darwin-skill
alchaincyf
达尔文.skill —— 一个让你的Skill无限进化的系统:评估→改进→测试→保留或回滚 | Autoresearch-inspired autonomous skill optimization for Claude Code. Evaluate, improve, test, keep or revert.
GITHUB TOPIC
13projects include this topic
The "evaluation" topic on GitHub groups 13 open-source projects in the DeepSeek Harness (DSH) ecosystem, led by darwin-skill with 6.8k GitHub stars. darwin-skill — 达尔文. Every project here is indexed by DSH Universe with live GitHub data — stars, activity and install status — so you can compare and install directly.
{count} projects
Exact GitHub Topic match
alchaincyf
达尔文.skill —— 一个让你的Skill无限进化的系统:评估→改进→测试→保留或回滚 | Autoresearch-inspired autonomous skill optimization for Claude Code. Evaluate, improve, test, keep or revert.
Sahir619
The Fable Workflow: how Claude Fable 5 worked, distilled into skills any model can run, with the eval that keeps it honest. Think / act / prove.
BiBoyang
DSH plugin eval tool: YAML case-driven real agent regression eval + baseline comparison PASS/WARN/FAIL gates|Regression eval harness for DeepSeek Harness plugins
Apageoflove
Local-first experiment and evaluation workbench plugin for DeepSeek Harness (DSH).
aryswisnu
No project description provided for this repository yet.
young-tim
Reproducible DSH profile and patch experiment matrices with reports and policy gates
xu-jin-cs
Mechanical gates + skills that make LLM coding agents keep their promises — agent capability evaluation (9-dim radar/rank reports), parallel dispatch, architecture mapping. Plain SKILL.md, zero lock-in. CC BY-NC-SA 4.0.
bradheitmann
Tiered model routing with evidence-based disqualification: a harness-neutral skill, a Rust engine and CLI, a hosted MCP server (Cloudflare Worker in Rust) and a dsh adapter.
CZ-ZL
Composable DSH-native evaluation and optimization with explicit evidence modes, bounded budgets and traceable results
hj01857655
DeepSeek Harness 插件集合(monorepo):context-memory / verdict / theme-studio / cost-track / model-arena / prompt-vcs / step-trace / tool-stats / spill-hygiene
hj01857655
Measure whether a change to your dsh setup actually helped: register repeatable cases, run them, diff before/after. DeepSeek Harness plugin.
ruby1304
Public, reusable DeepSeek Harness plugins and skills: workflow canvas toolkit, blind eval harness, LLM cost lab, incident ledger.
ubik-dsh
Clean, portable agent skills for DeepSeek Harness, Claude Code and any harness reading the Agent Skills standard. Plain text, nothing to build. Every skill ships a checker and a measured evaluation protocol — and says what was not verified.