writing-legal
Internal skill for academic legal writing. Loaded by /writing when style=legal. Based on Volokh's "Academic Legal Writing".
What this skill does
# Academic Legal Writing
Style guide for law review articles, seminar papers, and legal scholarship based on Eugene Volokh's *Academic Legal Writing*.
## On Skill Load
**Step 1: Load base writing rules**
Read `${CLAUDE_SKILL_DIR}/../../skills/writing/SKILL.md` and follow its instructions.
**Step 2: Check for active workflow**
If `.planning/ACTIVE_WORKFLOW.md` exists and `workflow: writing`, update `style: legal`.
If no `.planning/PRECIS.md` exists in the project:
- Suggest: "No PRECIS.md found. Consider `/writing` to set up thesis, audience, and claims first."
**Step 3: Apply legal-specific rules below**
## When to Use
Invoke this skill for:
- Law review articles and student notes
- Seminar papers and legal scholarship
- Academic legal writing with footnotes
- Editing legal prose for structure and argument
**For general writing**: Use `/writing` skill (Strunk & White)
**For economics/finance**: Use `/writing-econ` skill (McCloskey)
## Required Skills
When generating Word documents (`.docx`), you MUST load the `/docx` skill first. The docx skill provides proper document manipulation capabilities.
## Template Requirement
**Template location:** `templates/law_review_template.docx`
When creating or converting a docx, load `references/formatting.md` for heading styles, body text styles, pandoc `--reference-doc` usage, and the document creation gate function.
## Enforcement
### IRON LAW #1: NO DOCX WITHOUT TEMPLATE FIRST
Before creating ANY Word document for legal writing:
1. Load the `/docx` skill
2. Copy `templates/law_review_template.docx` as the base
3. THEN add content to the template copy
If you created a blank docx without the template, DELETE IT and START OVER with the template.
### IRON LAW #2: NO CLAIM WITHOUT CONFRONTING COUNTERARGUMENTS
If your draft makes a prescriptive claim but doesn't address obvious objections, DELETE the section and START OVER. Legal scholarship requires anticipating and answering counterarguments, not ignoring them.
### IRON LAW #3: NO SECONDARY SOURCE CITATIONS FOR PRIMARY SOURCES
If you cite a case/statute/historical fact via an intermediate source (law review, treatise), DELETE the citation and READ THE ORIGINAL. Even Supreme Court opinions misstate precedents.
### Rationalization Table - STOP If You Think:
| Excuse | Reality | Do Instead |
|--------|---------|------------|
| "This article discusses..." | Bores reader instantly | START with concrete problem or controversy |
| "Table-of-contents paragraph helps" | Readers skip it | INTEGRATE roadmap into intro |
| "Background section comes first" | Not before establishing relevance | SHOW problem first, background second |
| "Case-by-case summary is thorough" | Tedious and unhelpful | SYNTHESIZE: "Courts hold X except Y" |
| "Counterargument would hurt my claim" | Ignoring it hurts worse | CONFRONT and refine claim |
| "Treatise summary is good enough" | Treatises have errors | READ original cases |
| "Arguably" makes my point | Acknowledges controversy without arguing | MAKE the argument explicitly |
| "This metaphor is clear" | Metaphors hide incomplete logic | UNPACK: what's the actual argument? |
### Drive-Aligned Framing
**Citing a case without reading its holding is NOT HELPFUL — the user submits a paper with a wrong citation and reviewers destroy their credibility.** Relying on headnotes or training data is not legal research.
- You omitted the strongest counterargument to make the thesis look stronger. The reader sees through it — your omission destroyed credibility.
- You cited a treatise instead of the primary case. The reader checks and finds the user didn't read the original — your shortcut destroyed their scholarly reputation.
- You wrote the analysis free-form to be "more natural." The argument has no structure — your creativity produced confusion.
### Red Flags - STOP Immediately If You Think:
**Content Red Flags:**
- "Let me write standard intro" → NO. Find concrete problem first.
- "I'll address objections later" → NO. Confront counterarguments NOW.
- "This treatise explains the case" → NO. Read the original case.
- "Background section needs more" → NO. Only include what proves claim.
### Delete & Restart Pattern
**When to delete and restart:**
1. **Intro starts with "This article discusses"** → Delete, start with concrete problem
2. **Background exceeds proof section** → Delete excessive background
3. **Claim made without addressing objections** → Delete section, add counterargument confrontation
4. **Citation chain to primary source** → Delete citation, read and cite original
5. **Unpacked metaphor used as argument** → Delete, write actual logical argument
**How to restart:**
```
Old: "This article discusses privacy concerns in Fourth Amendment doctrine..."
New: "When police drones photograph backyards, does the Fourth Amendment require a warrant?
Courts disagree, but three features of aerial surveillance suggest yes."
```
Start with CONCRETE QUESTION that matters, not abstract topic description.
## Law Review Article Structure
### Introduction
The introduction serves three functions:
1. Persuade readers to keep reading
2. Summarize the article for those who won't read it
3. Frame how readers interpret what follows
**Requirements:**
- Show the problem concretely with specific examples or hypotheticals
- State the claim clearly—what does the article contribute?
- Integrate the roadmap into the introduction, not as a separate paragraph
- Hook the reader: concrete question, engaging story, controversy, or argument to rebut
**Anti-patterns:**
- Starting with "This article discusses..."
- Separate table-of-contents paragraph (readers skip it)
- Historical background before establishing relevance
- Vague generalities about the importance of the topic
### Background Section
Synthesize precedents; do not summarize each case sequentially. Focus only on facts and rules necessary for the argument.
| Problem | Solution |
|---------|----------|
| Summarizing each case | Synthesize: "Courts generally hold X, except when Y" |
| Mini-treatise on the area | Only what's needed for the claim |
| 80% background, 20% claim | Balance must favor the original contribution |
### Proof of the Claim
For prescriptive claims: Show the proposal is both doctrinally sound AND good policy.
**Use a test suite:** Apply the proposal to concrete scenarios (easy cases, hard cases, edge cases) to demonstrate it works.
**Confront counterarguments:**
- Turn problems to advantage: refine the claim, acknowledge uncertainty
- Stay on offense—address objections without becoming defensive
- Acknowledge costs honestly; readers respect candor
**Connect to broader issues:**
- How does the claim relate to parallel debates?
- What subsidiary discoveries emerged?
- What questions remain for future research?
### Conclusion
Keep conclusions brief. The real work is rewriting the introduction after the draft is complete, ensuring it accurately reflects the article's contributions.
## Legal Argument Problems
Common logical problems in legal writing (see `references/volokh-distilled.md` for detailed examples):
| Problem | Issue |
|---------|-------|
| Categorical assertions | "Always" and "never" invite counterexamples |
| Unpacked metaphors | "Slippery slope" and "chilling effect" hide incomplete arguments |
| Missing logical pieces | Syllogisms that skip steps (subject to scrutiny ≠ fails scrutiny) |
| Universal criticisms | "Chilling effect" applies to most laws—explain why *this* one matters |
| Undefined abstractions | "Privacy," "paternalism," "democratic legitimacy" need definitions |
| "Arguably" as argument | Acknowledges controversy but doesn't make the case |
## Evidence and Citation
### Read Original Sources
Never rely on intermediate sources for cases, statutes, or historical facts. Even Supreme Court opinions misstate precedents.
| Source Type | Rule |
|-------------|------|
| Cases/statutes | Read the original; don't trust trRelated in Writing & Docs
jax-development
IncludedUse this skill when the user is writing, debugging, profiling, refactoring, reviewing, benchmarking, parallelising, exporting, or explaining JAX code, or when they mention JAX, jax.numpy, jit, grad, value_and_grad, vmap, scan, lax, random keys, pytrees, jax.Array, sharding, Mesh, PartitionSpec, NamedSharding, pmap, shard_map, Pallas, XLA, StableHLO, checkify, profiler, or the JAX repo. It helps turn NumPy or PyTorch-style code into pure functional JAX, fix tracer/control-flow/shape/PRNG bugs, remove recompiles and host-device syncs, choose transforms and sharding strategies, inspect jaxpr/lowering/IR, and benchmark compiled code correctly.
nature-article-writer
IncludedDrafts, rewrites, diagnostically critiques, and style-calibrates primary research manuscripts for Nature and Nature Portfolio journals. Use when the user wants a Nature-style title, summary paragraph or abstract, introduction, results, discussion, methods, figure legends, presubmission enquiry, cover letter, reviewer response, or when a scientific draft sounds generic, jargon-heavy, structurally weak, or AI-ish and needs precise, broad-reader-friendly prose without inventing data, analyses, or references. Best for primary research articles and letters rather than reviews or press releases unless explicitly adapting one.
deckrd
IncludedDocument-driven framework that derives requirements, specifications, implementation plans, and executable tasks from goals through structured AI dialogue. Use when user says "write requirements", "create spec", "plan implementation", "derive tasks", "structure this feature", "break down into tasks", or "document this module". Also use for reverse engineering existing code into docs (/deckrd rev). Do NOT use for direct code writing — use /deckrd-coder after tasks are generated. Do NOT use when the user only wants to run or fix existing code without planning.
clinical-decision-support
IncludedGenerate professional clinical decision support (CDS) documents for pharmaceutical and clinical research settings, including patient cohort analyses (biomarker-stratified with outcomes) and treatment recommendation reports (evidence-based guidelines with decision algorithms). Supports GRADE evidence grading, statistical analysis (hazard ratios, survival curves, waterfall plots), biomarker integration, and regulatory compliance. Outputs publication-ready LaTeX/PDF format optimized for drug development, clinical research, and evidence synthesis.
handling-sf-data
IncludedSalesforce data operations with 130-point scoring. Use this skill to create, update, delete, bulk import/export, generate test data, and clean up org records using sf CLI and anonymous Apex. TRIGGER when: user creates test data, performs bulk import/export, uses sf data CLI commands, needs data factory patterns for Apex tests, or needs to seed/clean records in a Salesforce org. DO NOT TRIGGER when: SOQL query writing only (use querying-soql), Apex test execution (use running-apex-tests), or metadata deployment (use deploying-metadata).
accelint-ac-to-playwright
IncludedConvert and validate acceptance criteria for Playwright test automation. Use when user asks to (1) review/evaluate/check if AC are ready for automation, (2) assess if AC can be converted as-is, (3) validate AC quality for Playwright, (4) turn AC into tests, (5) generate tests from acceptance criteria, (6) convert .md bullets or .feature Gherkin files to Playwright specs, (7) create test automation from requirements. Handles both bullet-style markdown and Gherkin syntax with JSON test plan generation and validation.