Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Adversarial Debate Protocol · yogsoth-ai | DecimalAI

agent toolingby yogsoth-ai

Adversarial Debate Protocol

yogsoth-ai/adversarial-debate-protocol

Source yogsoth-ai/de-anthropocentric-research-engine ↗License Apache-2.0

Structured debate protocol that constructs an advocate, deploys critic attacks, and renders a judge verdict through iterative rounds.

SkillScore55Maintained

Automatic

Research pack

Last verified 8/22/2026

What it changes

Passed 12 of 22 test cases with the skill, and 5 of 22 without it.

Without skill23%

With skill55%

Checks it passed that the model alone missed

Judge verdict uses standardized terms ACCEPT, REJECT, or REVISE.
Critic rates attack severity using HIGH, MEDIUM, or LOW categories.
Advocate case provides explicit reasoning for the proposed position.

and 12 more in the full report

9 fixed3 passed either way8 still failing2 broke

Pass-rate lift: +32 pp
Tokens: +46%
Agent turns: 0%
Response time: +24%

Model gemini-3.6-flashMeasured 8/22/2026v112 of 22 cases passed with skill

Tokens, turns and time describe resource use, not a dollar price.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/yogsoth-ai-adversarial-debate-protocol/SKILL.md https://app.decimal.ai/s/yogsoth-ai-adversarial-debate-protocol/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add yogsoth-ai-adversarial-debate-protocol, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/yogsoth-ai-adversarial-debate-protocol/ and pins it in .decimal/skills.lock

decimalai skills add yogsoth-ai-adversarial-debate-protocol

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/yogsoth-ai-adversarial-debate-protocol/SKILL.md https://app.decimal.ai/s/yogsoth-ai-adversarial-debate-protocol/SKILL.md

Raw file: /s/yogsoth-ai-adversarial-debate-protocol/SKILL.md ↗ · machine-readable summary at /s/yogsoth-ai-adversarial-debate-protocol.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 9 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 9

Prompt

We are considering splitting our core monolithic backend into a microservices architecture. I want us to run a formal adversarial debate on this proposed migration. Please outline the strongest arguments in favor, systematically attack those points with rated counter-arguments, and provide an impartial final decision on whether we should proceed, modify, or reject the plan, making sure to explicitly address each objection.

What was checked, without and with the skill
Checked	Without skill	With skill
Critic counter-arguments utilize severity ratings of HIGH, MEDIUM, or LOW.	Missed	Passed
Final verdict uses one of the standardized terms ACCEPT, REJECT, or REVISE.	Missed	Passed
When judge issues REVISE, the evaluation executes a second iteration round.	Missed	Passed

case-01 · gemini-3.6-flash · 8/22/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md48 linessingle file

Adversarial Debate Protocol

A formal three-role debate structure ensuring decisions survive rigorous adversarial challenge. The protocol assigns distinct roles (advocate, critic, judge) to prevent confirmation bias and ensure intellectual honesty.

Stages

Advocate Construction — Build the strongest possible case for the position under debate
Critic Attack — Attack the advocate's case from multiple angles with severity ratings
Judge Verdict — Impartial assessment of advocate case vs critic attacks, rendering ACCEPT/REJECT/REVISE
Iteration (if REVISE) — Advocate revises case, critic re-attacks, judge re-evaluates

Available SOPs

SOP	Role	Purpose
advocate-construction	Advocate	Build strongest case for position
critic-attack	Critic	Attack the case with rated arguments
judge-verdict	Judge	Render impartial verdict

Execution Guidance

Minimum 2 rounds before accepting ACCEPT verdict
Critic must produce >= 3 distinct attack arguments per round
Judge must address every critic argument explicitly
If judge verdict is REVISE, advocate must address specific weaknesses identified
Maximum 4 rounds before escalating to strategy level

Minimum Yield

Advocate case with explicit evidence and reasoning
Critic attacks with severity ratings (HIGH/MEDIUM/LOW)
Judge verdict (ACCEPT/REJECT/REVISE) with point-by-point reasoning
Conditions for acceptance (if ACCEPT)
Required modifications (if REVISE)

Available SOPs

Optional, no fixed order; the final leaf is always a sop.

Track record

Benchmark

12 / 22

test cases passed, vs 5 / 22 without

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

yogsoth-ai / de-anthropocentric-research-engine

skills/adversarial-debate-protocol/SKILL.md

View on GitHub ↗

License Apache-2.0Imported 8/3/2026Version v1

More skills from the same source and nearby in the registry, with their headline benchmark lift.

Ready to supercharge your AI agents?

See it in action

What's inside

Adversarial Debate Protocol

Stages

Available SOPs

Execution Guidance

Minimum Yield

Available SOPs

Track record

Benchmark

Adoption

SkillSafety

Source

Related skills