Agent skill

K-12 Core Literacy Lesson Design

by THU-MAIC in THU-MAIC/OpenMAIC

Designs a Chinese K-12 classroom for one OpenMAIC stage around the core-literacy model, using authentic tasks, performance assessment and observable evidence.

MITAuto-check passedEducation

Install K-12 Core Literacy Lesson Design

skills CLI
$ npx skills add THU-MAIC/OpenMAIC --skill k12-core-literacy-planning -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install THU-MAIC/OpenMAIC k12-core-literacy-planning --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/THU-MAIC/OpenMAIC.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/agent-runtime/k12-core-literacy-planning .claude/skills/k12-core-literacy-planning && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
k12-core-literacy-planning
GitHub stars
40k
Token cost
~2.4k tokens
SKILL.md length
1,265 words
Files
6 (incl. references)
Skills in repo
25
Repo updated
First seen
Licence
MIT

At a glance

Designs a Chinese K-12 classroom for one OpenMAIC stage around the core-literacy model, using authentic tasks, performance assessment and observable evidence.

  • Works in 2 steps: references/core-literacy.md, always; → exactly one matching subject guide
  • Designing a Chinese primary or secondary lesson around a real-world task
  • SKILL.md covers Ground the lesson before…, Settle the learning contract, Plan pages around learner work and New-stage execution, plus 3 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

The deliverable is the classroom itself: pages, roles, learner activity, assessment evidence and narration written into a persisted OpenMAIC stage, not a Word lesson plan, a `lesson.json`, HTML or render-script instructions. Every lesson follows one chain: an authentic context, a performance task, a learning activity, observable evidence and transfer. The `stage-design` skill still governs how a new stage is saved, and an existing stage is edited surgically under the `pro-editing` rules instead of being duplicated.

Before proposing pages, the agent determines the subject and school stage and loads `references/core-literacy.md` plus exactly one subject guide for languages, mathematics, science or humanities. If grade or topic is unknown it asks at most two questions in a single call and defaults to a 45-minute lesson. It aligns to a named textbook or standard clause, otherwise says the lesson is not tied to a specific edition and never invents standard numbers. One or two primary literacy dimensions are chosen and a learning contract is stated before the page list.

When your agent uses it

  • Designing a Chinese primary or secondary lesson around a real-world task
  • Reshaping an existing OpenMAIC stage toward core-literacy goals
  • Choosing literacy dimensions and performance evidence for a lesson

Example prompts

  • “Design a junior-high science lesson on water quality as an authentic task for my OpenMAIC classroom.”
  • “Rework this primary mathematics stage so students show their reasoning through a performance task.”
  • “Which core-literacy dimensions fit a senior-high history lesson on trade routes?”

Requirements

  • An OpenMAIC classroom stage the agent can read and edit

Workflow steps

2 steps, taken from the first numbered list in SKILL.md.

  1. references/core-literacy.md, always;
  2. exactly one matching subject guide

What it can do on your machine

Read from SKILL.md and the folder at commit 4c67608. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

K-12 Core Literacy Lesson Design loads about 2.4k tokens when it runs, and up to ~5.4k if it reads all its reference files. Until then it costs about 105 tokens; SKILL.md has 1,265 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~105
When it runs · the whole SKILL.md, loaded when a task matches
~2.4k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~5.4k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from THU-MAIC/OpenMAIC at commit 4c67608, republished under its MIT licence (© THU-MAIC). 1,265 words, ~2,403 tokens.

Download SKILL.mdSave it as .claude/skills/k12-core-literacy-planning/SKILL.md (or your agent's skills folder). This skill also uses 5 other files; get the full folder from GitHub.
name
k12-core-literacy-planning
description
Chinese K-12 core-literacy course design for a single OpenMAIC classroom. Use when a teacher asks for 中小学课程、核心素养、素养导向、2022 课标、真实情境、任务群、表现性评价, or wants a grade-and-subject lesson designed around authentic tasks rather than content delivery. Covers Chinese, mathematics, languages, science, humanities, technology, arts, PE and labor education across primary, junior-high and senior-high stages.
title
核心素养教学设计

K-12 core-literacy classroom design

Design or reshape one persisted OpenMAIC stage around the Chinese curriculum standards' core-literacy model. The deliverable is the classroom itself: pages, roles, learner activity, assessment evidence and narration written into the stage. Do not produce a Word lesson plan, a lesson.json, HTML, or instructions for running local render scripts.

The invariant is:

authentic context → performance task → learning activity → observable evidence → transfer

stage-design still governs the persistence sequence for a new stage. This skill governs the pedagogy and the information carried in every page brief. If the stage already has pages, edit it surgically under the pro-editing rules; do not create a duplicate stage.

Ground the lesson before planning

Before proposing pages, determine the subject and school stage. Then use the native read tool to load both:

  1. references/core-literacy.md, always;
  2. exactly one matching subject guide:

Loading the relevant reference is mandatory. Do not rely on a remembered dimension name when the reference distinguishes compulsory and senior-high wording.

If grade or topic is genuinely unknown, ask at most two load-bearing questions in one ask_user call. Default the rest to 45 minutes, general curriculum quality expectations and UDL support. Never ask again for information already present in the request or attached material.

If the teacher names a textbook edition, standard clause or supplied material, align to it. Otherwise use general curriculum wording and say the lesson is not aligned to a specific textbook edition. Never invent a standard number, quote or material fact.

Settle the learning contract

Choose only one or two primary literacy dimensions for one lesson. State the contract in this form before the page list:

Students will do X in order to make literacy dimension Y observable through evidence Z.

Weak targets such as “understand”, “master” and “cultivate thinking” are not a contract. Use visible verbs: annotate, model, compare, justify, test, revise, design, decide, create or present.

The authentic context must carry all the way through the lesson:

  • it creates the opening problem;
  • learners use it in the central task;
  • assessment returns to it with a new case or changed condition.

A story discarded after page 1 is decoration, not context. A normal exercise with a person's name pasted on it is not an authentic problem.

Plan pages around learner work

Default to 6–10 pages for a 45-minute lesson, but do not treat that range as a hard page cap. Each proposed page includes title, type, brief, the learner action, the evidence collected and its link to adjacent pages.

A useful default arc is:

  1. slide: the authentic situation, the unresolved question and the final task;
  2. interactive or evidence page: observe, manipulate, read, map or collect evidence;
  3. interactive or slide: compare, classify, model, closely read or reason;
  4. quiz: diagnose the most likely misconception and require a reason;
  5. interactive, pbl or task page: produce the main explanation, model, decision, text, design or performance;
  6. slide: success criteria, scaffold, worked fragment or peer-review method;
  7. quiz or task page: transfer into a new version of the same context;
  8. optional closing slide: consolidate the method learners established and name what remains open.

Choose the page type by the learning action:

  • slide frames a problem, carries source material or evidence, or consolidates a method. It must not become a run of teacher exposition.
  • interactive is for changing a variable, tracing a structure, running code, repeated rule-bound decisions or spatial inspection. One interactive page carries one mechanism and says what changes, what is observed and what the observation establishes.
  • quiz diagnoses a misconception, compares explanations or checks transfer. Distractors come from real misconceptions and feedback teaches, not merely marks wrong.
  • pbl is for a genuinely multi-step inquiry, artifact or public performance. Do not wrap one simple exercise in PBL machinery.

Titles name what learners discover or make: 「拖动倾角,看射程怎么变」, 「两份史料为什么说得不一样」, 「给校园开放日改写导览词」. Do not use 「概念介绍」「知识讲解」「案例分析」「课堂总结」.

Show full SKILL.md (598 more words)Show less

New-stage execution

After the teacher approves the page plan through ask_user:

  1. create_stage with the settled title and the series folderId when relevant.
  2. set_roster before any page. Use exactly one teacher and at least two agents. The teacher persona embodies the subject method; another role surfaces a typical misconception, asks for evidence or compares strategies. Keep language and cognitive demand appropriate to the grade.
  3. Call generate_scene once for each approved page, in ascending order. Pass the page's title, type and a self-contained brief. When attached material grounds the page, pass only verified facts in materialFacts.
  4. Carry this skill into every generator call. A page brief must say:
    • the target literacy dimension and visible learner action;
    • what learners see, manipulate, read, discuss or produce;
    • the evidence or source they must use;
    • the likely misconception and the scaffold that addresses it;
    • the assessment evidence collected on this page;
    • the grade-appropriate register and the handoff to the next page.
  5. list_scenes and verify every approved page persisted in the correct order.
  6. Read the pages' narration actions. Call generate_tts on every page whose speech is new, changed or missing audioId. A planned or silent page is not finished.

Do not stop after presenting a plan. A turn ends only at an ask_user gate, after a page has actually persisted, or when the whole stage passes the checks below.

Existing-stage adaptation

When the current stage already has pages:

  1. list_scenes, then read_stage the relevant pages before writing.
  2. Audit subject/stage wording, context continuity, learner product, evidence, misconception handling, assessment alignment and narration.
  3. Repair only the pages that break the contract. Prioritize decorative contexts, conclusions revealed before inquiry, no observable learner product, activity/assessment mismatch, wrong school-stage difficulty, literacy labels with no evidence, and exit tickets that collapse into recall.
  4. Use patch_stage for narrow edits and edit_deck for page-list changes. Regenerate a whole page only when the user explicitly wants a rewrite.
  5. Re-run generate_tts after speech changes, then read back touched pages and list_scenes for the final structure.

Universal non-negotiables

  • Learners do the cognitive work. The teacher supplies phenomena, sources, questions, models and scaffolds without announcing the conclusion first.
  • The main task itself yields assessment evidence. The exit task uses a new case with the same reasoning or production structure.
  • Primary school favors concrete manipulation, experience and short language; junior high favors concepts, evidence and explicit reasoning; senior high favors systems, models, multiple sources and justified value decisions.
  • Include at least one visual or structural scaffold, one language-expression scaffold and one extension for learners ready for greater challenge.
  • Create original cases, questions and activities. Textbooks and uploaded sources determine scope and facts, not learner-facing copy to reproduce.

Completion check

Do not call the classroom done until all are true:

  • the subject and school stage use the correct curriculum dimension wording;
  • one or two dimensions appear as learner actions and observable evidence;
  • the authentic context survives from opening through task to transfer;
  • every approved page exists, has content and sits in the right order;
  • learners acquire, process or compare evidence at least once;
  • learners produce at least one explanation, model, text, design, decision, performance or other inspectable artifact;
  • the central misconception is handled by an activity or quiz;
  • assessment is isomorphic to the learning task and includes transfer;
  • narration matches page content and every required speech line has audio;
  • no curriculum quote, textbook edition, source fact or external lookup result was fabricated.

Close in one or two sentences: name the primary literacy dimensions and the performance task that now makes them visible. Do not replay the whole page list.

© THU-MAIC, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 5 other files (references) in skills/agent-runtime/k12-core-literacy-planning of THU-MAIC/OpenMAIC.

  • SKILL.md
  • references/core-literacy.md
  • references/subjects/humanities.md
  • references/subjects/languages.md
  • references/subjects/mathematics.md
  • references/subjects/science.md

Open the folder on GitHubat commit 4c67608

Compare with similar skills

K-12 Core Literacy Lesson Design next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

K-12 Core Literacy Lesson Design compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
K-12 Core Literacy Lesson Design this skillTHU-MAIC/OpenMAIC40k—~2.4kAutomated safety check: PassMIT
Competency UnpackerGarethManning/education-agent-skills840—~4.5kAutomated safety check: PassCustom licence
HTML Ppt Course Modulesanqiufong/slides-from-anything132—~1.1kAutomated safety check: PassApache-2.0
AI Engineering Placement Quizrohitg00/ai-engineering-from-scratch67k—~2kAutomated safety check: PassMIT
AnythingAtlasLiuziyu77/AnythingAtlas195—~3.6kAutomated safety check: PassApache-2.0
Codex Skill Self-AssessmentFlorianBruniaux/claude-code-ultimate-guide6.1k—~2.3kAutomated safety check: PassCC-BY-SA-4.0

Similar skills

  • Competency Unpacker

    GarethManning/education-agent-skills

    Unpack a broad standard or competency descriptor into specific, assessable success criteria and sub-skills.

    840 GitHub stars~4.5k tokensUpdated 1 mo ago
    EducationAuto-check passed
  • HTML Ppt Course Module

    sanqiufong/slides-from-anything

    Online-course / workshop module deck — warm paper background + Playfair serif, persistent left sidebar of learning objectives, MCQ self-check page.

    132 GitHub stars~1.1k tokensUpdated yesterday
    EducationAuto-check passed
  • AI Engineering Placement Quiz

    rohitg00/ai-engineering-from-scratch

    Runs a 10-question quiz across five areas to place a learner in the AI Engineering from Scratch curriculum, so they skip what they already know.

    67k GitHub stars~2k tokensUpdated today
    EducationAuto-check passed
  • AnythingAtlas

    Liuziyu77/AnythingAtlas

    Researches an unfamiliar topic and delivers a verified resource guide and a staged, timed learning roadmap as matching Markdown and HTML files.

    195 GitHub stars~3.6k tokensUpdated 1 mo ago
    EducationAuto-check passed
  • Codex Skill Self-Assessment

    FlorianBruniaux/claude-code-ultimate-guide

    Runs an interactive quiz in a quick or comprehensive mode, scores your skill level by topic and generates a personalized learning path with practice projects.

    6.1k GitHub stars~2.3k tokensUpdated today
    EducationAuto-check passed
  • Course Design

    madhvantyagi/Gnos

    Design and revise a course's goal, progression, prerequisites, and sources.

    339 GitHub stars~1.4k tokensUpdated today
    EducationAuto-check passed

More from THU-MAIC/OpenMAIC

All 25 skills in this repo
  • Guides setup, classroom generation and secondary development for OpenMAIC, the multi-agent interactive classroom, one confirmed phase at a time.

    40k GitHub stars~1.7k tokensUpdated today
    Auto-check: notes
  • Maps the structure of an OpenMAIC stage document so an agent can find the right path, read it and patch quizzes, widgets, actions and project pages without guessing.

    40k GitHub stars~2.4k tokensUpdated today
    Auto-check passed
  • Designs a review-and-practice lesson around an independent first attempt, targeted feedback, supported practice, a fresh independent check and a next step.

    40k GitHub stars~1.1k tokensUpdated today
    Auto-check passed
  • Derives a reusable personal skill for course-making from a representative sample of the user's own past classrooms and chat history, confirmed with them before saving.

    40k GitHub stars~678 tokensUpdated today
    Auto-check passed
  • Curriculum Planner

    THU-MAIC/OpenMAIC

    Plans a multi-classroom series such as a seven-day course, clarifies the brief in rounds, gets sign-off on the full lesson list, then builds each stage in a shared folder.

    40k GitHub stars~2.8k tokensUpdated today
    Auto-check passed
  • Plans online courses so learners manipulate simulations, diagrams, code, games or 3D scenes on most pages, with slides only for the opening and the close.

    40k GitHub stars~681 tokensUpdated today
    Auto-check passed

Categories

Questions about K-12 Core Literacy Lesson Design

What does K-12 Core Literacy Lesson Design do?

Designs a Chinese K-12 classroom for one OpenMAIC stage around the core-literacy model, using authentic tasks, performance assessment and observable evidence. json`, HTML or render-script instructions. Every lesson follows one chain: an authentic context, a performance task, a learning activity, observable evidence and transfer.

When should I use K-12 Core Literacy Lesson Design?

K-12 Core Literacy Lesson Design fits situations like: designing a Chinese primary or secondary lesson around a real-world task; reshaping an existing OpenMAIC stage toward core-literacy goals; choosing literacy dimensions and performance evidence for a lesson.

How do I install K-12 Core Literacy Lesson Design in Claude Code?

Run `npx skills add THU-MAIC/OpenMAIC --skill k12-core-literacy-planning -a claude-code`. Or copy the skill folder (skills/agent-runtime/k12-core-literacy-planning in THU-MAIC/OpenMAIC) into .claude/skills/k12-core-literacy-planning in your project. Claude Code loads it when a task matches its description.

How do I install K-12 Core Literacy Lesson Design in Codex?

Run `npx skills add THU-MAIC/OpenMAIC --skill k12-core-literacy-planning -a codex`. Or copy the skill folder (skills/agent-runtime/k12-core-literacy-planning in THU-MAIC/OpenMAIC) into .agents/skills/k12-core-literacy-planning in your project. Codex loads it when a task matches its description.

Can I use K-12 Core Literacy Lesson Design in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add THU-MAIC/OpenMAIC --skill k12-core-literacy-planning -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/k12-core-literacy-planning, .gemini/skills/k12-core-literacy-planning, .github/skills/k12-core-literacy-planning and .opencode/skills/k12-core-literacy-planning in your project.

What does K-12 Core Literacy Lesson Design need to run?

SKILL.md names no scripts, command-line tools or credentials: K-12 Core Literacy Lesson Design is instructions for the agent only. Our summary lists: An OpenMAIC classroom stage the agent can read and edit.

Does K-12 Core Literacy Lesson Design access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is K-12 Core Literacy Lesson Design safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does K-12 Core Literacy Lesson Design use?

K-12 Core Literacy Lesson Design is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does K-12 Core Literacy Lesson Design use?

About 2.4k tokens (SKILL.md is roughly 9.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 3k tokens, read only when the agent opens those files.

What are the alternatives to K-12 Core Literacy Lesson Design?

Skills that share tags, products or a category with K-12 Core Literacy Lesson Design: Competency Unpacker (GarethManning/education-agent-skills, 840 stars), HTML Ppt Course Module (sanqiufong/slides-from-anything, 132 stars), AI Engineering Placement Quiz (rohitg00/ai-engineering-from-scratch, 67k stars) and AnythingAtlas (Liuziyu77/AnythingAtlas, 195 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains K-12 Core Literacy Lesson Design?

THU-MAIC (a GitHub organization) maintains it in THU-MAIC/OpenMAIC, which has 40,347 GitHub stars. The repository holds 25 skills in this directory. The repository was last updated on October 11, 2026.

Source: THU-MAIC/OpenMAIC on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.