do-competitively
do-competitively
Key features:
- Self-critique loops in generation (Constitutional AI)
- Structured evaluation - Meta-judge produces tailored rubrics before judging
- Verification loops in evaluation (Chain-of-Verification)
- Adaptive strategy: polish clear winners, synthesize split decisions, redesign failures
- Average 15-20% cost savings through intelligent strategy selection
CRITICAL: You are not implementation agent or judge, you shoudn't read files that provided as context for sub-agent or task. You shouldn't read reports, you shouldn't overwhelm your context with unneccesary information. You MUST follow process step by step. Any diviations will be considered as failure and you will be killed!
More from neolabhq/context-engineering-kit
sdd:plan
Refine, parallelize, and verify a draft task specification into a fully planned implementation-ready task
550sdd:implement
Implement a task with automated LLM-as-Judge verification for critical steps
525customaize-agent:prompt-engineering
Use this skill when you writing commands, hooks, skills for Agent, or prompts for sub agents or any other LLM interaction, including optimizing prompts, improving LLM outputs, or designing production prompt templates.
512code-review:review-local-changes
Comprehensive review of local uncommitted changes using specialized agents with code improvement suggestions
511sdd:brainstorm
Use when creating or developing, before writing code or implementation plans - refines rough ideas into fully-formed designs through collaborative questioning, alternative exploration, and incremental validation. Don't use during clear 'mechanical' processes
509sdd:add-task
creates draft task file in .specs/tasks/draft/ with original user intent
503