice problems with graduated difficulty and strategic variability.
Generate scaffolds that gradually increase student choice, voice, and ownership within a learning task.
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.
How to write Blueprint-quality blueprints that AI agents can consume effectively. Covers implementation-agnostic blueprint design, testable acceptance criteria, hierarchical…
Takes a curriculum framework and a statutory or accreditation requirement list; produces a coverage table, gap summary, and CSV showing which framework content covers each…
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…
Design a Funhouse Mirror activity where students use their own domain expertise to detect AI distortions, omissions, and overconfidence.
Persist design documents with branch tracking, revision chains, and cross-session discovery
Generate tiered sentence frames for academic tasks that scaffold language production across proficiency levels.
Build students' capacity to read historical documents closely — attending to word choice, tone, and rhetoric as evidence of perspective.
Personal-data-protection compliance reference for engineers building applications subject to Singapore PDPA, Indonesia UU PDP 27/2022, Thailand PDPA B.E.
Use when starting any conversation - establishes how to find and use HOTL skills for implementation tasks
提供基于 Testcontainers 的 Java 集成测试工作流，用于数据库、中间件和外部依赖的接近真实行为验证。 当任务涉及持久化、消息、缓存、对象存储或多依赖编排时使用。
Recognize and design against the cost of attention fragmentation — the disproportionate damage that even small interruptions do to focused work.
Anchor a multidisciplinary unit in a real-world phenomenon that requires multiple subject lenses to understand.
Map a scoped topic across three coexisting horizons — current system under strain (H1), preferred future (H3), and transition innovations sorted as H2+ or H2- — to understand…
Design a spaced retrieval schedule for any topic list and timeline. Use when planning units, term sequences, or revision programmes.
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…
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.
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…
Design deliberately flawed examples that develop error-detection skills and deepen understanding. Use when students make characteristic errors and need practice spotting mistakes.
The learner teaches the concept to the AI, which plays a curious novice peer and identifies gaps through authentic questions.
NLSpec authoring — use when you need a structured specification from multi-AI research and consensus
Structured four-way AI debates between Claude, Sonnet, Gemini, and Codex — use for critical decisions
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…
HTTP API-based documentation server (always running). Questions about project architecture, conventions, decisions, code structure, tech debt, env config, progress, or doc health.
Analyse the language demands of a classroom task to identify barriers for EAL and multilingual learners.
Map which elements of an assignment benefit from AI assistance vs. which AI use undermines. Use when redesigning tasks for AI-age classrooms or setting defensible AI use policies…
对失败或卡住的团队工作流进行事后调查：时间线重建、角色交接审计、 产出缺失定位、重复循环检测和根因归类。 与 systematic-debugging（代码级调试）互补，本 skill 面向工作流级诊断。
将 GitNexus 作为受控可选代码智能能力接入，用于 brownfield MCP 查询、影响面分析、 detect_changes、多仓分析和更深代码图谱证据。输出必须回落到 `/team-*` 主链和 artifacts。
Use visual similarity to create perceptual groups — making related items look alike so users perceive them as a set.
Tier vocabulary from a text or topic into everyday, academic, and technical categories with teaching priorities.
Apply deliberate dissimilarity (contrast) to distinguish elements that need to be perceived as different — primary vs. secondary actions, normal vs. error states, foreground vs.
Reverse-engineer design systems, tokens, and components from live products or screenshots
Design a source evaluation protocol using lateral reading and credibility checks for digital information.