Search
Better Tropes
fromfireside
A catalogue of 49 AI writing tells, each with a plain rewrite, shared by Fireside. Drop it into a system prompt to stop LLM output reading like LLM output.
...moreJuanjuan Team
dxkjuanjuan
🌀 The first adversarial-collaboration multi-agent Skill for Claude Code. 7 agents + 11 phases + Hook enforcement + 9 signal groups + dual-layer adversarial review. Inspired by NTCoding, agent-review-panel, AgentTeams. v1.6 — main+sub dual-layer adversarial review.
...morereact-pragmatic-router
Marcus Rognes
A simple react router for lazy people, without all the added complexity of react-router and the likes.
judgekit
Hadi Mohammadi
Audit an LLM judge before you trust it: agreement, bias probes, calibration and consistency, with bootstrap confidence intervals.
...morellm_runner
None
local-llmup
shashank-mishra-007
Hardware-aware CLI to recommend, install, serve, and migrate memory between local LLMs.
sayf-eval
A lightweight, model-agnostic framework for evaluating LLMs on cybersecurity benchmarks.
@allma/flow-builder
@webjema
TypeScript builder and CLI for authoring Allma flow definitions as code, with compile-time type safety and a deterministic JSON artifact.
...moreboruna
escapeboy
Boruna: a deterministic, capability-safe programming language and framework for LLM-native applications