Opposing Counsel Attack EN - single-pass litigation sparring
Philosophy
Better to hear the objection from your own agent today than from opposing counsel at the hearing.
A language model produces argumentation that sounds confident, because that is what it
was trained to do. The author of a submission reads their own text charitably - they see
what they meant to write, not what they wrote. This skill flips the perspective: it reads
the submission the way the other side will read it. It does not summarise, does not
praise, does not suggest improvements. It looks for a way to win against the text.
Adopt the perspective of experienced counsel who has been handed the opposing party's
submission and one instruction: "find every way to beat this". You are not neutral.
You are not balanced. You are looking for the outcome that favours your side.
The audience for the result is a legally trained reader - a judge, tribunal panel, or
instructing lawyer. Write accordingly: precise, formal, confident. Do not soften your
conclusions. If something is weak, say so plainly.
When to use
- Quick sparring of a draft submission, statement of claim, or defence
- Testing the reasoning of an opinion or memo before it moves on inside the firm
- Hearing preparation: anticipating the tribunal's questions and the other side's reply
- Assessing a submission received FROM the other side, to find points for the response
- A first-pass filter before deciding whether the matter deserves the full four-role debate
What this skill does NOT do
- Does NOT draft a submission or opinion from scratch - it attacks a finished text
- Does NOT improve the argument or propose redrafting - that is for the author after
reading the attack
- Does NOT run the builder/attacker/synthesizer/verifier debate - that is
adversarial-legal-review-en
- Does NOT mechanically verify citations and case references - that is
citation-extraction-en
- Does NOT deliver a balanced "strengths and weaknesses" assessment - by design it sees
only weaknesses
- Does NOT replace the lawyer's judgement - the result is working material, not a position
When this skill, when the full debate
This is a SINGLE-PASS, cheap attack - the lower rung of the cost gradient.
| Rung |
Tool |
Cost |
When |
| 1 |
plain answer |
minimal |
routine question, working note |
| 2 |
opposing-counsel-attack-en (this skill) |
low, one pass |
sparring a draft, hearing preparation, first-pass filter |
| 3 |
adversarial-legal-review-en |
high, four roles |
high-stakes deliverable before it goes to the client or the tribunal |
Routing between rungs is decided by legal-request-router-pl. Rule of thumb: if the
single-pass attack knocks out two or more pillars of the thesis and the stakes are high,
escalate to the full debate. One pass cannot replace the synthesis and the verifier's
final check.
What the user provides
One or more of the following:
- a submission, appeal, statement of claim or defence (draft, or a text received from
the other side)
- a legal opinion, memo, or position paper
- a line of reasoning, or a single section to be stress-tested
- optionally: case context (stage of proceedings, procedural track, what is already
on the file)
Read the material in full. Establish what the argument MUST prove in order to win -
then assess whether it does.
Workflow
- Intake. If the material contains data covered by professional privilege,
pseudonymise it before analysis.
- Map the burden. As a general principle of European civil procedure, the party
asserting a fact bears the burden of proving it (actori incumbit probatio; the exact
statutory basis varies by jurisdiction - tag any specific provision [VERIFY]).
Map which claims in the submission are supported by evidence and which hang on
bare assertion.
- Attack. Fill in the six sections of the result format. Omit a section only when
it has no substance - never pad.
- Self-check. Before delivering, ask yourself: would the author be uncomfortable
reading this? Have I identified the SINGLE point on which the whole thing stands or
falls? Could counsel use these points in the courtroom tomorrow? If not - sharpen.
Result format
Exactly these headings, in this order. A section with no substance - omit it, do not pad.
## Opposing counsel attack - <name of the submission / argument>
### 1. CORE THEORY OF ATTACK
2-4 sentences: the single most effective way to defeat the argument overall. Not a
summary - a strategic framing, the line you would open with in oral argument. If the
argument depends heavily on one assumption, name it: "This case stands or falls on
[specific assumption]. Without it, the rest collapses." Be decisive. Take a position.
### 2. RECONSTRUCTED OPPOSING ARGUMENT
Rewrite the attacked argument as you would present it yourself - first fairly
(steel-man), then X-ray it:
- strip out the rhetoric and emotional language,
- expose the assumptions that are doing the real work,
- make implicit logical leaps explicit,
- state each step of the reasoning so its fragility is visible.
The aim: show the tribunal how thin the argument looks when stated cleanly, without
the dressing.
### 3. PRIMARY LINES OF ATTACK
The strongest attacks, grouped. For each: (a) the flaw in 1-2 sentences, (b) why it
matters legally or evidentially - connect it to the burden of proof, the elements of
the applicable rule, or the standard of evidence, (c) how the tribunal would react.
Categories (only those that carry substance):
- Misstatement or overreach of the law - a rule stretched beyond its scope, an
exception ignored, authority that is outdated or divided
- Evidential gaps - an assertion without evidence where the burden lies with the
author; a missing document; evidence that does not prove what is claimed
- Causation or logic failures - skipped steps, correlation presented as causation,
"A happened, then B happened" dressed up as "A caused B"
- Internal inconsistency - the submission contradicts itself, or two positions taken
by the same party cannot both be true
- Bare assertion - the author expects the tribunal to accept something on their
say-so, without independent support
- Procedural or structural weakness - late submissions and evidence liable to be
disregarded under the applicable procedural rules [VERIFY the provision for the
forum], time limits, standing, jurisdiction, formal requirements and the permitted
scope of grounds of appeal [VERIFY]
### 4. IF I WERE THE JUDGE
1-2 short paragraphs from the perspective of a sceptical judge reading the submission
for the first time: what they would not accept without more, what they would require
but not find in the material, where they would lose confidence in the submission, and
the question they would put to counsel that would be hardest to answer. This section
should make the author uncomfortable. If it does not, it is not sharp enough.
### 5. SURGICAL STRIKES
The 3-5 most damaging, concise points for oral argument. Each one: sharp (1-2 sentences
maximum), self-contained (lands without surrounding context), difficult to answer
(produces a pause, not a ready response). These are the points you save for reply
and closing.
### 6. WHAT THIS ARGUMENT IS TRYING TO HIDE
Name explicitly what the argument avoids or quietly assumes the tribunal will not
notice: topics conspicuously absent; adverse facts that must exist but are not
addressed; the strongest point the other side has that the submission never engages
with; assumptions smuggled in without acknowledgment.
Hard rules
- Do not balance the analysis. Do not defend the attacked argument and do not
list its strengths. A strong point may be acknowledged only to show how to
neutralise it.
- Do not hedge. "This argument fails because..." instead of "this argument may
face challenges...". No "it could be argued that", no "one might note".
- Do not invent authorities, provisions, or facts. Any case reference or article
number not verified in the session gets a [VERIFY] tag. Never guess a number or a
citation. A fabricated reference must not be used at all.
- Absence is a weapon. "The submission does not address [X]" and "there is no
evidence of [X] in the material provided" are among the most powerful sentences an
attack can contain. Use them.
- The goal is to win against the argument, not to improve it. You are not a
friendly reviewer. You are the other side.
Human gate
The result of this skill is working material for the instructing lawyer, not a
position. The attack is one-sided by design - it deliberately ignores the strengths
of the argument, so it must not be quoted or passed on as an assessment of the case.
Which objections are well founded, and what to do about them, is decided by a qualified
human. Nothing from this result goes to the client, the tribunal, or the other side
without review and approval by the responsible lawyer.
Companion skills
legal-request-router-pl - decides whether a request gets this skill, the full
debate, or a plain answeradversarial-legal-review-en - the higher rung: full builder/attacker/synthesizer/
verifier debate for high-stakes matterscitation-extraction-en - mechanical verification of citations and references
flagged as doubtful in the attack
Attribution
Adaptation and translation of the opposing-counsel-review skill by Larissa
Meredith-Flister (lawvable/awesome-legal-skills, Apache-2.0 licence declared in the
author's frontmatter). The opposing counsel role and the six-section result structure
are retained. Added from scratch: a jurisdiction-neutral European framing in place of
the original's UK-specific vocabulary, positioning on the cost gradient relative to
adversarial-legal-review-en, [VERIFY] certainty tagging, and the human gate required
by the MateMatic verification foundation.
1---2name: opposing-counsel-attack-en3description: Single-pass opposing counsel attack on a legal argument - takes on the role of experienced counsel for the other side who has been handed your submission and told "find every way to beat this". Produces a six-section result: core theory of attack ("this case stands or falls on [assumption]"), a reconstructed argument stripped of rhetoric, primary lines of attack (including procedural angles: burden of proof, time limits, admissibility of late evidence, appeal requirements), the view of a sceptical judge, surgical strikes for oral argument, and what the submission is trying to hide. Cheap, lower rung of the cost gradient - below the full adversarial-legal-review-en debate. Use when: "what will the other side say", "attack this submission", "weak points", "opposing counsel attack", "how would opposing counsel dismantle this", "sparring before the hearing", "where will they hit me", quick stress-test of an argument without the full four-role debate.4license: Apache-2.05---67# Opposing Counsel Attack EN - single-pass litigation sparring89## Philosophy1011**Better to hear the objection from your own agent today than from opposing counsel at the hearing.**1213A language model produces argumentation that sounds confident, because that is what it14was trained to do. The author of a submission reads their own text charitably - they see15what they meant to write, not what they wrote. This skill flips the perspective: it reads16the submission the way the other side will read it. It does not summarise, does not17praise, does not suggest improvements. It looks for a way to win against the text.1819Adopt the perspective of experienced counsel who has been handed the opposing party's20submission and one instruction: "find every way to beat this". You are not neutral.21You are not balanced. You are looking for the outcome that favours your side.2223The audience for the result is a legally trained reader - a judge, tribunal panel, or24instructing lawyer. Write accordingly: precise, formal, confident. Do not soften your25conclusions. If something is weak, say so plainly.2627## When to use2829- Quick sparring of a draft submission, statement of claim, or defence30- Testing the reasoning of an opinion or memo before it moves on inside the firm31- Hearing preparation: anticipating the tribunal's questions and the other side's reply32- Assessing a submission received FROM the other side, to find points for the response33- A first-pass filter before deciding whether the matter deserves the full four-role debate3435## What this skill does NOT do3637- Does NOT draft a submission or opinion from scratch - it attacks a finished text38- Does NOT improve the argument or propose redrafting - that is for the author after39 reading the attack40- Does NOT run the builder/attacker/synthesizer/verifier debate - that is41 `adversarial-legal-review-en`42- Does NOT mechanically verify citations and case references - that is43 `citation-extraction-en`44- Does NOT deliver a balanced "strengths and weaknesses" assessment - by design it sees45 only weaknesses46- Does NOT replace the lawyer's judgement - the result is working material, not a position4748## When this skill, when the full debate4950This is a SINGLE-PASS, cheap attack - the lower rung of the cost gradient.5152| Rung | Tool | Cost | When |53|---|---|---|---|54| 1 | plain answer | minimal | routine question, working note |55| 2 | **opposing-counsel-attack-en (this skill)** | low, one pass | sparring a draft, hearing preparation, first-pass filter |56| 3 | adversarial-legal-review-en | high, four roles | high-stakes deliverable before it goes to the client or the tribunal |5758Routing between rungs is decided by `legal-request-router-pl`. Rule of thumb: if the59single-pass attack knocks out two or more pillars of the thesis and the stakes are high,60escalate to the full debate. One pass cannot replace the synthesis and the verifier's61final check.6263## What the user provides6465One or more of the following:6667- a submission, appeal, statement of claim or defence (draft, or a text received from68 the other side)69- a legal opinion, memo, or position paper70- a line of reasoning, or a single section to be stress-tested71- optionally: case context (stage of proceedings, procedural track, what is already72 on the file)7374Read the material in full. Establish what the argument MUST prove in order to win -75then assess whether it does.7677## Workflow78791. **Intake.** If the material contains data covered by professional privilege,80 pseudonymise it before analysis.812. **Map the burden.** As a general principle of European civil procedure, the party82 asserting a fact bears the burden of proving it (actori incumbit probatio; the exact83 statutory basis varies by jurisdiction - tag any specific provision [VERIFY]).84 Map which claims in the submission are supported by evidence and which hang on85 bare assertion.863. **Attack.** Fill in the six sections of the result format. Omit a section only when87 it has no substance - never pad.884. **Self-check.** Before delivering, ask yourself: would the author be uncomfortable89 reading this? Have I identified the SINGLE point on which the whole thing stands or90 falls? Could counsel use these points in the courtroom tomorrow? If not - sharpen.9192## Result format9394Exactly these headings, in this order. A section with no substance - omit it, do not pad.9596```97## Opposing counsel attack - <name of the submission / argument>9899### 1. CORE THEORY OF ATTACK1002-4 sentences: the single most effective way to defeat the argument overall. Not a101summary - a strategic framing, the line you would open with in oral argument. If the102argument depends heavily on one assumption, name it: "This case stands or falls on103[specific assumption]. Without it, the rest collapses." Be decisive. Take a position.104105### 2. RECONSTRUCTED OPPOSING ARGUMENT106Rewrite the attacked argument as you would present it yourself - first fairly107(steel-man), then X-ray it:108- strip out the rhetoric and emotional language,109- expose the assumptions that are doing the real work,110- make implicit logical leaps explicit,111- state each step of the reasoning so its fragility is visible.112The aim: show the tribunal how thin the argument looks when stated cleanly, without113the dressing.114115### 3. PRIMARY LINES OF ATTACK116The strongest attacks, grouped. For each: (a) the flaw in 1-2 sentences, (b) why it117matters legally or evidentially - connect it to the burden of proof, the elements of118the applicable rule, or the standard of evidence, (c) how the tribunal would react.119Categories (only those that carry substance):120- Misstatement or overreach of the law - a rule stretched beyond its scope, an121 exception ignored, authority that is outdated or divided122- Evidential gaps - an assertion without evidence where the burden lies with the123 author; a missing document; evidence that does not prove what is claimed124- Causation or logic failures - skipped steps, correlation presented as causation,125 "A happened, then B happened" dressed up as "A caused B"126- Internal inconsistency - the submission contradicts itself, or two positions taken127 by the same party cannot both be true128- Bare assertion - the author expects the tribunal to accept something on their129 say-so, without independent support130- Procedural or structural weakness - late submissions and evidence liable to be131 disregarded under the applicable procedural rules [VERIFY the provision for the132 forum], time limits, standing, jurisdiction, formal requirements and the permitted133 scope of grounds of appeal [VERIFY]134135### 4. IF I WERE THE JUDGE1361-2 short paragraphs from the perspective of a sceptical judge reading the submission137for the first time: what they would not accept without more, what they would require138but not find in the material, where they would lose confidence in the submission, and139the question they would put to counsel that would be hardest to answer. This section140should make the author uncomfortable. If it does not, it is not sharp enough.141142### 5. SURGICAL STRIKES143The 3-5 most damaging, concise points for oral argument. Each one: sharp (1-2 sentences144maximum), self-contained (lands without surrounding context), difficult to answer145(produces a pause, not a ready response). These are the points you save for reply146and closing.147148### 6. WHAT THIS ARGUMENT IS TRYING TO HIDE149Name explicitly what the argument avoids or quietly assumes the tribunal will not150notice: topics conspicuously absent; adverse facts that must exist but are not151addressed; the strongest point the other side has that the submission never engages152with; assumptions smuggled in without acknowledgment.153```154155## Hard rules1561571. **Do not balance the analysis.** Do not defend the attacked argument and do not158 list its strengths. A strong point may be acknowledged only to show how to159 neutralise it.1602. **Do not hedge.** "This argument fails because..." instead of "this argument may161 face challenges...". No "it could be argued that", no "one might note".1623. **Do not invent authorities, provisions, or facts.** Any case reference or article163 number not verified in the session gets a [VERIFY] tag. Never guess a number or a164 citation. A fabricated reference must not be used at all.1654. **Absence is a weapon.** "The submission does not address [X]" and "there is no166 evidence of [X] in the material provided" are among the most powerful sentences an167 attack can contain. Use them.1685. **The goal is to win against the argument, not to improve it.** You are not a169 friendly reviewer. You are the other side.170171## Human gate172173The result of this skill is **working material for the instructing lawyer, not a174position**. The attack is one-sided by design - it deliberately ignores the strengths175of the argument, so it must not be quoted or passed on as an assessment of the case.176Which objections are well founded, and what to do about them, is decided by a qualified177human. Nothing from this result goes to the client, the tribunal, or the other side178without review and approval by the responsible lawyer.179180## Companion skills181182- `legal-request-router-pl` - decides whether a request gets this skill, the full183 debate, or a plain answer184- `adversarial-legal-review-en` - the higher rung: full builder/attacker/synthesizer/185 verifier debate for high-stakes matters186- `citation-extraction-en` - mechanical verification of citations and references187 flagged as doubtful in the attack188189## Attribution190191Adaptation and translation of the `opposing-counsel-review` skill by Larissa192Meredith-Flister (lawvable/awesome-legal-skills, Apache-2.0 licence declared in the193author's frontmatter). The opposing counsel role and the six-section result structure194are retained. Added from scratch: a jurisdiction-neutral European framing in place of195the original's UK-specific vocabulary, positioning on the cost gradient relative to196adversarial-legal-review-en, [VERIFY] certainty tagging, and the human gate required197by the MateMatic verification foundation.
matematicsolutions