smithery/elevanaltd

debate-hall-auto

Automated Wind/Wall/Door debate orchestration with tier-based model selection.

Installation

$ npx skills add smithery/elevanaltd --skill debate-hall-auto

Similar popular skills

Related neighbors and high-traction skills in the same topics — useful to compare before installing.

Also in this package

Other skills from smithery/elevanaltd.

npx skills add smithery/elevanaltd

Browse all from smithery/elevanaltd

More details

Agent compatibility

Declared targets from SKILL.md / docs. Unmarked agents are not listed — the skill may still install via the CLI.

Claude Code Not declared
Cursor Not declared
Codex Not declared
GitHub Copilot Not declared
Windsurf Not declared
Gemini CLI Not declared
Cline Not declared
OpenCode Not declared

Skill metadata

Parsed from SKILL.md frontmatter.

Allowed toolsRead, mcp__debate-hall__run_debate, mcp__debate-hall__resolve_question, mcp__debate-hall__resume_debate, mcp__debate-hall__search_decisions

Package contents

Files included with this skill beyond the listing page.

  • skill md SKILL.md 3,486 B
  • docs SUMMARY.md 102 B

History

  1. First recorded snapshot · 0 installs

SKILL.md

===DEBATEHALLAUTO===

META: TYPE::SKILL[FOCUSED] VERSION::"1.0" PURPOSE::"Automated debate orchestration via rundebate and resolvequestion" ROUTER::debate-hall

§1::TOOLS

RUNDEBATE::[ PURPOSE::"Single-call automated Wind/Wall/Door debate", PARAMS::[ topic::REQUIRED[questionordecision], tier::"fast"|"standard"|"premium"[default:standard], threadid::OPTIONAL[autogeneratedifomitted], compressiontier::"none"|"basic"|"aggressive"|"ultra", primertier::"none"|"literacy"|"standard"|"advanced" ], RETURNS::synthesis+turncount+status ]

RESOLVEQUESTION::[ PURPOSE::"Highest-level API - debate + decision record in one call", PARAMS::[topic::REQUIRED,tier::OPTIONAL,threadid::OPTIONAL], RETURNS::DecisionRecord[thread_id,synthesis,rationale,validation,provenance] ]

RESUMEDEBATE::[ PURPOSE::"Continue PAUSED debates after provider timeouts", PARAMS::[threadid::REQUIRED,tier::OPTIONAL], USE_WHEN::status="PAUSED" ]

SEARCHDECISIONS::[ PURPOSE::"Find past decisions by topic", PARAMS::[query::REQUIRED,limit::10,minscore::0.0], RETURNS::rankedresults[threadid,topic,synthesis,score] ]

§2::TIER_CONFIGURATIONS

FAST::[ COST::~$0.02, MODELS::[gemini-3-flash,gpt-5.1-codex-mini,claude-haiku-4.5], MAXTURNS::6, CONSENSUS::false, USEFOR::[exploration,lowstakes,rapiditeration] ]

STANDARD::[ COST::~$0.30, MODELS::[gemini-3-pro,gpt-5.2-codex,claude-sonnet-4.5], MAXTURNS::12, REFINEMENTLOOPS::4, USEFOR::[designdecisions,medium_complexity] ]

PREMIUM::[ COST::~$0.60, MODELS::[claude-opus-4.5,gpt-5.2-pro,gemini-3-pro], MAXTURNS::16, REFINEMENTLOOPS::5, CONSENSUS::true, USEFOR::[productiondecisions,high_stakes] ]

§2.1::AGENT_ROLES // Restored from monolith §5

TIER1BASIC::[ AGENTS::[wind-agent,wall-agent,door-agent], BEHAVIOR::[exploresobviouspaths,balancedjudgment,balancedintegration], MAPPEDTO::fasttier ] TIER2SPECIALIST::[ PATHOS::[ideator[minimalelegant],edge-optimizer[hiddenvectors]], ETHOS::[validator[coldtruth],critical-engineer[productionreadiness]], LOGOS::[synthesizer[breakthrough1+1=3],technical-architect[systemdesign]], MAPPEDTO::standardandpremiumtiers ] MAPPING::specialists→cognition_role[PATHOS→Wind,ETHOS→Wall,LOGOS→Door]

§3::EXAMPLES

QUICK::rundebate("Redis vs Memcached for sessions?",tier:"fast") STANDARD::rundebate("API versioning strategy?",tier:"standard") PREMIUM::resolve_question("Migrate PostgreSQL to CockroachDB?",tier:"premium")

GRAVITYHINTS::[ fast::[namingconventions,uitweaks,toolingchoices], standard::[apidesign,moduleboundaries,testingstrategy], premium::[securityarchitecture,datamodel,externalcontracts] ]

§4::BESTPRACTICES TIERSELECTION::"Match tier to decision gravity" ESCALATION::"If fast insufficient, re-run with premium" THIRD_WAY::"Best debates synthesize what neither Wind nor Wall proposed alone"

===END===