Sourcing Skill Builder

Build students' capacity to interrogate a historical source before reading — asking who authored it, when, why, and what this means for…

Context cost
8.7k tokensestimated from the bundle, loaded when it triggers
Bundle
1 file · 34.8 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 interrogate a historical source before reading — asking who authored it, when, why, and what this means for reliability. Use when students read documents without attending to authorship.

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.

digdisciplinary-literacydocument-analysisdocumentationhistorical-thinkingprimary-sourcessourcingwineburg

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.md34.8 kB · preview
--- # AGENT SKILLS STANDARD FIELDS (v2) name: sourcing-skill-builder disable-model-invocation: false user-invocable: true effort: medium # EXISTING FIELDS skill_id: "historical-thinking/sourcing-skill-builder" skill_name: "Sourcing 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" - "Wineburg (2007) — Unnatural and essential: the nature of historical thinking" - "Gottlieb & Wineburg (2012) — Between Veritas and Communitas: epistemic switching in the reading of academic and sacred history" - "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" 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: "sourcing_progression" type: "object" - field: "explicit_instruction_sequence" type: "object" - field: "guiding_questions" type: "array" - field: "common_failure_patterns" type: "array" - field: "assessment_indicators" type: "object" chains_well_with: - "close-reading-skill-builder" - "contextualisation-skill-builder" - "corroboration-skill-builder" - "historical-thinking-strategy-modelling-guide" - "document-based-lesson-designer" - "historical-source-adapter" - "historical-thinking-assessment-designer" - "source-credibility-evaluation-protocol" teacher_time: "3 minutes" tags: ["sourcing", "historical-thinking", "primary-sources", "disciplinary-literacy", "document-analysis", "Wineburg", "DIG"] ---
78# Sourcing Skill Builder
79
80## What This Skill Does
81
82Designs targeted instruction to develop students' sourcing practice — the habit of interrogating who authored a historical document, when, why, for what audience, and what this means for the document's reliability — before and during reading. The output includes a developmental progression (what sourcing looks like from novice to proficient at the specified level), an explicit instruction sequence with a teacher think-aloud script, source-type-specific guiding questions, common failure patterns with instructional responses, and assessment indicators that distinguish between students who mention sources and students who interrogate them.
83
84Sourcing is the foundational move in historical thinking. Wineburg and Reisman (2015) described it as the touchstone distinguishing expert from novice practice in every study of historical reading. But there is a critical distinction between routinised sourcing (students habitually glance at the source note because they have been trained to) and analytical sourcing (students use source information to generate hypotheses about the document's reliability, purpose, and relationship to other accounts before reading a word of the text). Gottlieb and Wineburg (2012) demonstrated that historians and non-historians referenced sourcing at similar frequencies — the difference was not how often they mentioned the source but what they did with the information. A scientist noted the authors' names and moved on. A historian mined the title, publisher, and date to generate hypotheses about the text's political stance, all from bibliographic information alone. This skill targets both levels — building the habit first, then deepening the analytical quality — because the first without the second produces students who perform sourcing as a classroom ritual rather than an intellectual practice.
85
86AI is specifically valuable here because diagnosing why students fail to source requires distinguishing between several different failure modes that require different instructional responses. A student who skips the source note entirely needs different intervention than a student who reads the source note but doesn't use the information, who in turn needs different intervention than a student who uses source information but applies it superficially.
87
88## Evidence Foundation
89
90Wineburg (1991) established sourcing as an expert-novice discriminator through a landmark study comparing how historians and high school students read historical documents. Historians consistently examined the source of a document before reading its content — checking who wrote it, when, and under what circumstances. Students dove straight into the text. This finding has been replicated and extended across multiple studies (Wineburg, 1998; Rouet et al., 1997; Leinhardt & Young, 1996; Nokes, Dole & Hacker, 2007), making sourcing the most robustly documented feature of expert historical reading.
91
92Wineburg (2007) explained why sourcing is cognitively "unnatural" through the mechanisms of spread of activation and the availability heuristic. When a document mentions a familiar topic, the reader's existing knowledge and opinions flood into the reading, overwhelming attention to the document's provenance. Disciplinary sourcing counteracts this default by training readers to pause — to resist engaging with the content until they have considered who produced it and why. Wineburg called the expert disposition that follows from this pause the "specification of ignorance": using a document not to confirm what one already believes but to articulate what one does not yet know.
93
94Gottlieb and Wineburg (2012) refined the picture by showing that the quantity of sourcing references was similar between historians and PhD scientists/engineers — both groups noticed and mentioned source information. The difference was qualitative. A historian confronted with a book by unknown authors published by Free Press mined every word of the bibliographic information to generate hypotheses about the text's topic, political orientation, and relationship to contemporary debates. Scientists noted the same information and moved on. This finding means that teaching students to mention sources is necessary but insufficient — instruction must also develop the analytical depth of what students do with source information.
95
96Reisman (2012) demonstrated that sourcing is teachable through explicit instruction in urban high school classrooms. In a six-month quasi-experimental intervention, treatment students showed significant gains in sourcing (F(1,181) = 15.89, p < .001, ηp² = .08). Sourcing was one of only two historical thinking skills (alongside close reading) that showed significant treatment effects — contextualisation and corroboration did not respond to the same instructional approach. Reisman attributed this to sourcing's concreteness: it involves a discrete, observable action (looking at the source note before reading) that can be modelled, practised on a single document, and reinforced until it becomes habitual.
This is a preview of SKILL.md. Download or install the skill to get the whole thing.
In the file
SKILL.md5,099 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.
7,580
on trigger
The instruction body, read only when the skill fires.
4.3%
of a 200k window
Ten skills this size would take about 44% of the window before you open a file.
050k100k150k200k context window

8.7k 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, 34.8 kB on disk. A bundle is text throughout: the instructions the model reads, plus the templates it fills in.

  • SKILL.md34.8 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.

# Sourcing Skill Builder · 8.7k tokens when loaded · macOS, Linux mkdir -p .claude/skills && t=$(mktemp -d) && curl -fsSL -o "$t/bundle.tar.gz" https://mcprush.com/api/skills/garethmanning-sourcing-skill-builder/bundle.tar.gz && tar -xzf "$t/bundle.tar.gz" -C "$t" && [ -d "$t/sourcing-skill-builder" ] && { [ ! -e .claude/skills/sourcing-skill-builder ] || { mv .claude/skills/sourcing-skill-builder "$t/.previous" && echo "Previous copy moved to $t/.previous"; }; } && mv "$t/sourcing-skill-builder" .claude/skills/ && echo "Installed .claude/skills/sourcing-skill-builder"
On Windows, or any OS with Node 20+
npx mcprush@latest skill add garethmanning/sourcing-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/sourcing-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/garethmanning-sourcing-skill-builder/bundle.tar.gz && tar -xzf "$t/bundle.tar.gz" -C "$t" && [ -d "$t/sourcing-skill-builder" ] && { [ ! -e ~/.claude/skills/sourcing-skill-builder ] || { mv ~/.claude/skills/sourcing-skill-builder "$t/.previous" && echo "Previous copy moved to $t/.previous"; }; } && mv "$t/sourcing-skill-builder" ~/.claude/skills/ && echo "Installed ~/.claude/skills/sourcing-skill-builder" (macOS, Linux) — or add --global to the npx line. The curl line replaces .claude/skills/sourcing-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/sourcing-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