citation-form-check
$
npx mdskill add lyndonkl/claude/citation-form-checkEnforce citation format by flagging bare hyperlinks and missing institutions.
- Ensures external research references follow Author, Institution, Year style.
- Reads shared-context/style-guide.md for citation template requirements.
- Detects bare hyperlinks and title-only references in draft text.
- Returns flagged citations requiring author and institution additions.
SKILL.md
.github/skills/citation-form-checkView on GitHub ↗
---
name: citation-form-check
description: Verifies every paper or named research result cited in a substacker draft uses the inline "Author(s), Institution, Year" form per style-guide, not a bare hyperlink or title-alone reference. Flags bare-hyperlink citations and missing-institution attributions. Use whenever the draft references external research. Trigger keywords: citation, paper citation, bare hyperlink, authors, institution, reference format.
---
# Citation Form Check
## Table of Contents
- [Correct form](#correct-form)
- [Workflow](#workflow)
- [Worked example](#worked-example)
- [Guardrails](#guardrails)
**Related skills:** Called by Editor in voice pass. Reads `shared-context/style-guide.md` for the citation template.
## Correct form
From `style-guide.md`:
> Papers cited in prose: `Author(s), Institution, Year — Title` on first mention. Not a bare hyperlink, not a title alone.
Examples of correct:
- "Chen et al., Google, 2024 showed that retrieval beats parametric recall at the tail."
- "Vaswani et al. (Google Brain, 2017) introduced the Transformer architecture."
- "Dao et al., 2022, on FlashAttention demonstrated that memory is O(N), not O(N²)."
Examples to flag:
- "[this paper](https://arxiv.org/abs/...)" — bare hyperlink without author + institution.
- "A Google paper said…" — no authors.
- "*Attention Is All You Need*" (title only) — no authors, no year.
- "Recent research shows…" — no citation at all.
## Workflow
```
Citation check draft D:
- [ ] Step 1: Detect paper references (arXiv patterns, italicized titles, hyperlinks to paper sites, "a paper")
- [ ] Step 2: For each reference, parse surrounding sentence for author + institution
- [ ] Step 3: If author OR institution missing, flag tier-2 (unless it's the second+ mention of a paper already correctly cited once)
- [ ] Step 4: Suggest the correct form
```
### Detection patterns
- arXiv URLs: `arxiv.org/abs/\d{4}\.\d{4,5}`
- DOIs: `10\.\d+/\S+`
- Italicized titles: `\*[A-Z][^*]+\*` of length ≥3 words (filters out italicized phrases)
- Hyperlinks to paper sites: `(arxiv|openreview|papers\.nips|proceedings)`
- Generic "a paper" / "recent research" / "a Google paper"
### Exemption
If a paper is correctly cited in full on first mention, subsequent mentions can use a short form ("Chen et al. also noted…"). Only first-mention requires full `Author, Institution, Year`.
## Worked example
**Draft**:
> RAG (as shown in [this paper](https://arxiv.org/abs/2005.11401)) beats fine-tuning for recall.
>
> A Google paper found that retrieval dominates for rare facts.
>
> *Attention Is All You Need* is the foundational work.
>
> Chen et al., Google, 2024 — "Fine-Tuning or Retrieval?" — compared both approaches; Chen et al. concluded fine-tuning loses on tail knowledge.
**Flags**:
1. (Tier-2) "[this paper](https://arxiv.org/abs/2005.11401)" — bare hyperlink. Rewrite: "Lewis et al., FAIR, 2020 — *Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks*."
2. (Tier-2) "A Google paper" — no authors. Rewrite: insert authors, year, title.
3. (Tier-2) "*Attention Is All You Need*" — title only. Rewrite: "Vaswani et al., Google Brain, 2017 — *Attention Is All You Need*."
4. (PASS) Chen et al. citation is correct on first mention; second mention (short form) is acceptable.
## Guardrails
1. Citation form is tier-2. The writer can publish with a bare hyperlink; it's a craft miss, not a voice violation.
2. Don't flag mentions of blogs, tools, or GitHub projects — only formal research citations.
3. First mention rule: full form required. Subsequent mentions can be short.
4. If the writer uses a different citation template (e.g., footnote-based), respect the style-guide.
5. Never rewrite a citation without the writer's confirmation — suggest only.
6. Don't flag citations the writer explicitly annotates `[short]` in their draft (convention for intentional short-form on first mention).
## Quick reference
- Input: draft + style-guide.md.
- Output: citation flags with tier-2 severity.
- First mention = full form; subsequent mentions = short form.
More from lyndonkl/claude
- abstraction-concrete-examplesBuilds structured abstraction ladders that translate high-level principles into concrete, actionable examples across 3-5 levels. Bridges communication gaps, reveals hidden assumptions, and tests whether abstract ideas work in practice. Use when explaining concepts at different expertise levels, moving between abstract principles and concrete implementation, identifying edge cases by testing ideas against scenarios, designing layered documentation, decomposing complex problems into actionable steps, or bridging strategy-execution gaps.
- academic-letter-architectGuides the creation of evidence-based academic recommendation letters, reference letters, and award nominations that combine concrete examples, meaningful comparisons, and genuine enthusiasm. Use when writing recommendation letters for students, postdocs, or colleagues, or when user mentions recommendation letter, reference, nomination, letter of support, endorsement, or needs help with strong advocacy and comparative statements.
- adr-architectureDocuments significant architectural and technical decisions with full context, alternatives considered, trade-offs analyzed, and consequences understood. Creates a decision trail that helps teams understand why decisions were made. Use when choosing between technology options, making infrastructure decisions, establishing standards, migrating systems, or when user mentions ADR, architecture decision, technical decision record, or decision documentation.
- adverse-selection-priorProduces a Bayesian prior probability that an offered transaction is +EV for the recipient, given that the counterparty chose to propose it. Applies Akerlof market-for-lemons logic -- if they offered it, they believe it is +EV for them, so the prior that it is +EV for us is materially below 50%. Reusable across trade evaluation, waiver drops (another team dropping a player is also adverse selection), job-offer analysis, M&A, and any "someone offered me this" situation. Use when you receive an unsolicited trade/offer/proposal, analyzing incoming trade prior, evaluating why a counterparty proposed a deal, or when user mentions adverse selection, market for lemons, why did they offer this, incoming trade prior, they proposed it, Bayesian adjustment on received offer.
- alignment-values-north-starCreates actionable alignment frameworks that give teams a shared North Star (direction), values (guardrails), and decision tenets (behavioral standards). Enables autonomous decision-making while maintaining organizational coherence. Use when starting new teams, scaling organizations, defining culture, establishing product vision, resolving misalignment, creating strategic clarity, or when user mentions North Star, team values, mission, principles, guardrails, decision framework, or cultural alignment.
- analogy-weight-checkFor every analogy in a substacker draft, verifies it carries mechanical weight — the analogy does real work explaining the mechanism, not merely decorates it. Cross-references analogy-catalog.md for novelty (is this analogy reused from a prior post?) and domain fit (biology > organizational > sports preferred; physics/military disfavored). Use whenever an analogy appears in the draft. Trigger keywords: analogy weight, decorative, mechanical weight, reused analogy, catalog check, metaphor check.
- answer-uncomfortable-questionTakes one strategic question about substacker ("should we launch paid?", "is this section dead?", "are we writing for the wrong audience?") and produces the mandatory evidence + reasoning + downside triad plus a recommendation. Used 3 times per Growth Strategist review. Trigger keywords: uncomfortable question, strategic question, evidence reasoning downside, triad.
- attribute-performanceFor each substacker post that materially over- or under-performs the rolling baseline (|z| ≥ 1.0), produces a plain-English attribution paragraph with calibrated confidence (high / medium / low / unexplained). Considers subject-line effect, topic zeitgeist, external share, day-of-week, length effect, and audience-notes signals. Labels unexplained outliers explicitly rather than fabricating a story. Use after compute-baseline when outlier posts exist. Trigger keywords: attribution, why did this post work, outlier explanation, performance analysis.
- auction-first-price-shadingComputes the optimal shaded bid for a first-price sealed-bid auction given a true private value, an estimate of the number of competing bidders N, and a value-distribution assumption. Implements the `(N-1)/N` equilibrium shading rule for uniform private values, adjusts for log-normal or empirical value distributions, layers a risk-aversion adjustment, and caps output against the bidder's remaining budget. Domain-neutral auction theory reusable across fantasy sports (baseball FAAB, NBA/NHL waiver auctions), prediction-market limit sizing, sealed procurement bids, and any blind-bid context. Use when user mentions "first-price auction bid", "sealed bid shading", "(N-1)/N", "FAAB bid amount", "auction shading", "optimal bid first-price", "bid for sealed-bid", "blind bid sizing", or when downstream logic needs a principled shade factor rather than an ad-hoc heuristic.
- auction-winners-curse-haircutApplies a Bayesian haircut to a bid valuation for common-value auctions where winning is itself evidence the bidder over-estimated. Takes a raw valuation, a value-type classification (common_value / private_value / mixed), the number of informed bidders N, and a signal-dispersion estimate, and returns an adjusted valuation. Domain-neutral and reusable across fantasy FAAB, prediction markets, M&A bids, ad-auction budgets, and any generic bidding context. Use when user mentions "winner's curse", "common value auction", "valuation haircut", "adverse valuation", "Bayesian bid adjustment", or "over-paying in auction".