Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Sgcite

ASecurity

Use when verifying Singapore court citations in legal submissions, checking for hallucinated cases in AI-generated text, or validating citations against eLitigation.

15 stars
0 votes
0 copies
1 views
Added 6/7/2026
ai-agentsbashgitdatabase

Security Analysis

A100/100

Scanned 6/7/2026

$npx -y skills add ThomasMoreAI/legal-skills-open --skill sgcite --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Sgcite?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Sgcite
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/thomasmoreai-sgcite/badge)](https://www.skillsdirectory.com/skills/thomasmoreai-sgcite)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: sgcite
title: sgcite — Singapore Court Citation Checker
description: Use when verifying Singapore court citations in legal submissions, checking for hallucinated cases in AI-generated text, or validating citations against eLitigation.
author: LegalQuants
author_url: https://github.com/LegalQuants/lq-skills/tree/main/skills/sgcite
license: Apache-2.0
version: 0.1.0
execution_mode: open
jurisdiction: sg
practice: litigation
language: en
tags: [citation, singapore, legal-research, hallucination-detection, elitigation]
---

# sgcite — Singapore Court Citation Checker

## When to Use

- Reviewing legal submissions before filing
- Checking AI-generated legal text for hallucinated citations
- Verifying that cited Singapore cases actually exist in eLitigation
- Detecting fabricated case names, paragraph references, or distorted quotations
- Routine citation audit for Singapore law documents

## How It Works

### Input

A legal text (submission, memo, brief, AI-generated draft) containing Singapore court citations.

### Process

1. **Extract** — Parse all case citations from the text
2. **Validate** — Query eLitigation (Singapore's case law database) for each citation
3. **Check** — Detect:
   - Hallucinated authorities (case doesn't exist)
   - Mismatched case names (case exists but different party names)
   - Fabricated paragraph references
   - Distorted quotations
4. **Report** — Flag each issue with specific location and explanation

### Output

```
✓ 5 citations verified
✗ 2 issues found:
  - [Para 23] "ABC v DEF [2023] SGHC 45" — Case not found in eLitigation
  - [Para 41] Quotation distorted — actual text differs from cited passage
```

## Example

```bash
npx sgcite check ./my-submission.docx
```

Or import as a library in your legal workflow tools.

## Audience and Work Shape

Audience: Singapore-qualified lawyers, paralegals, and litigation-support teams running a pre-filing or pre-circulation citation check. Not for unsupervised drafting or non-lawyer use.

Work shape: Pattern-Matched Review. Each citation is checked against a known reference (eLitigation). Output is a list of findings, not a sign-off.

## Scope and Legal Use

This skill provides legal *support*, not legal advice. A `verified` result means "the cited case was found in eLitigation with matching party names" — not "this citation is correctly used in your submission" and not "this submission is fit to file."

**Privilege and confidentiality.** sgcite sends extracted citation text (and quoted passages, when checking for distorted quotations) to eLitigation. Do not invoke on privileged or unfiled draft material unless your firm has assessed that routing the cited extracts through a public case-law database is acceptable. Configure the tool to send citation strings only (not surrounding context) where possible.

**Accountability.** A qualified lawyer must review each flagged and each `verified` citation before filing or circulating the submission. The skill does not sign off on accuracy of use, substantive correctness, or fitness to file.

## Confidence Bands

- **High** — citation extracted cleanly, eLitigation returns an exact match on case name and citation reference.
- **Medium** — citation matched on case name or reference but with a fuzzy hit, neutral citation variant, or paragraph reference not present in the source. Flag for lawyer review.
- **Low / Review** — possible distorted quotation, ambiguous case name, non-SG citation in input, or eLitigation lookup failed. Do not present as `verified`; route to REVIEW.

## Out of Scope

- Does not check substantive accuracy of cited holdings or whether the citation supports the proposition advanced.
- Does not cover non-Singapore citations or unreported decisions outside eLitigation.
- Does not constitute citation-review or quality-control sign-off for purposes of professional rules.
- Does not handle PDPA, privilege, or confidentiality-by-design — the user controls what text is passed in.

## Escalation

Stop and route to the responsible lawyer when:
- a citation cannot be resolved with High confidence after one pass;
- quoted text in the submission differs materially from the eLitigation source;
- the input appears to contain non-SG citations (treat as unsupported by this skill);
- the input contains material that may be privileged and the firm has not approved external lookups.

## Limitations

- Only covers Singapore court decisions in eLitigation
- Does not verify substantive accuracy of cited holdings
- Some unreported decisions may not be available

Attribution

ThomasMoreAIThomasMoreAI
View sourceSee grades on GitHubMore from ThomasMoreAI →
SSkills Directory ProSkills Directory

Get any skill into Claude in one click.

Download any skill as a ZIP for Claude.ai, Claude Desktop, or .claude/skills. $9/mo.

See Pro

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills Directory ProSkills Directory

Get any skill into Claude in one click.

Download any skill as a ZIP for Claude.ai, Claude Desktop, or .claude/skills. $9/mo.

See Pro

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

698431 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →