Agent skill · Testing & QA

pre-motion-andrew-bird

Adversarial premortem for England & Wales civil litigation - builds the strongest version of a case, then attacks it from four angles to find where it loses before opposing counsel does. Runs an adversarial premortem on a UK litigation matter. Builds the strongest version of the case, then attacks it from four angles — procedural, substantive, evidentiary, strategic — to find where it actually loses. Returns a ranked stress-test brief: failure scenarios, evidence inconsistencies, blind spots, mitigations, and one brutal one-sentence verdict. Use before issue, before settlement negotiations, be

lawve-aigithub.com/lawve-aiGitHub ↗
claude-codeNOASSERTION
Install
npx skills add lawve-ai/awesome-legal-skills --skill pre-motion-andrew-bird --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 2
SKILL.md size: 8 KB
Bundled scripts: none
Version: 2026-06-05
Declared author: Andrew Bird
Path: skills/pre-motion-andrew-bird/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 618
Language: Python

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

From the SKILL.md

# Pre-Motion — adversarial premortem for UK litigation You think you've built the strongest version of your case. Pre-Motion runs it through a structured adversarial pipeline to find where it actually loses — the procedural, substantive, evidentiary, and strategic failure modes opposing counsel will pull on first. The opposite of confirmation bias, by design. For: solicitors stress-testing before issue, in-house counsel before sign-off, mediators valuing settlement, litigation funders pricing a matter, anyone deciding whether to take a case. ## How it runs Four passes over the matter. Run the four adversarial passes in Stage 3 as parallel sub-agents if your environment supports them; otherwise run them in sequence — the method and the output are the same either way. 1. **Optimistic baseline.** Build the strongest version of the case the evidence supports. This is the foil for everything that follows. 2. **Evidence inspection.** Three checks: document review (gaps, weak documents), cross-reference (one document contradicting another), chronology (timeline gaps, dates that don't fit). Produce evidence flags with a severity each. 3. **Premortem adversary.** Four adversarial passes, on

What's inside
Steps it walks through
  1. How it runs
  2. Inputs
  3. Step 1 — Permitted-use check (CPR 31.22 + privilege)
  4. Failure-mode categories
  5. Procedural
  6. Substantive
  7. Evidentiary
  8. Strategic
  9. Output
  10. What this skill does not do
  11. v0.2 roadmap
Ships with 1 file
  • README.md
More from awesome-legal-skills
All skills →
About this skill
What does the pre-motion-andrew-bird skill do?

Adversarial premortem for England & Wales civil litigation - builds the strongest version of a case, then attacks it from four angles to find where it loses before opposing counsel does. Runs an adversarial premortem on a UK litigation matter. Builds the strongest version of the case, then attacks it from four angles — procedural, substantive, evidentiary, strategic — to find where it actually loses. Returns a ranked stress-test brief: failure scenarios, evidence inconsistencies, blind spots, mitigations, and one brutal one-sentence verdict. Use before issue, before settlement negotiations, be

How do I install it?

Run `npx skills add lawve-ai/awesome-legal-skills --skill pre-motion-andrew-bird --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.

Where does this skill come from?

From lawve-ai/awesome-legal-skills, a repository with 618 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.

Is a popular skill a good skill?

Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.

Keep going