Historical Source Adapter Agent Skill

Adapt a historical primary source for classroom use — modifying complexity and length while preserving features for sourcing, close…

Context cost
6k tokensestimated from the bundle, loaded when it triggers
Bundle
1 file · 24.2 kBtext throughout, nothing executable
Licence
not declarednone named by its author
Last change
—v1.0
Servers it uses
Noneruns standalone

What it does

Adapt a historical primary source for classroom use — modifying complexity and length while preserving features for sourcing, close reading, and corroboration. Use when a primary source is too complex for the target age group.

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.

accessibilitydifferentiationdigdisciplinary-literacydocumentationhistorical-thinkingprimary-sourcessource-adaptation

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.md24.2 kB · preview
--- # AGENT SKILLS STANDARD FIELDS (v2) name: historical-source-adapter disable-model-invocation: false user-invocable: true effort: medium # EXISTING FIELDS skill_id: "historical-thinking/historical-source-adapter" skill_name: "Historical Source Adapter" domain: "historical-thinking" version: "1.0" contributor: "Sean Hu" evidence_strength: "moderate" 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 & Reisman (2015) — Disciplinary literacy in history: a toolkit for digital citizenship" - "Wineburg (2007) — Unnatural and essential: the nature of historical thinking" - "Faggella-Luby, Graner, Deshler & Drew (2012) — Building a house on sand: why disciplinary literacy is not sufficient to replace general strategies for adolescent learners who struggle" input_schema: required: - field: "original_source" type: "string" - field: "student_level" type: "string" - field: "target_skills" type: "string" optional: - field: "target_length" type: "string" - field: "central_question" type: "string" - field: "key_passages" type: "string" - field: "eal_considerations" type: "string" - field: "paired_documents" type: "string" output_schema: type: "object" fields: - field: "adapted_source" type: "string" - field: "adaptation_notes" type: "object" - field: "preserved_features" type: "array" - field: "word_bank" type: "array" - field: "analytical_value_check" type: "object" chains_well_with: - "document-based-lesson-designer" - "historical-document-set-curator" - "central-historical-question-evaluator" - "sourcing-skill-builder" - "close-reading-skill-builder" - "text-complexity-analyser" - "vocabulary-tiering-tool" - "language-demand-analyser" - "scaffolded-task-modifier" teacher_time: "3 minutes" tags: ["source-adaptation", "historical-thinking", "primary-sources", "accessibility", "disciplinary-literacy", "differentiation", "DIG"] ---
81# Historical Source Adapter
82
83## What This Skill Does
84
85Adapts a historical primary source for classroom use — modifying language complexity, length, and presentation while preserving the features that make the document analytically valuable for historical thinking. The output includes the adapted source with full attribution, transparent documentation of every change, a list of features preserved for each target skill, a word bank for difficult retained vocabulary, and an analytical value check confirming the adapted version still supports the intended historical thinking skills.
86
87The central tension in source adaptation is between accessibility and authenticity. A source simplified into modern paraphrase is easy to read but analytically dead — if the author's word choices have been replaced, there is nothing left to close-read; if archaic phrasing has been modernised, the document no longer feels like a product of its time. Conversely, an unmodified 17th-century document may be so linguistically impenetrable that students spend all their cognitive resources on decoding and have nothing left for analysis. The goal is the middle ground: a document that students can read with effort but that retains the features — loaded language, source attribution, temporal markers, rhetorical strategies — that make historical thinking possible.
88
89Reisman (2012) addressed this directly in the Reading Like a Historian curriculum. The 83 Document-Based Lessons used primary sources that had been "modified for accessibility" — adapted for the reading level of urban 11th-grade students, many of whom read below the 25th percentile. Crucially, these adaptations preserved the documents' analytical features: source notes remained intact, key language choices were retained, and the modifications were transparent (original and adapted versions were often provided side by side, as in the Pocahontas chapter of Wineburg, Martin & Monte-Sano, 2011). The significant treatment effects for sourcing and close reading suggest that well-adapted sources can support disciplinary reading even with struggling readers.
90
91## Evidence Foundation
92
93Reisman (2012) demonstrated that primary sources modified for accessibility can produce significant gains in historical thinking. Treatment students, including those reading below the 25th percentile, showed significant improvements in sourcing and close reading when working with adapted documents. The adaptations in the RLH curriculum involved shortening documents, glossing archaic vocabulary, and providing both original and adapted versions — but did not paraphrase the author's voice or remove source attribution. The finding that struggling readers in the treatment condition outperformed their counterparts on historical thinking (ηp² = .17) and factual knowledge (ηp² = .22) suggests that accessibility modifications do not compromise analytical value when done carefully.
94
95Wineburg, Martin, and Monte-Sano (2011) provided concrete examples of source adaptation in the Pocahontas chapter. Smith's 1608 and 1624 accounts appear in both original and adapted forms, with a word bank for archaic terms. The adapted versions preserve the key analytical features: the source attribution (author, date, publication), the contrasting language ("kindly" vs. "barbarous"), and the narrative structure. What is modified is sentence complexity and archaic spelling — changes that reduce the decoding burden without altering the analytical opportunity.
96
97Wineburg and Reisman (2015) argued that disciplinary literacy in history requires engagement with the author's actual language — sourcing depends on the source note, close reading depends on word choice, contextualisation depends on temporal markers. Generic reading strategies (summarising, predicting) can be applied to paraphrased documents, but disciplinary strategies cannot. This means that source adaptation must preserve the features that disciplinary reading targets, even as it modifies the features that obstruct access.
98
99Faggella-Luby et al. (2012) argued that general reading strategies "may even form the bedrock of fluent reading" — students who cannot decode the text cannot analyse it. This supports the case for adaptation: if a document is so linguistically complex that students cannot read it fluently, the historical thinking skills that depend on fluent reading are inaccessible. Adaptation is not a concession to lower standards but a prerequisite for disciplinary engagement.
This is a preview of SKILL.md. Download or install the skill to get the whole thing.
In the file
SKILL.md3,388 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.

≈1,170
always loaded
The name and description, so the model knows the skill exists and when to reach for it.
4,880
on trigger
The instruction body, read only when the skill fires.
3.0%
of a 200k window
Ten skills this size would take about 30% of the window before you open a file.
050k100k150k200k context window

6k 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, 24.2 kB on disk. A bundle is text throughout: the instructions the model reads, plus the templates it fills in.

  • SKILL.md24.2 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.

# Historical Source Adapter · 6k tokens when loaded · macOS, Linux mkdir -p .claude/skills && t=$(mktemp -d) && curl -fsSL -o "$t/bundle.tar.gz" https://mcprush.com/api/skills/historical-source-adapter/bundle.tar.gz && tar -xzf "$t/bundle.tar.gz" -C "$t" && [ -d "$t/historical-source-adapter" ] && { [ ! -e .claude/skills/historical-source-adapter ] || { mv .claude/skills/historical-source-adapter "$t/.previous" && echo "Previous copy moved to $t/.previous"; }; } && mv "$t/historical-source-adapter" .claude/skills/ && echo "Installed .claude/skills/historical-source-adapter"
On Windows, or any OS with Node 20+
npx mcprush@latest skill add garethmanning/historical-source-adapter

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/historical-source-adapter/ 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/historical-source-adapter/bundle.tar.gz && tar -xzf "$t/bundle.tar.gz" -C "$t" && [ -d "$t/historical-source-adapter" ] && { [ ! -e ~/.claude/skills/historical-source-adapter ] || { mv ~/.claude/skills/historical-source-adapter "$t/.previous" && echo "Previous copy moved to $t/.previous"; }; } && mv "$t/historical-source-adapter" ~/.claude/skills/ && echo "Installed ~/.claude/skills/historical-source-adapter" (macOS, Linux) — or add --global to the npx line. The curl line replaces .claude/skills/historical-source-adapter/ 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/historical-source-adapter

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