2389-research/speed-run · Archived
judge
Scoring framework for speed-run showdown and any-percent. Invoked at Phase 4 to evaluate implementations using 5-criteria scoring. Do not invoke directly -…
Installation
npx skills add https://github.com/2389-research/speed-run
Stronger alternatives
This repository is archived — consider an actively maintained alternative.
Token-efficient code generation pipeline using hosted LLM. Triggers on "speed-run", "fast build…
3 installsExplore different architectural approaches in parallel using hosted LLM for code generation. No…
3 installsSame design, multiple parallel runners compete using hosted LLM for code generation. Each runne…
3 installsDirect code generation via hosted LLM (Cerebras). Write a contract prompt, generate code, fix s…
3 installsSimilar popular skills
Related neighbors and high-traction skills in the same topics — useful to compare before installing.
Evaluate Agent Skill design quality against official specifications and best practices. Use whe…
4.1K installsEvaluate solutions through multi-round debate between independent judges until consensus
1.1K installsExecute a task with sub-agent implementation and LLM-as-a-judge verification with automatic ret…
1.1K installsLaunch a meta-judge then a judge sub-agent to evaluate results produced in the current conversa…
1.1K installsDesign LLM-as-Judge evaluators for subjective criteria that code-based checks cannot handle. Us…
680 installsEvaluate solutions through multi-round debate between independent judges until consensus
455 installsAlso in this package
Other skills from 2389-research/speed-run.
npx skills add https://github.com/2389-research/speed-run
More details
Agent compatibility
Declared targets from SKILL.md / docs. Unmarked agents are not listed — the skill may still install via the CLI.
Repository health
main
History
- First seen on skills.sh
- First recorded snapshot · 3 installs