Close Reading Skill Builder

Build students' capacity to read historical documents closely — attending to word choice, tone, and rhetoric as evidence of perspective.

Context cost
6.5k tokensestimated from the bundle, loaded when it triggers
Bundle
1 file · 25.9 kBtext throughout, nothing executable
Licence
not declarednone named by its author
Last change
—v1.0
Servers it uses
Noneruns standalone

What it does

Build students' capacity to read historical documents closely — attending to word choice, tone, and rhetoric as evidence of perspective. Use when students summarise sources without analysing language.

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.

close-readingdigdisciplinary-literacydocument-analysisdocumentationhistorical-thinkinglanguage-analysisrhetoric

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.md25.9 kB · preview
--- # AGENT SKILLS STANDARD FIELDS (v2) name: close-reading-skill-builder disable-model-invocation: false user-invocable: true effort: medium # EXISTING FIELDS skill_id: "historical-thinking/close-reading-skill-builder" skill_name: "Close Reading Skill Builder" domain: "historical-thinking" version: "1.0" contributor: "Sean Hu" evidence_strength: "strong" evidence_sources: - "Wineburg (1991) — Historical problem solving: cognitive processes in the evaluation of documentary and pictorial evidence" - "Wineburg (1998) — Reading Abraham Lincoln: an expert/expert study in historical cognition" - "Reisman (2012) — Reading like a historian: a document-based history curriculum intervention in urban high schools" - "Wineburg & Reisman (2015) — Disciplinary literacy in history: a toolkit for digital citizenship" - "Wineburg, Martin & Monte-Sano (2011) — Reading like a historian: teaching literacy in middle and high school history classrooms" - "Leinhardt & Young (1996) — Two texts, three readers: distance and expertise in reading history" input_schema: required: - field: "historical_topic" type: "string" - field: "student_level" type: "string" - field: "current_challenge" type: "string" optional: - field: "source_type" type: "string" - field: "available_documents" type: "string" - field: "curriculum_framework" type: "string" - field: "prior_instruction" type: "string" output_schema: type: "object" fields: - field: "close_reading_progression" type: "object" - field: "explicit_instruction_sequence" type: "object" - field: "language_analysis_prompts" type: "array" - field: "common_failure_patterns" type: "array" - field: "assessment_indicators" type: "object" chains_well_with: - "sourcing-skill-builder" - "contextualisation-skill-builder" - "corroboration-skill-builder" - "historical-thinking-strategy-modelling-guide" - "document-based-lesson-designer" - "historical-source-adapter" - "historical-thinking-assessment-designer" - "disciplinary-writing-scaffold" - "text-complexity-analyser" teacher_time: "3 minutes" tags: ["close-reading", "historical-thinking", "disciplinary-literacy", "language-analysis", "document-analysis", "rhetoric", "DIG"] ---
79# Close Reading Skill Builder
80
81## What This Skill Does
82
83Designs targeted instruction to develop students' close reading of historical documents — the practice of attending to an author's word choice, claims, evidence, tone, and rhetorical strategies to assess argument, perspective, and probity. The output includes a developmental progression, an explicit instruction sequence with a teacher think-aloud script, language analysis prompts specific to the source type, common failure patterns with instructional responses, and assessment indicators.
84
85Close reading in history is distinct from close reading in English or Language Arts. Literary close reading attends to aesthetic features — imagery, symbolism, narrative voice. Historical close reading attends to language as evidence of the author's perspective, purpose, and relationship to the events described. When a historian reads a document closely, they ask: what claims is the author making? What evidence do they offer? What words reveal their stance? What is the gap between what the author says and what they might mean? Wineburg (1998) demonstrated this in a study where historians reading Lincoln's documents attended to the strategic deployment of language — not its beauty — to assess Lincoln's political positioning. The question driving historical close reading is not "What does this text mean?" but "What does this author's language reveal about their perspective, and what does that tell us about the reliability of their account?"
86
87Reisman (2012) found that close reading, alongside sourcing, was one of only two historical thinking skills that showed significant treatment effects in her intervention study (F(1,181) = 9.62, p = .002, ηp² = .05). Like sourcing, close reading involves concrete, demonstrable actions — underlining loaded language, identifying claims and evidence, noting shifts in tone — that can be modelled on a single document. This concreteness makes it more immediately teachable than contextualisation or corroboration, which require intertextual reasoning.
88
89## Evidence Foundation
90
91Wineburg (1991) identified close reading as a core component of expert historical reasoning. Historians in his study attended to the language of documents as evidence of perspective — noticing word choices that revealed an author's stance, identifying claims that went beyond what the evidence supported, and detecting rhetorical strategies designed to persuade. Students, by contrast, read for content: they extracted information from documents without attending to how the information was presented or what the presentation revealed about the author.
92
93Leinhardt and Young (1996) deepened this finding by showing that expert historians constructed what they called an "Event Model" — an integrated representation built from close attention to how multiple documents used language differently to describe the same events. The linguistic differences between accounts were not noise to be filtered out but signal to be analysed: why does one author use "rebellion" where another uses "revolution"? The answer reveals not a vocabulary preference but a political commitment.
94
95Wineburg (1998) demonstrated historical close reading in action through a study of historians reading Lincoln's documents. Experts attended to Lincoln's strategic deployment of language — how he positioned himself differently for different audiences, how his word choices shifted over time, and what the gaps between his public statements and private letters revealed about his actual views. This is close reading not as literary appreciation but as evidentiary analysis: the author's language is data about the author's perspective.
96
97Reisman (2012) operationalised close reading in the Reading Like a Historian curriculum through guiding questions: What claims does the author make? What evidence does the author use? What language does the author use to persuade? How does the document's language indicate the author's perspective? Treatment effects for close reading were significant, suggesting that these concrete analytical moves are teachable through explicit instruction and practice.
This is a preview of SKILL.md. Download or install the skill to get the whole thing.
In the file
SKILL.md3,672 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.

≈1,120
always loaded
The name and description, so the model knows the skill exists and when to reach for it.
5,355
on trigger
The instruction body, read only when the skill fires.
3.2%
of a 200k window
Ten skills this size would take about 32% of the window before you open a file.
050k100k150k200k context window

6.5k 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, 25.9 kB on disk. A bundle is text throughout: the instructions the model reads, plus the templates it fills in.

  • SKILL.md25.9 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.

# Close Reading Skill Builder · 6.5k tokens when loaded · macOS, Linux mkdir -p .claude/skills && t=$(mktemp -d) && curl -fsSL -o "$t/bundle.tar.gz" https://mcprush.com/api/skills/close-reading-skill-builder/bundle.tar.gz && tar -xzf "$t/bundle.tar.gz" -C "$t" && [ -d "$t/close-reading-skill-builder" ] && { [ ! -e .claude/skills/close-reading-skill-builder ] || { mv .claude/skills/close-reading-skill-builder "$t/.previous" && echo "Previous copy moved to $t/.previous"; }; } && mv "$t/close-reading-skill-builder" .claude/skills/ && echo "Installed .claude/skills/close-reading-skill-builder"
On Windows, or any OS with Node 20+
npx mcprush@latest skill add garethmanning/close-reading-skill-builder

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

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