Agent skill

Citation Hygiene

by mohitagw15856 in mohitagw15856/pm-claude-skills

Keep citations honest in business documents — every load-bearing claim sourced, links that actually contain the claim, the as-of dates that keep numbers honest, and the internal-vs-external sourcing…

MITAuto-check passedResearch & Science

Install Citation Hygiene

skills CLI
$ npx skills add mohitagw15856/pm-claude-skills --skill citation-hygiene -a claude-code

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

GitHub CLI
$ gh skill install mohitagw15856/pm-claude-skills citation-hygiene --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/mohitagw15856/pm-claude-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/citation-hygiene .claude/skills/citation-hygiene && 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
citation-hygiene
GitHub stars
1.4k
Token cost
~1.4k tokens
SKILL.md length
729 words
Files
1
Skills in repo
1,348
Repo updated
First seen
Licence
MIT

At a glance

Keep citations honest in business documents — every load-bearing claim sourced, links that actually contain the claim, the as-of dates that keep numbers honest, and the internal-vs-external sourcing…

  • Works in 5 steps: Triage by load-bearing: the claims that… → The link must contain the claim: the… → Numbers wear dates and denominators: "as… → …
  • Asked check the sourcing in this deck
  • SKILL.md covers What This Skill Produces, Required Inputs, Framework: The Hygiene Rules and Output Format, plus 7 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Citation Hygiene is an agent skill from mohitagw15856/pm-claude-skills. Keep citations honest in business documents — every load-bearing claim sourced, links that actually contain the claim, the as-of dates that keep numbers honest, and the internal-vs-external sourcing rules for decks and memos. Use when asked check the sourcing in this deck, add citations to this doc, our slide says 'studies show' — which studies, or set citation norms for the team. Produces the claim-by-claim audit, the fixes (source found, claim softened, or cut), the citation format for the venue, and the team…

Its SKILL.md is about 1.4k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Research & Science, covering Citation management. The repository describes itself as: 1255 professional Agent Skills for Claude, ChatGPT, Gemini, Cursor & Codex — PRDs, postmortems, leases, medical bills, layoffs, go-bags, new countries. Plain markdown, MIT, in… The licence is MIT.

When your agent uses it

  • Asked check the sourcing in this deck
  • Add citations to this doc
  • Our slide says studies show — which studies
  • Set citation norms for the team

Example prompts

  • “studies show”
  • “/citation-hygiene”

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. Triage by load-bearing: the claims that carry the recommendation, the sizing, or the urgency get the audit; connective prose doesn't. The…
  2. The link must contain the claim: the drive-by cite — a link that discusses the topic but never states the number — is the most common…
  3. Numbers wear dates and denominators: "as of Q2 2026" on every market figure and internal metric ("40% growth" — of what, since when?); an…
  4. Unsourceable claims soften or die: the options, in order — find the source · soften to earned confidence ("we believe, based on [basis]" /…
  5. Venue formats keep it light: slides get the small source line (source, date) per chart/claim · memos get footnotes or inline links · docs…

What it can do on your machine

Read from SKILL.md and the folder at commit 1cbf1f0. 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

    No scripts in the folder and no shell commands in SKILL.md.

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

  • Network

    No URLs in SKILL.md.

    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

Citation Hygiene loads about 1.4k tokens when it runs. Until then it costs about 136 tokens; SKILL.md has 729 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~136
When it runs · the whole SKILL.md, loaded when a task matches
~1.4k

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 mohitagw15856/pm-claude-skills at commit 1cbf1f0, republished under its MIT licence (© mohitagw15856). 729 words, ~1,397 tokens.

Download SKILL.mdSave it as .claude/skills/citation-hygiene/SKILL.md (or your agent's skills folder).
name
citation-hygiene
description
Keep citations honest in business documents — every load-bearing claim sourced, links that actually contain the claim, the as-of dates that keep numbers honest, and the internal-vs-external sourcing rules for decks and memos. Use when asked check the sourcing in this deck, add citations to this doc, our slide says 'studies show' — which studies, or set citation norms for the team. Produces the claim-by-claim audit, the fixes (source found, claim softened, or cut), the citation format for the venue, and the team norm card.

Citation Hygiene Skill

Business documents run on unsourced confidence: "studies show," "industry-standard," the market-size number nobody can trace, the chart with no as-of date. Each unsourced load-bearing claim is a small loan against credibility — called in the moment a skeptic asks "says who?" in front of the room. Citation hygiene is not academia: it's the practical discipline that every claim someone might challenge or act on carries its source, the link actually contains the claim (the classic drive-by cite doesn't), numbers wear their dates, and claims that can't be sourced get softened or cut before the meeting does it for you.

What This Skill Produces

  • The claim audit — the doc's load-bearing claims listed, each: sourced / sourceable / soften / cut
  • The fixes — sources attached (verified to contain the claim — the source-triangulation quick check), softenings drafted, the cut list
  • The venue format — how citations look here: footnotes for memos, the source line for slides, links for docs
  • The norm card — the team's three citation rules, postable

Required Inputs

Ask for these if not provided:

  • The document — and its stakes/venue (the board deck's bar differs from the team memo's; both have one)
  • Which claims are load-bearing — the ones decisions or credibility rest on; hygiene triages (sourcing every sentence is academia cosplay — sourcing none is the current problem)
  • The available sources — where the numbers came from (the analyst's model? a report? memory?) — "memory" is an honest answer that routes to softening
  • Internal-data provenance — for internal numbers: which system, what query, as of when — internal claims need internal citations too ("revenue dashboard, July 15" beats "our data shows")

Framework: The Hygiene Rules

  1. Triage by load-bearing: the claims that carry the recommendation, the sizing, or the urgency get the audit; connective prose doesn't. The test: if challenged in the room, would the author need to defend it? Then it needs its source now, cheaply, instead of live, expensively.
  2. The link must contain the claim: the drive-by cite — a link that discusses the topic but never states the number — is the most common citation fraud, usually accidental (the chain of paraphrase drifted). The verify step: open the source, find the sentence. Absent, the claim inherits the source's actual wording or loses the cite.
  3. Numbers wear dates and denominators: "as of Q2 2026" on every market figure and internal metric ("40% growth" — of what, since when?); an undated number in a living deck becomes silently false on schedule. Internal numbers cite system + date ("CRM export, Jul 15") so the inevitable "that doesn't match my dashboard" resolves in seconds.
  4. Unsourceable claims soften or die: the options, in order — find the source · soften to earned confidence ("we believe, based on [basis]" / "directionally," per the triangulation phrasing rules) · attribute honestly ("our estimate") · cut. What never survives: the bare assertion whose defense is hope.
  5. Venue formats keep it light: slides get the small source line (source, date) per chart/claim · memos get footnotes or inline links · docs get links. The norm card is three lines: load-bearing claims carry sources · numbers carry dates · "studies show" is banned without the study — light enough to enforce, sharp enough to matter.
Show full SKILL.md (211 more words)Show less

Output Format

Citation Audit: [document] — [N] load-bearing claims

The Audit

ClaimStatusFix
[Sourced ✓ (verified-contains) / softened to: "…" / internal-cited / cut]

The Fixes Applied

[Sources attached in venue format · the softened phrasings · the cut list with the credibility logic]

The Venue Format

[The citation style for this document type, shown]

The Norm Card (post this)

[The three rules · the banned phrase list ("studies show", "industry-standard" unaccompanied)]

Quality Checks

  • Load-bearing claims were triaged from connective prose
  • Every attached source was opened and verified to contain the claim
  • Every number carries its date (and internal numbers their system)
  • Unsourceable claims were softened or cut, never left bare
  • The format matches the venue and stays light

Anti-Patterns

  • Do not cite everything — academia cosplay buries the load-bearing sources in noise
  • Do not link topics — the link contains the claim or it's decoration
  • Do not ship undated numbers — they're scheduled falsehoods
  • Do not let "studies show" survive without the studies — it's the tell the whole audit exists for
  • Do not defend unsourceable claims by intensity — soften, attribute, or cut; the room's skeptic is faster than you

Example Trigger Phrases

  • "Check the sourcing in this deck."
  • "Does every claim in this memo have a source?"
  • "Do these links actually say what we claim?"
  • "Set citation norms for the team."

© mohitagw15856, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/citation-hygiene of mohitagw15856/pm-claude-skills.

Open the folder on GitHubat commit 1cbf1f0

Compare with similar skills

Citation Hygiene 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.

Citation Hygiene compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Citation Hygiene this skillmohitagw15856/pm-claude-skills1.4k—~1.4kAutomated safety check: PassMIT
Content Research Writerweapp-tailwindcss/weapp-tailwindcss1.9k25 repos~3.5kAutomated safety check: PassMIT
Systematic Review ScreenerImbad0202/academic-research-skills51k—~8.4kAutomated safety check: PassCustom licence
NetworkxzLanqing/codex-claude-academic-skills4.7k15 repos~3.2kAutomated safety check: PassBSD-3-Clause
Literature Reviewneflibata-feng/MyArxiv-Agent12620 repos~5.9kAutomated safety check: NotesMIT
Openalex Databaseneflibata-feng/MyArxiv-Agent12612 repos~3kAutomated safety check: PassCustom licence

Similar skills

  • Content Research Writer

    weapp-tailwindcss/weapp-tailwindcss

    Assists in writing high-quality content by conducting research, adding citations, improving hooks, iterating on outlines, and providing real-time feedback on each section.

    1.9k GitHub starsUsed in 25 repos~3.5k tokens
    Research & ScienceAuto-check passed
  • Systematic Review Screener

    Imbad0202/academic-research-skills

    Screens records for systematic, scoping and rapid reviews against fixed eligibility rules, using two blinded AI reviewers and a third adjudicator, with traceable PRISMA counts.

    51k GitHub stars~8.4k tokensUpdated yesterday
    Research & ScienceAuto-check passed
  • Networkx

    zLanqing/codex-claude-academic-skills

    Comprehensive toolkit for creating, analyzing, and visualizing complex networks and graphs in Python.

    4.7k GitHub starsUsed in 15 repos~3.2k tokens
    Research & ScienceAuto-check passed
  • Literature Review

    neflibata-feng/MyArxiv-Agent

    Conduct comprehensive, systematic literature reviews using multiple academic databases (PubMed, arXiv, bioRxiv, Semantic Scholar, etc.).

    126 GitHub starsUsed in 20 repos~5.9k tokens
    Research & ScienceAuto-check: notes
  • Openalex Database

    neflibata-feng/MyArxiv-Agent

    Query and analyze scholarly literature using the OpenAlex database.

    126 GitHub starsUsed in 12 repos~3k tokens
    Research & ScienceAuto-check passed
  • Citation Verification Guide

    Galaxy-Dawn/claude-scholar

    Reference guidance for checking every citation in academic writing against canonical sources such as DOI, arXiv, CrossRef and Semantic Scholar, to catch fake or wrong references.

    5.7k GitHub starsUsed in 2 repos~1.9k tokens
    Research & ScienceAuto-check passed

More from mohitagw15856/pm-claude-skills

All 1,348 skills in this repo
  • Car Tco

    mohitagw15856/pm-claude-skills

    Compare the total cost of car ownership across buy-new, buy-used, lease, and keep-your-current-car — depreciation, insurance, maintenance ramp, and fuel over a real horizon, not just the monthly…

    1.4k GitHub stars~1.1k tokensUpdated yesterday
    Auto-check passed
  • Cs Health Scorecard

    mohitagw15856/pm-claude-skills

    Build a customer health scorecard for a specific account. An agent skill from mohitagw15856/pm-claude-skills.

    1.4k GitHub stars~2.4k tokensUpdated yesterday
    Auto-check passed
  • Exit Waterfall

    mohitagw15856/pm-claude-skills

    Compute who gets what at each exit price from a cap table — liquidation preferences, conversion points, and where the founders' share collapses.

    1.4k GitHub stars~1.1k tokensUpdated yesterday
    Auto-check passed
  • Feature Prioritisation

    mohitagw15856/pm-claude-skills

    Apply prioritisation frameworks (RICE, MoSCoW, Kano, ICE, Opportunity Scoring) to rank features and backlog items.

    1.4k GitHub stars~2k tokensUpdated yesterday
    Auto-check passed
  • Fire Number

    mohitagw15856/pm-claude-skills

    Compute a financial-independence (FIRE) target and years-to-reach with every assumption labeled as an assumption — plus a sensitivity table instead of a single false-precision answer.

    1.4k GitHub stars~1.1k tokensUpdated yesterday
    Auto-check passed
  • Freelance Rate

    mohitagw15856/pm-claude-skills

    Derive a freelance day/hourly rate backwards from target income, honest billable utilization, overhead, and the self-employment tax premium — the arithmetic that proves a rate is not salary÷2000.

    1.4k GitHub stars~1.2k tokensUpdated yesterday
    Auto-check passed

Questions about Citation Hygiene

What does Citation Hygiene do?

Keep citations honest in business documents — every load-bearing claim sourced, links that actually contain the claim, the as-of dates that keep numbers honest, and the internal-vs-external sourcing…. Citation Hygiene is an agent skill from mohitagw15856/pm-claude-skills. Keep citations honest in business documents — every load-bearing claim sourced, links that actually contain the claim, the as-of dates that keep numbers honest, and the internal-vs-external sourcing rules for decks and memos.

When should I use Citation Hygiene?

Citation Hygiene fits situations like: asked check the sourcing in this deck; add citations to this doc; our slide says studies show — which studies; set citation norms for the team.

How do I install Citation Hygiene in Claude Code?

Run `npx skills add mohitagw15856/pm-claude-skills --skill citation-hygiene -a claude-code`. Or copy the skill folder (skills/citation-hygiene in mohitagw15856/pm-claude-skills) into .claude/skills/citation-hygiene in your project. Claude Code loads it when a task matches its description.

How do I install Citation Hygiene in Codex?

Run `npx skills add mohitagw15856/pm-claude-skills --skill citation-hygiene -a codex`. Or copy the skill folder (skills/citation-hygiene in mohitagw15856/pm-claude-skills) into .agents/skills/citation-hygiene in your project. Codex loads it when a task matches its description.

Can I use Citation Hygiene 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 mohitagw15856/pm-claude-skills --skill citation-hygiene -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/citation-hygiene, .gemini/skills/citation-hygiene, .github/skills/citation-hygiene and .opencode/skills/citation-hygiene in your project.

What does Citation Hygiene need to run?

SKILL.md names no scripts, command-line tools or credentials: Citation Hygiene is instructions for the agent only.

Does Citation Hygiene access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Citation Hygiene 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 Citation Hygiene use?

Citation Hygiene 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 Citation Hygiene use?

About 1.4k tokens (SKILL.md is roughly 5.6k 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 Citation Hygiene?

Skills that share tags, products or a category with Citation Hygiene: Content Research Writer (weapp-tailwindcss/weapp-tailwindcss, 1.9k stars), Systematic Review Screener (Imbad0202/academic-research-skills, 51k stars), Networkx (zLanqing/codex-claude-academic-skills, 4.7k stars) and Literature Review (neflibata-feng/MyArxiv-Agent, 126 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Citation Hygiene?

mohitagw15856 (a GitHub user) maintains it in mohitagw15856/pm-claude-skills, which has 1,434 GitHub stars. The repository holds 1,348 skills in this directory. The repository was last updated on October 9, 2026.

Source: mohitagw15856/pm-claude-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.