Agent skill · Code Review & Quality

unfair-dismissal-screener-andrew-bird

Screens a dismissal — proposed or already done — against the unfair dismissal framework for England & Wales, and shows where it is exposed. Structures the qualifying-service question, the automatically-unfair categories (no qualifying period), and a Burchell / Polkey / band-of-reasonable-responses analysis for a solicitor to verify — it does not determine fairness. Surfaces specific procedural risks. Use when the user says 'is this unfair', 'screen this dismissal', 'ordinary unfair dismissal', 'automatic unfair dismissal', or wants a structured fairness review before or after dismissal.

lawve-aigithub.com/lawve-aiGitHub ↗
claude-codeNOASSERTION
Install
npx skills add lawve-ai/awesome-legal-skills --skill unfair-dismissal-screener-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: 10 KB
Bundled scripts: none
Version: 2026-06-12
Declared author: Andrew Bird
Path: skills/unfair-dismissal-screener-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

# /unfair-dismissal-screener This skill structures an analysis for a solicitor to verify. It does not determine whether a dismissal was fair — that is the Tribunal's call, on facts and witnesses this prompt never sees. 1. Frame the qualifying service question (s.108 ERA): two years continuous service, **unless** the dismissal falls within an automatically unfair category (no qualifying period required). 2. Identify the potentially fair reason advanced (s.98(2)): conduct, capability, redundancy, illegality, some other substantial reason. If none, s.98(1) — burden on employer to show fair reason. 3. Structure the Burchell analysis (conduct cases): reasonable belief, reasonable investigation, dismissal within the band of reasonable responses. 4. Structure the Polkey question (procedural fairness): if the dismissal was procedurally unfair, what was the chance it would have happened anyway? Reduces compensatory award. 5. Note the ACAS Code position: failure to follow can produce up to 25% uplift (s.207A TULR(C)A 1992). 6. Output an indicative risk score with the reasoning visible — for a solicitor to check, not a prediction. Mark every authority you cannot pin to a section or case with

What's inside
Steps it walks through
  1. Purpose
  2. Qualifying service gate (s.108 ERA 1996)
  3. Potentially fair reasons (s.98(2) ERA)
  4. Burchell test (conduct dismissals — British Home Stores v Burchell)
  5. Polkey (procedural fairness — Polkey v A.E. Dayton Services)
  6. ACAS Code uplift
  7. Workflow
  8. Step 1 — Eligibility
  9. Step 2 — Reason
  10. Step 3 — Fairness
  11. Step 4 — Procedure
  12. Step 5 — Polkey + ACAS adjustments
  13. Step 6 — Output
  14. Output
Ships with 1 file
  • README.md
More from awesome-legal-skills
All skills →
About this skill
What does the unfair-dismissal-screener-andrew-bird skill do?

Screens a dismissal — proposed or already done — against the unfair dismissal framework for England & Wales, and shows where it is exposed. Structures the qualifying-service question, the automatically-unfair categories (no qualifying period), and a Burchell / Polkey / band-of-reasonable-responses analysis for a solicitor to verify — it does not determine fairness. Surfaces specific procedural risks. Use when the user says 'is this unfair', 'screen this dismissal', 'ordinary unfair dismissal', 'automatic unfair dismissal', or wants a structured fairness review before or after dismissal.

How do I install it?

Run `npx skills add lawve-ai/awesome-legal-skills --skill unfair-dismissal-screener-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