Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add NEU-ZHA/legal-ai-skills --skill legal-citation-comprehensivegit clone --depth 1 https://github.com/NEU-ZHA/legal-ai-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/neu-zha/legal-ai-skills/legal-citation-comprehensive)<a href="https://agentmods.dev/skills/neu-zha/legal-ai-skills/legal-citation-comprehensive"><img src="https://agentmods.dev/badge/skills/neu-zha/legal-ai-skills/legal-citation-comprehensive/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/neu-zha/legal-ai-skills/legal-citation-comprehensive"><img src="https://agentmods.dev/badge/skills/neu-zha/legal-ai-skills/legal-citation-comprehensive.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Rogue Agent · line 160 Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.Fix: Prevent the skill from modifying its own code, SKILL.md, or configuration files. Treat skill files as read-only at runtime.
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00119 | $0.02651 |
| Opus 5.5 | $0.00048 | $0.01060 |
| Sonnet 5.5 | $0.00024 | $0.00530 |
| Haiku 4.5 | $0.00012 | $0.00265 |
Grade A, and why
legal-citation-comprehensive scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Legal Citation Comprehensive
Role
This skill is the citation brain. It diagnoses and generates citation text. It does not edit Word files directly; use legal-citation-automator for DOCX insertion.
Primary rule: never invent missing bibliographic facts. If a required element is absent and cannot be extracted from a provided source, mark it as [待补: 要素名] and tell the user where to find it.
Completeness rule: the simplified templates are not the whole handbook. Before giving a final answer for any non-trivial citation, consult a legally obtained copy of the citation handbook or a user-provided rule index. This public repository does not redistribute third-party handbook PDFs or OCR dumps. Use references/citation_rules.json only as a fast execution layer when the user or local installation provides it.
Weak-agent guardrail: if you are unsure, do not improvise. Follow references/operator_guardrails.md exactly. A citation answer is not complete unless it states the source type, missing elements, lookup path, suggested format, and relevant handbook rule numbers.
Quick Workflow
- Classify the citation type.
- Search the user-provided handbook/rule index for the source category and rule numbers.
- Use
references/citation_rules.jsonfor required elements, templates, and handbook anchors when that optional local reference file is available. - If the repository lacks full reference data, stop at diagnosis/placeholders and tell the user what source material is needed.
- Extract existing elements from the messy footnote or supplied source.
- Diagnose missing required and optional elements.
- Give source lookup guidance from
references/source_lookup_guide.md. - Generate a standard citation.
- If complete: output the final footnote.
- If incomplete: output a placeholder version and a precise checklist.
- For Chinese Civil Law homework, apply the course-specific statute rule:
- If正文 only names a statute article, the footnote should include the article text.
- If正文 already quotes the full article and the footnote adds nothing, omit the footnote.
- Run
python scripts/self_test.pyafter changing this skill or before distributing it. Full handbook coverage tests require locally supplied reference data.
What ships with it
12 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/citation_types.md 16 KB
- references/common_errors.md 14 KB
- references/missing_elements_matrix.md 2.2 KB
- references/operator_guardrails.md 4.0 KB
- references/README_REFERENCE_DATA.md 3.5 KB
- references/source_lookup_guide.md 2.4 KB
- scripts/analyze_citation.py 34 KB runs code
- scripts/audit_reference_data.py 11 KB runs code
- scripts/build_reference_data.py 26 KB runs code
- scripts/citation_diagnose.py 18 KB runs code
- scripts/handbook_lookup.py 2.1 KB runs code
- scripts/self_test.py 7.9 KB runs code
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 184 lines · 119 tokens per session scan A 605d7e000445
legal-citation-comprehensive is a skill published in the GitHub repository NEU-ZHA/legal-ai-skills (68 stars, last pushed 18d ago), licensed MIT. It adds 119 tokens to every session and 2,651 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
fto-triage
Freedom-to-operate triage — a structured first look at potentially blocking patents, not an FTO opinion. Use when a product, process, or feature is being evaluated for blocking patents, when asked whether anything stops a launch, or to build a claim-chart first pass against the most plausible patents before patent…
legal-hold
Issue, refresh, release, or report on legal holds — drafts the hold notice as .docx, updates legalhold fields in log.yaml, and calendars the next refresh. Use when the user says "issue a hold", "refresh hold", "release hold", or asks for a portfolio-wide hold status report.
specification-writing
A workflow for writing complete patent specifications from patent claims and an invention disclosure. It adapts the document to a chosen jurisdiction, such as the US, Europe, or China.
terms-of-service
Draft terms of service and a companion privacy notice matched to the product's form and feature modules, not legal advice, delivered as a Word document.
x-scorecard
OpenSSF Scorecard for assessing open source project security. Check security best practices and compliance. Dependency: This is an x-cmd module. Install x-cmd first (see x-cmd skill for installation options). see x-cmd skill for installation.
ai-risk-management
Apply the NIST AI Risk Management Framework (AI RMF 1.0) and adjacent guidance to AI / ML systems — model lifecycle governance, fairness and bias evaluation, robustness, transparency, accountability, third-party model risk, monitoring for drift, and AI incident response. Broader than prompt-injection (which is the…