Do Competitively
Skill Warnung AktivExecute tasks through competitive multi-agent generation, meta-judge evaluation specification, multi-judge evaluation, and evidence-based synthesis
To execute complex tasks by leveraging the strengths of multiple AI agents, ensuring high-quality, evidence-based results through a structured competitive evaluation process.
Funktionen
- Competitive generation with self-critique
- Meta-judge evaluation specification
- Multi-judge evaluation with verification loops
- Adaptive strategy selection (polish, synthesize, redesign)
- Evidence-based synthesis of results
Anwendungsfälle
- Designing complex APIs or systems where multiple approaches need evaluation.
- Generating and refining code for high-stakes projects requiring maximum quality.
- Producing comprehensive documentation or technical specifications through comparative agent output.
- Tasks where consensus among multiple AI perspectives is crucial for optimal outcome.
Nicht-Ziele
- Executing trivial tasks where the overhead of multi-agent competition is not justified.
- Simple code generation without comparative evaluation or synthesis.
- Replacing human oversight entirely; the framework aims to augment decision-making.
Workflow
- Create reports directory.
- Phase 1: Launch 3 generator agents and 1 meta-judge agent in parallel.
- Meta-judge generates evaluation specification YAML.
- Generators produce independent solutions.
- Phase 2: Launch 3 judges in parallel, evaluating solutions against meta-judge spec.
- Judges produce comparative reports and votes.
- Phase 2.5: Orchestrator analyzes judge outputs to select strategy (SELECT_AND_POLISH, REDESIGN, FULL_SYNTHESIS).
- Phase 3: Based on strategy, polish a winner, redesign fundamentally flawed solutions, or synthesize the best elements from multiple solutions.
- Output final solution and reports.
Documentation
- info:Configuration & parameter referenceThe SKILL.md provides a detailed workflow and prompt templates, but does not explicitly document all parameters or their default values for the `/do-competitively` command, nor does it detail precedence order for any configuration files.
License
- critical:License usabilityThe extension is licensed under GPL-3.0, which is a strong copyleft license and may not be compatible with all use cases or downstream redistribution plans.
Versioning
- warning:Release ManagementNo explicit versioning (e.g., semver in package.json or SKILL.md frontmatter) is detected, and installation instructions reference 'NeoLabHQ/context-engineering-kit' without a specific tag, which could lead to unexpected updates.
Installation
Zuerst Marketplace hinzufügen
/plugin marketplace add NeoLabHQ/context-engineering-kit/plugin install sadd@context-engineering-kitQualitätspunktzahl
WarnungVertrauenssignale
Ähnliche Erweiterungen
Ccg
99Claude-Codex-Gemini tri-model orchestration via /ask codex + /ask gemini, then Claude synthesizes results
Evaluation
98This skill should be used when the user asks to "evaluate agent performance", "build test framework", "measure agent quality", "create evaluation rubrics", or mentions LLM-as-judge, multi-dimensional evaluation, agent testing, or quality gates for agent pipelines.
Cli Creator
100Build a composable CLI for Codex from API docs, an OpenAPI spec, existing curl examples, an SDK, a web app, an admin tool, or a local script. Use when the user wants Codex to create a command-line tool that can run from any repo, expose composable read/write commands, return stable JSON, manage auth, and pair with a companion skill.
Context Mode Ops
100Verwalten Sie GitHub-Issues, PRs, Releases und Marketing mit parallelen Subagenten-Armeen im Context-Mode. Orchestriert 10-20 dynamische Agenten pro Aufgabe. Verwenden Sie dies bei der Triage von Issues, der Überprüfung von PRs, der Veröffentlichung von Versionen, dem Schreiben von LinkedIn-Posts, der Ankündigung von Releases, der Behebung von Fehlern, dem Mergen von Beiträgen, der Validierung von ENV-Variablen, dem Testen von Adaptern oder dem Synchronisieren von Branches.
Fixflow
100Führen Sie Codierungsaufgaben mit einem strengen Liefer-Workflow aus: Erstellen Sie einen vollständigen Plan, implementieren Sie Schritt für Schritt, führen Sie kontinuierlich Tests durch und committen Sie standardmäßig nach jedem Schritt (`per_step`). Unterstützt explizite Commit-Policy-Überschreibungen (`final_only`, `milestone`) und optional BDD (Given/When/Then), wenn Benutzer verhaltensgesteuerte Bereitstellung anfordern oder Anforderungen unklar sind.
Kotlin Mcp Server Generator
100Generate a complete Kotlin MCP server project with proper structure, dependencies, and implementation using the official io.modelcontextprotocol:kotlin-sdk library.