Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
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

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Evidence Review

ASecurity

Cross-reference evidence across the entire case vault to find contradictions, patterns, and gaps. Use when the user says "review my evidence", "find contradictions", "what patterns do you see", "cross-reference my documents", "update the evidence matrix", "what am I missing", "analyse my whole case", or wants a strategic overview of their evidence position.

17 stars
0 votes
0 copies
1 views
Added 9/19/2026
research

Security Analysis

A100/100

Scanned 9/19/2026

Install to Claude Code

$npx -y skills add CaseForgeHq/family-court-strategist --skill evidence-review --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Evidence Review?

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

Security grade badge for Evidence Review
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/caseforgehq-evidence-review/badge)](https://www.skillsdirectory.com/skills/caseforgehq-evidence-review)

More formats (shields.io, HTML) on the badges page.

Download with Pro
Files
SKILL.md
---
name: evidence-review
description: >
  Cross-reference evidence across the entire case vault to find contradictions,
  patterns, and gaps. Use when the user says "review my evidence", "find
  contradictions", "what patterns do you see", "cross-reference my documents",
  "update the evidence matrix", "what am I missing", "analyse my whole case",
  or wants a strategic overview of their evidence position.
metadata:
  version: "0.2.0"
---

# Evidence Review

Perform a comprehensive cross-document analysis of the user's case vault. This is where individual document analyses get connected into case-level insights.

Read `_system/verified-facts.md` when present. Preserve VERIFIED facts and use their canonical references. Conflicting evidence must become a conflict review with the new source, never a silent replacement of the existing fact. Source-matched findings remain proposals until explicit human verification. Do not self-verify, resolve conflicts without human review, edit registry JSON or alter generated lock blocks. Use the toolkit fact command and run `check` before sharing dependent documents; if unavailable, preserve locks and report conflicts without changing the registry.

## What to Do

### 1. Read the Vault
Read the key structural files first:
- CASE-DETAILS.md (case basics)
- MASTER-TIMELINE.md (chronology)
- EVIDENCE-MATRIX.md (current evidence map)
- CROSS-DOCUMENT-ANALYSIS.md (existing contradictions)

Then read individual document analyses in `legal-documents/` and `communications/`.

### 2. Cross-Document Analysis

Run every document against every other document looking for:

**Timeline Conflicts** — Same event described with different dates or sequences across documents. Create a table showing Document A vs Document B.

**Statement Evolution** — How someone's story changes over time. Track specific claims from affidavit → report interview → court hearing. Changes in detail, emphasis, or framing are significant.

**Professional Opinion Conflicts** — Where experts, caseworkers, or other professionals disagree. Which opinion is better supported by independent evidence?

**Internal Contradictions** — Where a single document contradicts itself. Note both statements with paragraph references.

**Credibility Vulnerabilities** — Specific points where a party's credibility can be challenged. Build a list with evidence links.

### 3. Pattern Detection

Look across all evidence for:
- Contact blocking or avoidance patterns (track frequency, excuses, timing)
- Relationship interference indicators — often called "alienation" (child's adult-directed language, loyalty conflicts, rejection without cause). Track the behaviours with dates and sources; advise the user that courts are cautious about the "alienation" label, so the evidence should lead with documented behaviour, not the label
- Allegation timing (do new allegations appear before court dates?)
- System failures (recommendations not followed, assessments incomplete)
- Communication patterns (response rates, tone shifts, silence periods)

For each pattern: how many instances? How strong is the evidence? What would a court find compelling?

### 4. Gap Analysis

Identify what's MISSING:
- Documents that should exist but aren't in the vault
- People who should have been assessed but weren't
- Questions that should have been asked but weren't
- Records that could be subpoenaed
- Evidence that would strengthen weak claims

### 5. Update the Vault

After analysis, update:
- EVIDENCE-MATRIX.md with new findings and strength ratings
- CROSS-DOCUMENT-ANALYSIS.md with new contradictions
- COINCIDENCE-MAP.md with timing alignments
- patterns.md with new or strengthened patterns

### 6. Strategic Summary

Present findings as:
1. **Strongest arguments** — your best evidence, why it's compelling
2. **Biggest risks** — where your case is weakest, what could undermine you
3. **Key contradictions** — the most damaging inconsistencies in the other side's case
4. **Missing evidence** — what you still need and how to get it
5. **Next steps** — prioritised actions

## Principles

- Think like a legal strategist, not a note taker
- Always link insights back to specific evidence with source references
- Focus on patterns over isolated events — courts care about behaviour over time
- Prioritise the child's wellbeing in every assessment
- Be honest about weaknesses in the user's case as well as strengths
- Never fabricate or exaggerate evidence

Attribution

CaseForgeHqCaseForgeHq
View sourceMore from CaseForgeHq →
SSkills DirectorySkills Directory

Know which skills are safe — weekly.

Best new skills + every skill we flagged as malicious. From the team that scanned 103,619.

Join free

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 DirectorySkills Directory

Know which skills are safe — weekly.

Best new skills + every skill we flagged as malicious. From the team that scanned 103,619.

Join free

Related Skills

Competitor Analysis

This skill provides comprehensive analysis of competitor SEO and GEO strategies, revealing what's working in your market and identifying opportunities to outperform the competition.

1823 votes

Deep Research

Universal deep research agent team. 13-agent pipeline for rigorous academic research on any topic. 8 modes: full research, quick brief, paper review, lit-review, fact-check, three-way literature scan, Socratic guided research dialogue, and systematic review with optional meta-analysis. Covers research question formulation, Socratic mentoring, methodology design, systematic literature search, source verification, cross-source synthesis, risk of bias assessment, meta-analysis, APA 7.0 report co...

492472 votes

Paperclip Distill

Use when an operation issue is a Paperclip cursor-window, distill, or backfill — `operationType: "distill"` or `"backfill"` and the body references a Paperclip source bundle for a project or root issue. Turn raw Paperclip activity into a wiki-insightful project page, decisions log, and history note. This skill exists specifically to replace the stiff, datestamp-heavy templated output that the deterministic distiller produces.

813271 votes

Academic Pipeline

Orchestrator for the full academic research pipeline: research -> write -> integrity check -> review -> revise -> re-review -> re-revise -> final integrity check -> finalize. Coordinates deep-research, academic-paper, and academic-paper-reviewer into a seamless 10-stage workflow with mandatory, coverage-bounded integrity checks, two-stage peer review, and auditable quality-assurance artifacts. Triggers on: academic pipeline, research to paper, full paper workflow, paper pipeline, end-to-end p...

492471 votes

Exa Search

Semantic search, similar content discovery, and structured research using Exa API

304951 votes
View all in research →