Document-Based Lesson Designer Agent Skill

Design a complete document-based history lesson using the Reading Like a Historian four-part structure.

Context cost
7.8k tokensestimated from the bundle, loaded when it triggers
Bundle
1 file · 31.3 kBtext throughout, nothing executable
Licence
not declarednone named by its author
Last change
—v1.0
Servers it uses
Noneruns standalone

What it does

Design a complete document-based history lesson using the Reading Like a Historian four-part structure. Use when planning a primary source inquiry lesson or converting a textbook lesson into document-based investigation.

What this skill changes about the agent has not been set out here as a list. Its SKILL.md, shown below, says it in the author’s own words.

activity-structuredigdisciplinary-literacydocument-based-lessonshistorical-thinkinglesson-designprimary-sourcesrlh

The skill itself

A skill is instructions the model reads, so you can see what you are getting: below is the start of its SKILL.md. The front matter loads with every session, the body loads when the skill triggers, and the whole file comes with the install.

SKILL.md31.3 kB · preview
--- # AGENT SKILLS STANDARD FIELDS (v2) name: document-based-lesson-designer disable-model-invocation: false user-invocable: true effort: high # EXISTING FIELDS skill_id: "historical-thinking/document-based-lesson-designer" skill_name: "Document-Based Lesson Designer" domain: "historical-thinking" version: "1.0" contributor: "Sean Hu" evidence_strength: "strong" evidence_sources: - "Reisman (2012) — Reading like a historian: a document-based history curriculum intervention in urban high schools" - "Wineburg, Martin & Monte-Sano (2011) — Reading like a historian: teaching literacy in middle and high school history classrooms" - "Wineburg & Martin (2004) — Reading and rewriting history" - "Wineburg (2007) — Unnatural and essential: the nature of historical thinking" - "Wineburg & Reisman (2015) — Disciplinary literacy in history: a toolkit for digital citizenship" - "Wineburg (2016) — Why historical thinking is not about history" input_schema: required: - field: "central_question" type: "string" - field: "document_set" type: "string" - field: "student_level" type: "string" - field: "lesson_duration" type: "string" optional: - field: "target_skills" type: "string" - field: "background_knowledge" type: "string" - field: "learning_objectives" type: "string" - field: "writing_task" type: "string" - field: "curriculum_framework" type: "string" - field: "prior_instruction" type: "string" output_schema: type: "object" fields: - field: "lesson_plan" type: "object" - field: "strategy_instruction_plan" type: "object" - field: "discussion_plan" type: "object" - field: "differentiation_notes" type: "object" - field: "assessment_opportunities" type: "array" chains_well_with: - "central-historical-question-evaluator" - "historical-document-set-curator" - "historical-source-adapter" - "historical-thinking-strategy-modelling-guide" - "sourcing-skill-builder" - "close-reading-skill-builder" - "contextualisation-skill-builder" - "corroboration-skill-builder" - "historical-thinking-assessment-designer" - "backwards-design-unit-planner" - "discussion-protocol-selector" teacher_time: "5 minutes" tags: ["lesson-design", "document-based-lessons", "historical-thinking", "primary-sources", "disciplinary-literacy", "activity-structure", "RLH", "DIG"] ---
90# Document-Based Lesson Designer
91
92## What This Skill Does
93
94Designs a complete document-based history lesson following the four-part activity structure from the Reading Like a Historian curriculum: (1) background knowledge, (2) central historical question, (3) primary source investigation with explicit strategy instruction, and (4) whole-class discussion. The output is a lesson plan with timing, teacher actions, student actions, strategy instruction points, a discussion plan, differentiation notes, and formative assessment opportunities.
95
96This skill is the integrator of the historical thinking domain. It takes the outputs of the other skills — a central question (evaluated by central-historical-question-evaluator), a document set (curated by historical-document-set-curator), adapted sources (from historical-source-adapter), and strategy instruction plans (from the four skill builders and strategy-modelling-guide) — and assembles them into a coherent lesson architecture. It can also work from scratch when a teacher provides the central question and documents directly.
97
98The four-part activity structure is not arbitrary. Reisman (2012) demonstrated its effectiveness in a six-month intervention with 236 students across five urban high schools. Treatment students who experienced this lesson format outperformed controls on historical thinking, factual knowledge, reading comprehension, and transfer of historical thinking to contemporary topics. The structure works because each phase serves a specific cognitive function: background knowledge activates the context students need for contextualisation; the central question provides the analytical focus; the document rounds scaffold progressive complexity; and whole-class discussion makes reasoning visible and social.
99
100However, Reisman also found that teacher fidelity to the full structure was low — most teachers scored below baseline on the fidelity rubric, and whole-class discussion was extremely rare. The most common failure was omitting discussion, which may explain the null results for contextualisation and corroboration (both of which benefit from dialogic instruction). This skill designs the discussion phase explicitly and provides the questions and protocols teachers need to facilitate it, because discussion is both the most important and the most frequently skipped component of the lesson.
101
102## Evidence Foundation
103
104Reisman (2012) developed the Document-Based Lesson as a new "activity structure" consisting of four phases. Treatment teachers used this structure for 42–72% of instructional time (M = 58.3%), implementing 36–50 document-based lessons over six months. The intervention produced significant effects across all four outcome measures: historical thinking (ηp² = .09), transfer (ηp² = .08), factual knowledge (ηp² = .03), and reading comprehension (ηp² = .05). No school × treatment interaction was found, suggesting the structure worked across widely varying school contexts.
105
106The four-part structure was designed to address specific pedagogical problems. The background knowledge phase ensures students have the contextual knowledge needed for contextualisation — without it, students cannot connect documents to their historical moment (Wineburg, 2007). The central question phase provides analytical focus — without a driving question, source analysis becomes a skills exercise rather than an investigation (Wineburg, Martin & Monte-Sano, 2011). The document investigation phase with explicit strategy instruction makes historical thinking skills visible and practicable — without modelling, students do not develop sourcing, close reading, contextualisation, or corroboration (Wineburg, 1991). The whole-class discussion phase makes reasoning social and accountable — without discussion, the comparative and inferential reasoning that corroboration and contextualisation require remains internal and undeveloped (Reisman, 2012).
107
108Wineburg, Martin, and Monte-Sano (2011) provided eight complete lesson exemplars following this structure. Analysis reveals consistent design principles: lessons begin by activating what students already know (often starting with the familiar — Disney's Pocahontas, for example — then complicating it); documents are introduced in rounds of increasing complexity (primary sources first, then historians' interpretations); and each round is followed by discussion that connects back to the central question.
This is a preview of SKILL.md. Download or install the skill to get the whole thing.
In the file
SKILL.md4,293 words
Files1
Licencenot declared
Why you can read it

Nothing in a skill executes. The client loads the text and the model follows it, so a skill can be audited the way a runbook is — by reading it.

What it costs in context

Skills are not billed by the call. They are paid for in context: every token the instructions occupy is a token your code, your diff and your conversation cannot use. Here is what this one takes and when it takes it.

≈1,270
always loaded
The name and description, so the model knows the skill exists and when to reach for it.
6,555
on trigger
The instruction body, read only when the skill fires.
3.9%
of a 200k window
Ten skills this size would take about 39% of the window before you open a file.
050k100k150k200k context window

7.8k tokens, estimated from the bundle at four bytes to the token, held for the rest of the session once it triggers. Heavy. Teams tend to install this one per project rather than globally, and load it only when the job comes up.

Servers bill, skills cost

A server charges by the month. A skill charges once per session, in context, and then keeps charging it for as long as the session lives.

Before and after

The same question, put to the same model twice: once as it comes, and once with these instructions loaded.

No worked example has been published for this skill yet.

The procedure it runs

The procedure has not been set out here step by step. It is in the body of its SKILL.md: the start of it is shown above, and the whole file comes with the install.

Prose, not code

These steps are written for a model to follow, not executed by a runtime. It can still be told to skip one, and it will say so when it does.

Servers it uses

None. This skill calls no MCP servers at all.

Everything it needs is in the instructions, so it works in a project with nothing connected — the model reads the file and changes how it works with what it can already reach.

Its SKILL.md does not declare which tools it asks the agent for, so what it touches is whatever the instructions themselves ask for — read them before you install it.

What it asks for
Writes filesnot declared
Network accessnot declared

This SKILL.md carries no allowed-tools line, so neither is declared. A skill grants no permissions of its own — it can only ask for tools your client already has.

What it will not do

Every skill is narrow, and the useful ones say where they stop. These are the jobs this one is the wrong tool for.

What this skill is not for has not been published here. Nothing is implied by that: it is a section the author has not filled in.

What is in the bundle

1 file, 31.3 kB on disk. A bundle is text throughout: the instructions the model reads, plus the templates it fills in.

  • SKILL.md31.3 kB
What is not in it

No dependencies and nothing executable: a skill is text the agent reads, so the bundle is 1 file you can review in full before installing.

Install

Installing copies the bundle into your project. Nothing runs at install time — the files sit on disk until the model reads them.

# Document-Based Lesson Designer · 7.8k tokens when loaded · macOS, Linux mkdir -p .claude/skills && t=$(mktemp -d) && curl -fsSL -o "$t/bundle.tar.gz" https://mcprush.com/api/skills/document-based-lesson-designer/bundle.tar.gz && tar -xzf "$t/bundle.tar.gz" -C "$t" && [ -d "$t/document-based-lesson-designer" ] && { [ ! -e .claude/skills/document-based-lesson-designer ] || { mv .claude/skills/document-based-lesson-designer "$t/.previous" && echo "Previous copy moved to $t/.previous"; }; } && mv "$t/document-based-lesson-designer" .claude/skills/ && echo "Installed .claude/skills/document-based-lesson-designer"
On Windows, or any OS with Node 20+
npx mcprush@latest skill add garethmanning/document-based-lesson-designer

Windows PowerShell says 'running scripts is disabled on this system'? Run Set-ExecutionPolicy -Scope CurrentUser RemoteSigned once, or type npx.cmd instead of npx (codex.cmd, gemini.cmd, grok.cmd likewise). PowerShell 7 needs neither. Writes to .claude/skills/document-based-lesson-designer/ in the current project. For every project instead, run mkdir -p ~/.claude/skills && t=$(mktemp -d) && curl -fsSL -o "$t/bundle.tar.gz" https://mcprush.com/api/skills/document-based-lesson-designer/bundle.tar.gz && tar -xzf "$t/bundle.tar.gz" -C "$t" && [ -d "$t/document-based-lesson-designer" ] && { [ ! -e ~/.claude/skills/document-based-lesson-designer ] || { mv ~/.claude/skills/document-based-lesson-designer "$t/.previous" && echo "Previous copy moved to $t/.previous"; }; } && mv "$t/document-based-lesson-designer" ~/.claude/skills/ && echo "Installed ~/.claude/skills/document-based-lesson-designer" (macOS, Linux) — or add --global to the npx line. The curl line replaces .claude/skills/document-based-lesson-designer/ only after the download succeeds, so files left there by another skill of the same name, or by an older release, do not mix in. A copy already there is moved aside, not deleted, and the line prints where.

Which clients pick it up on their own

A skill is a folder of text. Most of these read a skills folder and pick it up without being told; the rest take the same folder another way — an upload in the app, a parameter on an API call — and then choose it by its description just the same.

Claude Code.claude/skills/
Claude DesktopCustomize › Skills
ChatGPTSkills › Create › Upload
Cursor.cursor/skills/
VS Code.github/skills/
Codex CLI.agents/skills/
Gemini CLI.gemini/skills/
Grok Build.grok/skills/
Microsoft CopilotSkills › Upload a skill
PerplexityComputer › Skills › Upload a skill
DeepSeek Harness.dsh/skills/
Zed.agents/skills/
Devin Desktop.devin/skills/
Windsurf (legacy).windsurf/skills/
OpenAI Agents SDKInstructions or sandbox Skills
HTTP / APIa request parameter
This release
Version1.0
Publishedno release date on file
PriceFree
Referencegarethmanning/document-based-lesson-designer

Versions

v1.0 is what is on the shelf; no release here carries a date. Instructions change more often than APIs do — a skill can be rewritten entirely without anything it depends on moving.

v1.0
  • No earlier releases have been published to the marketplace.
Pinning

The install command always fetches the release that is current the day you run it — v1.0 today — and cannot ask for an earlier one. The copy on your disk does not change until you run it again.

Reviews

—no reviews yet

Nobody has reviewed this skill yet. The rating is the mean of the reviews written here, so there is none until somebody writes the first.

Sign in to review it

A review is tied to an account so it can be answered, edited and taken down by the person who wrote it.

Sign in
Who can post

Anybody with an account, one review each. It carries the version that was current when you wrote it, and the publisher may reply once.

Publisher
Servers0
Claim this skill