expert-impeachment
Surfaces inconsistencies, opinion shifts, methodological flaws, and credential discrepancies across expert reports, transcripts, CVs, and publications for impeachment, cross-examination, and exclusion motions. Trigger when the user references expert impeachment, expert report analysis, Daubert or Frye challenges, deposition prep against an expert, or credibility attacks on opposing expert witnesses.
Best use case
expert-impeachment is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Surfaces inconsistencies, opinion shifts, methodological flaws, and credential discrepancies across expert reports, transcripts, CVs, and publications for impeachment, cross-examination, and exclusion motions. Trigger when the user references expert impeachment, expert report analysis, Daubert or Frye challenges, deposition prep against an expert, or credibility attacks on opposing expert witnesses.
Teams using expert-impeachment should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/expert-impeachment/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How expert-impeachment Compares
| Feature / Agent | expert-impeachment | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Surfaces inconsistencies, opinion shifts, methodological flaws, and credential discrepancies across expert reports, transcripts, CVs, and publications for impeachment, cross-examination, and exclusion motions. Trigger when the user references expert impeachment, expert report analysis, Daubert or Frye challenges, deposition prep against an expert, or credibility attacks on opposing expert witnesses.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# Expert Witness Impeachment Builds a citation-ready inconsistency map to challenge expert credibility, reliability, and admissibility. ## Quick Start 1. Collect all expert materials: reports, supplements, rebuttals, deposition/trial transcripts, declarations, CV, publications, prior testimony, data/appendices. 2. Confirm page/line or Bates-citable versions of each source. 3. Identify the case theory, key disputed issues, and governing admissibility standard (Daubert, Frye, or local rule). 4. Proceed through the workflow steps below in order. ## Workflow ### 1. Source Inventory Build a table of every source document with columns: Source, Date, Type, Citation Format, Notes. ### 2. Opinion Chronology Map the expert's opinions over time with columns: Date, Document/Testimony, Key Opinion Statement, Cite. Track how positions evolved across filings. ### 3. Inconsistency Log For each inconsistency found, log: - **ID** — unique identifier - **Category** — one of: `Opinion Change`, `Methodology`, `Facts/Assumptions`, `Credentials`, `Scope Creep`, `Prior Testimony Conflict`, `Publication Conflict`, `Math/Calculation Error` - **Statement A** and **Statement B** — exact quotes with pinpoint cites - **Delta** — nature of the conflict - **Materiality** — H/M/L - **Admissibility Impact** — Reliability, Fit, Qualifications, or combination - **Explanation Offered** — any justification on record - **Cross-Exam Hook** — suggested line of questioning ### 4. Methodology Audit - Identify each dataset, test, model, or protocol relied upon. - Confirm consistent application across reports and testimony. - Flag changes in assumptions, variables, or inputs without explanation. - Flag conclusions not supported by stated method. - Note departures from the expert's own published standards or prior testimony. - Record concessions on limitations, error rates, or missing data. ### 5. Credentials & Bias Check Verify each claimed credential. Log: Claim, Source, Verification Status, Conflict, Materiality. Flag financial bias, repeat retention patterns, and advocacy history. ### 6. Materiality & Strategy Ranking Rank each inconsistency ID by: relevance to core issues, expected defense, backfire risk, and recommended use (Motion / Cross / Both). Prioritize contradictions tied to disputed issues or damages. ### 7. Cross-Examination Questions For each high-priority ID, draft 3–6 tight questions following this pattern: - Lock in Statement A (cite) - Confirm Statement B (cite) - Force the inconsistency - Tie to reliability/fit - Obtain concession on impact to opinion ### 8. Admissibility Analysis - Map high-priority inconsistencies to governing standard elements (reliability, relevance/fit, qualifications). - Note curative explanations and whether the record supports them. - Draft a motion-ready paragraph per high-priority ID. ## Pitfalls - Always use exact quotes with pinpoint citations; paraphrasing undermines impeachment value. - Treat evolving opinions as impeachment only when unsupported by new data or analysis. - Do not assume Daubert applies — verify the governing standard and local rules. - Separate peripheral inconsistencies from motion-worthy defects; over-inclusion dilutes impact. - Flag any legal citations or standards with `[VERIFY]` if uncertain. - Avoid character attacks; focus strictly on record-supported reliability and fit.