Agent skill

Scholarly Citation

by alfadur7 in alfadur7/llm-wiki-newsroom

Verifiable-attribution and citation-discipline craft — atomic claim decomposition, evidence grading (primary/analysis/forecast tiers), claimant attribution, citation typing…

MITAuto-check passedKnowledge Management

Install Scholarly Citation

skills CLI
$ npx skills add alfadur7/llm-wiki-newsroom --skill scholarly-citation -a claude-code

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

GitHub CLI
$ gh skill install alfadur7/llm-wiki-newsroom scholarly-citation --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/alfadur7/llm-wiki-newsroom.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/scholarly-citation .claude/skills/scholarly-citation && 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
scholarly-citation
GitHub stars
171
Token cost
~1.7k tokens
SKILL.md length
741 words
Files
3
Skills in repo
5
Repo updated
First seen
Licence
MIT

At a glance

Verifiable-attribution and citation-discipline craft — atomic claim decomposition, evidence grading (primary/analysis/forecast tiers), claimant attribution, citation typing…

  • Reviewing a reference
  • SKILL.md covers Claim atomization & grading…, Claimant attribution…, Citation typing (cit.cite-type… and Source anchoring (cit.anchor ·…, plus 3 more sections
  • Runs Python scripts from its folder
  • Synthesis page that attributes and cites source-based claims so they stay traceable

What it does

Scholarly Citation is an agent skill from alfadur7/llm-wiki-newsroom. Verifiable-attribution and citation-discipline craft — atomic claim decomposition, evidence grading (primary/analysis/forecast tiers), claimant attribution, citation typing (cites/references/contradicts/defines), source anchoring (Xanadu). Use when writing or reviewing a reference or synthesis page that attributes and cites source-based claims so they stay traceable, or when claim attribution, citation typing, or evidence grading is needed.

Its SKILL.md is about 1.7k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `checks.py` and `criteria.json`).

It sits in Knowledge Management, covering Citation management. The repository describes itself as: Harness engineering applied to knowledge production: a self-evolving multi-agent newsroom that turns your documents into a cross-linked markdown wiki. A "reground" loop pulls… The licence is MIT.

When your agent uses it

  • Reviewing a reference
  • Synthesis page that attributes and cites source-based claims so they stay traceable
  • Claim attribution
  • Citation typing

Example prompts

  • “/scholarly-citation”

Requirements

  • Python 3

What it can do on your machine

Read from SKILL.md and the folder at commit 03173ce. 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

    Ships script files (Python), which the agent can run.

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

  • Network

    Links to these hosts (documentation or services it may open):

    • scite.ai
    • en.wikipedia.org
    • owl.purdue.edu
    • elicit.com
    • iicm.tugraz.at
    • apastyle.apa.org

    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

Scholarly Citation loads about 1.7k tokens when it runs. Until then it costs about 116 tokens; SKILL.md has 741 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~116
When it runs · the whole SKILL.md, loaded when a task matches
~1.7k

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 alfadur7/llm-wiki-newsroom at commit 03173ce, republished under its MIT licence (© alfadur7). 741 words, ~1,685 tokens.

Download SKILL.mdSave it as .claude/skills/scholarly-citation/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.
name
scholarly-citation
description
Verifiable-attribution and citation-discipline craft — atomic claim decomposition, evidence grading (primary/analysis/forecast tiers), claimant attribution, citation typing (cites/references/contradicts/defines), source anchoring (Xanadu). Use when writing or reviewing a reference or synthesis page that attributes and cites source-based claims so they stay traceable, or when claim attribution, citation typing, or evidence grading is needed.

scholarly-citation

Verifiable-attribution craft drawn from scholarly/scientific citation traditions (citation classification, typing, anchoring). It ensures every claim in this wiki is atomized, evidence-graded, attributed to a speaker, typed by citation meaning, and anchored to a source location — and therefore traceable. Unlike the three borrowed traditions (narrative, exec summary, encyclopedic neutrality), this craft synthesizes external sources into an atomic-claim schema and is the project's signature. criteria.json is the SoT for each criterion's definition, comparator, and source; wiki-global state (page existence·hub type·section titles) is injected by the orchestrator (tools/_lint/source.py). The schema literals (## Key Claims, [fact], cites: etc.) are the wiki's actual schema markers and section headers.

Claim atomization & grading (cit.grade-marker · cit.atomic · cit.composite-split)

One claim, one line, one utterance. Each line of ## Key Claims (Key Claims) marks an evidence grade — [fact] (primary source), [analysis] (secondary analysis), [forecast] (forecast). Putting two subjects' claims on one line (joined by "and"/"&" or a comma series spanning two hubs; ko: the conjunctions 와/및), or chaining verb phrases on one line ("…did, and …did"; ko: ~했고, ~했다), breaks atomicity.

Every claim is bound to who said it. The slot right after the grade marker names the speaker — a [[wikilink]] when they have a page, their plain-text real name and role when they fall below the page-creation threshold. What WP:ASF requires is the named source; the wikilink is one means to it, so demanding a link from a speaker who cannot have a page only pushes the author to link some other entity. Anonymous or collective subjects ("the government"·"industry sources"; ko 정부는·업계에서는) stay forbidden in either form ("avoid stating opinions as facts"; attribute them to a named source), as does naming in plain text a page that does exist. A blockquote names its speaker (APA author-date principle — identify the cited author), wikilinked when that speaker has a page. A speaker with no page stays plain text with their role spelled out. Any target that is linked must exist as a real page.

Citation typing (cit.cite-type · cit.cite-distribution · cit.cite-type-hub)

Each line of ## Connections (Connections) types the citation's meaning — cites: (direct grounds)·references: (context)·contradicts: (dispute)·defines: (definition). This extends scite Smart Citations' Supporting / Mentioning / Contrasting classes (with defines: added). If every line collapses to the default-safe references:, that signals avoidance of meaning classification. defines: points only to a concept hub.

Source anchoring (cit.anchor · cit.anchor-valid)

An external-evidence citation anchors to the source's section — [[slug#section]] (ko: [[slug#섹션]]). This applies Xanadu citation anchoring (visible links to the precise source location, Ted Nelson) at the source level; a gradual migration, so 0% still passes (advisory), but the anchor target's slug and section must exist.

Show full SKILL.md (311 more words)Show less

Synthesis citation integrity (cit.cite-consistency · cit.grounding · cit.anchor-evidence)

A piece synthesizing many sources follows Select→Read→Cite discipline — the declared source set (frontmatter) is the top set, and both the sources read and the sources cited in the body are subsets of it.

  • cit.cite-consistency — every source cited in the body is registered in the declared source list (body ⊆ declaration). Citing an undeclared source is an editorial slip (omission).
  • cit.grounding — a source offered as representative evidence must actually be read and used. When at least one of the source's direct-quote / key-claim items appears in the body as a substring, that is objective evidence of having read it (writing from a one-line summary by memory/guess risks divergence from the source). The deterministic lint blocks only the "never read at all" extreme; full read-through rests on editor self-discipline.
  • cit.anchor-evidence — when a direct quote is placed in representative evidence, mark the citation location with a source section anchor ([[slug#section]]; ko [[slug#섹션]]) — the same Xanadu principle applied to synthesis evidence. A gradual migration, so advisory.

Schema meta-use (cit.grade-meta · cit.cite-type-meta)

The synthesizing piece's narrative consciously reflects the evidence-grade ([fact]·[analysis]·[forecast]) and citation-type (cites:·references:·contradicts:·defines:) schema attached to sources — noting which grades the evidence base rests on, the dominant claimant, strong coupling (cites) vs context (references) — to deepen attribution. Confine attribution strength to factual statements; do not let it spill into verdict conclusions. Deterministic measurement (count_grade_meta·count_cite_type_meta) counts grade/cite-type meta expressions as advisory; the lints judge the cite-type count only under WIKI_LANG=ko.

Sources

Each URL points to the relevant page as of the last verification.

© alfadur7, 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 2 other files in .claude/skills/scholarly-citation of alfadur7/llm-wiki-newsroom.

  • SKILL.md
  • checks.py
  • criteria.json

Open the folder on GitHubat commit 03173ce

Compare with similar skills

Scholarly Citation 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.

Scholarly Citation compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Scholarly Citation this skillalfadur7/llm-wiki-newsroom171—~1.7kAutomated safety check: PassMIT
Llmwikiatomicstrata/llm-wiki-compiler2.2k—~814Automated safety check: PassMIT
Corgispec Askricoyudog/Coding_Corgi_flow104—~689Automated safety check: PassNone
Evidence ExtractoropenJiuwen-ai/sciencediscovery159—~4.6kAutomated safety check: PassApache-2.0
Kb Answertechwolf-ai/ai-first-toolkit132—~1.5kAutomated safety check: PassMIT
Source Grounded Research ReportNeuroAIHub/BrainPilot1.1k—~503Automated safety check: PassAGPL-3.0

Similar skills

  • Llmwiki

    atomicstrata/llm-wiki-compiler

    Build and use a persistent, citation-traceable knowledge wiki from documents, research papers, notes, or project documentation.

    2.2k GitHub stars~814 tokensUpdated yesterday
    Knowledge ManagementAuto-check passed
  • Corgispec Ask

    ricoyudog/Coding_Corgi_flow

    Answer pending Obsidian questions from CorgiSpec Memory/Wiki with early-stop retrieval, source citations, and a strict file budget.

    104 GitHub stars~689 tokensUpdated 1 mo ago
    Knowledge ManagementAuto-check passed
  • Evidence Extractor

    openJiuwen-ai/sciencediscovery

    A skill your agent uses when a research workflow needs source-grounded evidence extraction from a literaturesources.json package or compatible source list.

    159 GitHub stars~4.6k tokensUpdated yesterday
    Knowledge ManagementAuto-check passed
  • Kb Answer

    techwolf-ai/ai-first-toolkit

    Answer questions using your project's knowledge base with evidence-backed citations.

    132 GitHub stars~1.5k tokensUpdated 12 days ago
    Knowledge ManagementAuto-check passed
  • Source Grounded Research Report

    NeuroAIHub/BrainPilot

    Research a bounded factual, documentation, API, or literature question from authoritative sources and save a self-contained Markdown report with claim-level citations.

    1.1k GitHub stars~503 tokensUpdated 9 days ago
    Knowledge ManagementAuto-check passed
  • Sophosia Reference Guide

    wentorai/research-plugins

    Reference manager with PDF viewer and Markdown note support. An agent skill from wentorai/research-plugins.

    298 GitHub starsUsed in 1 repo~810 tokens
    Knowledge ManagementAuto-check passed

More from alfadur7/llm-wiki-newsroom

  • Guideline Writing

    alfadur7/llm-wiki-newsroom

    Guideline-authoring craft for instruction SoTs (.claude/ guides, CLAUDE.md, plan files) — operative rules vs recital, MUST/SHOULD/MAY force tiers, pruning, bloat control, blind review protocol…

    171 GitHub stars~2.4k tokensUpdated 6 days ago
    Auto-check passed
  • Consulting Writing

    alfadur7/llm-wiki-newsroom

    Management-consulting writing craft — McKinsey SCR (Situation·Complication·Resolution), Minto Pyramid/MECE, BCG bold-bullet executive summary, so-what upfront, numeric precision, Forrester Landscape.

    171 GitHub stars~1.1k tokensUpdated 6 days ago
    Auto-check passed
  • Encyclopedia Writing

    alfadur7/llm-wiki-newsroom

    Encyclopedic neutral-reference writing craft — NPOV (attribute facts not opinions, due weight, neutral faction labels, verdict restraint), summary style and Coatrack avoidance, wikilink conventions…

    171 GitHub stars~2.5k tokensUpdated 6 days ago
    Auto-check passed
  • Journalism Writing

    alfadur7/llm-wiki-newsroom

    Journalism and argumentation writing craft — inverted pyramid, lede, nut graph, kicker, explainer framing, PAGE frames, Toulmin argument (claim/rebuttal/qualifier), Hegelian dialectic, BBC due…

    171 GitHub stars~2.1k tokensUpdated 6 days ago
    Auto-check passed

Questions about Scholarly Citation

What does Scholarly Citation do?

Verifiable-attribution and citation-discipline craft — atomic claim decomposition, evidence grading (primary/analysis/forecast tiers), claimant attribution, citation typing…. Scholarly Citation is an agent skill from alfadur7/llm-wiki-newsroom. Verifiable-attribution and citation-discipline craft — atomic claim decomposition, evidence grading (primary/analysis/forecast tiers), claimant attribution, citation typing (cites/references/contradicts/defines), source anchoring (Xanadu).

When should I use Scholarly Citation?

Scholarly Citation fits situations like: reviewing a reference; synthesis page that attributes and cites source-based claims so they stay traceable; claim attribution; citation typing.

How do I install Scholarly Citation in Claude Code?

Run `npx skills add alfadur7/llm-wiki-newsroom --skill scholarly-citation -a claude-code`. Or copy the skill folder (.claude/skills/scholarly-citation in alfadur7/llm-wiki-newsroom) into .claude/skills/scholarly-citation in your project. Claude Code loads it when a task matches its description.

How do I install Scholarly Citation in Codex?

Run `npx skills add alfadur7/llm-wiki-newsroom --skill scholarly-citation -a codex`. Or copy the skill folder (.claude/skills/scholarly-citation in alfadur7/llm-wiki-newsroom) into .agents/skills/scholarly-citation in your project. Codex loads it when a task matches its description.

Can I use Scholarly Citation 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 alfadur7/llm-wiki-newsroom --skill scholarly-citation -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/scholarly-citation, .gemini/skills/scholarly-citation, .github/skills/scholarly-citation and .opencode/skills/scholarly-citation in your project.

What does Scholarly Citation need to run?

Going by SKILL.md and its folder, Scholarly Citation needs Python for the scripts in its folder. Our summary lists: Python 3.

Does Scholarly Citation access the network?

SKILL.md names 6 domains. As links in the text: scite.ai, en.wikipedia.org, owl.purdue.edu, elicit.com, iicm.tugraz.at and apastyle.apa.org. This is read from the text; nothing was executed.

Is Scholarly Citation 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 Scholarly Citation use?

Scholarly Citation 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 Scholarly Citation use?

About 1.7k tokens (SKILL.md is roughly 6.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Scholarly Citation?

Skills that share tags, products or a category with Scholarly Citation: Llmwiki (atomicstrata/llm-wiki-compiler, 2.2k stars), Corgispec Ask (ricoyudog/Coding_Corgi_flow, 104 stars), Evidence Extractor (openJiuwen-ai/sciencediscovery, 159 stars) and Kb Answer (techwolf-ai/ai-first-toolkit, 132 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Scholarly Citation?

alfadur7 (a GitHub user) maintains it in alfadur7/llm-wiki-newsroom, which has 171 GitHub stars. The repository holds 5 skills in this directory. The repository was last updated on October 5, 2026.

Source: alfadur7/llm-wiki-newsroom on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.